Papers.

Andrei Krovopuskov

Presents a fully automated pipeline for wrapping and cleaning up dozens of FACS expression scans using WrapAI to build silver-level likeness rigs in minutes.

Facial / Skinning

Eric Saindon, Sam Cole

Covers updates to Weta's muscle-driven APFS facial system and Bodyopt full-body skin-deformation network for performance-captured Avatar characters.

Facial / Muscles / Retargeting

Arad Mohammadi, Sebastian Weiss, Jakob Buhmann, Loic Ciccone, Robert Sumner, Derek Bradley, Martin Guay

Cross-attention neural network for face rigging enabling variable local control over expression and pose for production face pipelines.

Facial / Rigging / ML Deformation

Erik Ostsjo, Bjorn Arvidsson

Embark Studios outlines their Houdini and USD-based procedural character pipeline shared across Arc Raiders and The Finals, balancing manual and automated rigging workflows.

Rigging / Skinning

Rui Mu

Details Team Jade's cross-platform character art pipeline for Delta Force, covering asset workflows that deliver AAA fidelity on both PC and mobile targets.

Skinning / Rigging

Beth Albright

Examines how Pixar's Hoppers unified modeling, animation, simulation, and lighting to achieve felted cloth characters with physical realism and stylized appeal.

CFX / Skinning

Benoit Bargeton

Animation director at Illogic Studios demonstrates feature-quality rigging and cross-department animation workflow for a commercial wolf character at production scale.

Rigging / Skinning

Martin Singh-Blom

Describes a reinforcement-learning locomotion controller that trains robot enemies to self-discover terrain-adaptive walking and combat movement in physics simulation.

Motion Synthesis

Kristin Gallagher, Christopher Jarvis

Covers building a Vicon Valkyrie-based performance capture facility with custom file-management APIs to support complex multi-actor stunt and dialogue capture pipelines.

Retargeting / Facial

Martin Hill, Jono Dysart

Lead Creatures TD Jono Dysart details creature development pipelines for Vecna and the Mind Flayer across 1,185 VFX shots, including skin, muscle, and cloth systems.

Muscles / CFX / Skinning

Elvis Liu

Introduces a markerless mocap capture pipeline paired with a dedicated generation model for real-time fluid Kung Fu transition synthesis in a fighting game.

Motion Synthesis / Retargeting

Cheng Ge

Presents VISVISE's full-stack pipeline covering 3D structural sketch generation, auto-retopology, auto-rigging, high-precision auto-skinning, and motion in-betweening.

Rigging / Skinning / Motion Synthesis

Andrew Anagnost, Lance Thornton

Autodesk University 2025 live demo by CEO Andrew Anagnost and Product Manager Lance Thornton showing Maya's MotionMaker locomotion synthesis, FaceAnimator, and additional AI-driven character animation tools.

Motion Synthesis / Facial

Sumin Hong, Soojin Choi, Chaelin Kim, Seokhyeon Cha, Junyong Noh

2D generative prior guides joint placement and skinning weight prediction for diverse skeleton and mesh configurations.

Rigging / Skinning

Matthew Tucker

Maya Learning Channel tutorial by rigging expert Matthew Tucker introducing the Bifrost Modular Rigging Framework, covering modules, pins, and transforms for building procedural node-based animation rigs.

Rigging

Matthew Tucker

Covers the Bifrost rigging module interface in Maya, explaining input and output types, parent-child relationships, and how modules interact with Maya scenes for reusable rig components.

Rigging

Matthew Tucker

Walks through building and publishing a custom spline rig module inside the Bifrost Modular Rigging Framework, demonstrating how to author reusable procedural rig components for character pipelines.

Rigging

Kai Stavginski, SideFX

Introduces the Otis GPU-accelerated dynamics solver in Houdini 21, delivering FEM-quality muscle, fascia, and fat simulation at interactive speeds for character FX pipelines.

Muscles / CFX / Skinning

Epic Games

Artist-focused guide to Chaos Cloth simulation in Unreal Engine, building a production-ready pipeline for both real-time and cinematic cloth sequences.

CFX / Skinning

Tim Brakensiek, Epic Games

Technical presentation on integrating Chaos Cloth into AAA game production pipelines, covering simulation fidelity, performance budgets, and artist-facing tooling.

CFX / Skinning

Avneet Kaur, Hubert Leo, Nachiket Pujari, Bret Bays

Multi-tiered strategy for choreographing Moana 2 hair and cloth motion using performance categorization, visual planning, and iterative refinement.

CFX

Juan Carlos Olmos Guerra, Fernando de Goes, Christine Waggoner, David Eberle

Blends 3D target shapes into 2D fabric panels via custom UVs to retarget cloth simulations toward artist-directed draping looks, used in Inside Out 2 and Elio.

CFX

Gabor Molnar

Warhorse Studios presents character systems for KCD2 reducing memory, CPU, and draw calls via material atlasing, ID mapping, UV decals, and layered armor with blood, grime, and damage states.

CFX / Skinning

Epic Games

Practical advice on incrementally adopting Motion Matching in existing animation state-machine projects, demonstrating responsive pose selection with minimal data overhead.

Motion Synthesis / Retargeting

Carlos Valcarcel

Project Outback phase two: contrasts realistic versus stylized facial rig construction in KineFX, demonstrating multiple facial rigging techniques and their APEX implementation.

Facial / Rigging

Autodesk

Quick-start guide showing how to use MotionMaker in Maya 2026.1 to transform simple motion paths into smooth, lifelike character locomotion cycles for bipeds and quadrupeds.

Motion Synthesis

Zedong Chu, Feng Xiong, Meiduo Liu, Jinzhi Zhang, Mingqi Shao, Zhaoxu Sun, Di Wang, Mu Xu

Introduces the first large-scale humanoid rigging dataset of 11,434 T-posed meshes and a transformer-based framework fusing skeleton priors with 3D mesh features for automatic rigging.

Rigging / ML Deformation

Autodesk

Introduces MotionMaker, Maya 2026.1's AI-driven locomotion synthesis tool that generates biped and quadruped motion from a few keyframes or a guide path, trained on dedicated mocap datasets.

Motion Synthesis / Retargeting

Anna-Christine Lykkegaard, Andrew Butts, Julian Teo

Mesh-free character rig for Elio's implicit-surface liquid supercomputer, giving animators full fidelity control over a rigged shader while preserving renderability.

Rigging

Prashanth Chandran, Loic Ciccone, Gaspard Zoss, Derek Bradley

Neural method for transferring facial deformations across characters, generalizing expression retargeting to unseen identities and rig topologies.

Facial / Retargeting / ML Deformation

Jia-Peng Zhang, Cheng-Feng Pu, Meng-Hao Guo, Yan-Pei Cao, Shi-Min Hu

Large autoregressive transformer generates skeletons and skinning weights for diverse 3D asset categories in a single unified framework.

Rigging / Skinning / ML Deformation

Carlos Valcarcel

Explores the rigging framework built for Project Outback inside KineFX and APEX, covering customized rig workflows and future animation techniques under investigation.

Rigging / Skinning

Marco Romeo, Carlos Monteagudo Manas, Hristo Arabadzhiyski, Lucas Ferry, Julia Visser Conesa, Matthew Traynar

Lightweight pseudo-collision method preventing fur-skin intersection without full simulation, enabling scalable creature grooming at production scale.

CFX

Colin Nash, Jihun Yu, Epic Games

Under-the-hood look at MetaHuman Animator's latest real-time facial capture capabilities and the updated Live Link pipeline for on-set performance transfer.

Facial / Retargeting

Wenchao Ma, Dario Kneubuehler, Maurice Chu, Ian Sachs, Haomiao Jiang, Sharon X. Huang

A triangulation-agnostic surface network deforms neutral facial meshes into industry-standard FACS poses, using 2D supervision on unlabeled meshes to scale beyond scarce professional-rigged data.

Facial / Rigging

Evan Boucher, Luis San Juan Pallares, Carlos Puertolas, Yukinori Inagaki

DreamWorks rig system for stylized rubber-hose limb animation, enabling exaggerated cartoon deformation on production characters.

Rigging

Florian Canezin, Xing Ye, Cyril Corvazier

Procedural rigging framework using a direct graph-based control model enabling flexible, maintainable character rig construction.

Rigging

Xiao Zhai, Eston Schweickart, Jefri Haryono, Nikolay Ilinov, Andrea Merlo

Stabilizes cloth and hair collisions in impossible upstream animation configurations without modifying the original animation, integrated into Weta's Loki framework.

CFX

Andrea Lacedelli, Amaan Akram

Untold Studios CFX Supervisor and Head of VFX explain Houdini solutions for simulating octopus tentacles, skin, and hair in Disney's 2024 holiday short, covering challenging creature CFX.

CFX

Greg Richardson, Epic Games

Overview of UE5.6 IK Retargeter enhancements and the roadmap for animation retargeting, covering the journey from IK Rig setup to fully automated skeleton mapping.

Retargeting / Rigging

Shengjie Ma, Yanlin Weng, Tianjia Shao, Kun Zhou

Represents a neutral head and expression basis shapes as 3D Gaussians learned from monocular video, enabling real-time blendshape-style face animation with high-frequency detail.

Facial / ML Deformation

Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang

Learns non-rigid deformation of 3D Gaussians driven by a skeleton with isometric regularization, achieving real-time 50+ FPS rendering and training in 30 minutes from monocular video.

Skinning / ML Deformation

ChangAn Zhu, Chris Joslin

Anatomy-based pipeline translates mocap markers to FACS muscle activations with explicit passive-muscle modeling for diverse character faces.

Facial / Retargeting

Yushan Han, Yizhou Chen, Carmichael Ong, Jingyu Chen, Jennifer Hicks, Joseph Teran

Neural network approximates full musculoskeletal FEM skin deformation at interactive rates, trained on biomechanically accurate simulation data.

Muscles / ML Deformation / Skinning

Prashanth Chandran, Gaspard Zoss

Implicit face model constrained by anatomical priors, improving 3D face fitting generalization across diverse identities and expressions.

Facial

Matthew Lake

Fallen Leaf indie team details Fort Solis character pipeline using runtime deformation, artist-friendly facial rigging, UE5 motion matching locomotion, and PS5 60fps optimisation on limited resources.

Rigging / Facial / Motion Synthesis

Avneet Kaur, Jennifer Stratton, David Hutchins, Nikki Mull

Tools and workflows for grooming, simulating, and stylizing Asha's complex tightly-braided locks in Wish, covering braid simulation and art-direction techniques.

CFX

Guy Tevet, Sigal Raab, Setareh Cohan, Daniele Reda, Zhengyi Luo, Xue Bin Peng, Amit H. Bermano, Michiel van de Panne

Autoregressive diffusion planner runs in closed-loop with an RL tracking controller enabling text-guided multi-task physics character animation.

Motion Synthesis

Ladislav Kavan, John Doublestein, Martin Prazak, Matthew Cioffi, Doug Roble

Proximal-algorithm method to bake large facial blendshape sets into a compact linear blend skinning representation for real-time use.

Facial / Skinning

Lance Thornton, Evan Atherton

Autodesk Animation Product Manager Lance Thornton and Sr. Principal Research Scientist Evan Atherton explore how AI and ML techniques can accelerate rigging and animation production workflows in Maya.

ML Deformation / Rigging

Thomas Stevenson, Valerie Bernard

Case study on iteratively developing a curve rigging toolset responding to shifting production requirements across multiple film projects.

Rigging

Epic Games

Advanced MetaHuman workflows covering MetaHuman Creator, Mesh to MetaHuman, and MetaHuman Animator best practices including Live Link Face calibration and groom application.

Facial / Rigging / Skinning

Dónal Egan, Alberto Jovane, Jan Szkaradek, George Fletcher, Darren Cosker, Rachel McDonnell

Shared finite-scalar-quantisation codebook maps retargeted human skeleton motion to realistic synchronised quadruped animation.

Motion Synthesis / Retargeting

Joy Xiaoji Zhang, Gene Wei-Chin Lin, Lukas Bode, Hsiao-Yu Chen, Tuur Stuyck, Egor Larionov

End-to-end pipeline estimates shell-level cloth elasticity parameters from yarn stretch tests via extended homogenization matching.

CFX

Epic Games

Deep dive into Control Rig's animation editing and procedural rigging capabilities in UE5.4, covering real-time authoring workflows for character control rigs.

Rigging / Motion Synthesis

Justin Studer, Dhruv Agrawal, Dominik Borer, Seyedmorteza Sadat, Robert W. Sumner, Martin Guay, Jakob Buhmann

Diffusion model for motion inbetweening that factorizes motion into character-agnostic and character-specific components for precise controllability.

Motion Synthesis

Sebastian Weiss, Prashanth Chandran, Gaspard Zoss, Derek Bradley

Real-time method for synthesizing temporally consistent dynamic facial wrinkles driven by expression parameters for character faces.

Facial / ML Deformation

Shenhan Qian, Tobias Kirschstein, Liam Schoneveld, Davide Davoli, Simon Giebenhain, Matthias Niessner

Rigs 3D Gaussian splats to a parametric FLAME morphable model with explicit displacement offsets, enabling fully controllable photorealistic head avatar synthesis.

Facial / Rigging

Inseo Jang, Soojin Choi, Seokhyeon Hong, Chaelin Kim, Junyong Noh

Retargets interaction motions between two characters while preserving skinned mesh geometry and contact semantics.

Retargeting / Skinning

Bastien Arcelin, Sebastien Maraux, Nicolas Chaverou

Production experience implementing a neural network deformer for crowd characters, covering training, integration, and quality tradeoffs.

ML Deformation / Skinning

Bo Li, Jing Gong

Lightspeed Studios (Tencent) on a machine-learning-driven next-gen character creation pipeline for UE5 mobile, alongside high-performance mobile rendering.

ML Deformation / Rigging

Yi Shi, Jingbo Wang, Xuekun Jiang, Bingkun Lin, Bo Dai, Xue Bin Peng

Auto-regressive diffusion model generates physically plausible real-time character motion responding interactively to user control signals.

Motion Synthesis

Brown Bag Films, Epic Games

Brown Bag Films details their transition to an in-engine animation pipeline in UE5.3, focusing on squash, stretch, and melting deformation requirements for the character Jelly.

ML Deformation / Skinning / CFX

Wave VFX

Production case study implementing Houdini 20's APEX framework for quadruped rigging and applying the ML Deformer for high-quality real-time skinning deformation.

Rigging / ML Deformation / Skinning

Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley

Data-driven generalized physical face model that learns anatomy-consistent tissue mechanics from captured data for novel character synthesis.

Facial / Muscles / ML Deformation

Hau Nghiep Phan

EA presented FaceMixer, FaceOptim, and FaceBot: three ML tools that together generate blendshapes, automate expression scanning, and produce photorealistic face textures and meshes with minimal manual work.

Facial / ML Deformation

Zhipeng Hu, Jilin Tang, Lincheng Li, Jie Hou, Haoran Xin, Xin Yu, Jiajun Bu

Decomposes full-body mocap solving into local-part sub-motions aggregated by a graph network, reducing the costly manual labeling step.

Retargeting

Chen Tessler, Yunrong Guo, Ofir Nabati, Gal Chechik, Xue Bin Peng

Frames physics-based character control as motion inpainting so one model handles keyframes, objects, text, and sensor constraints.

Motion Synthesis

Heyuan Yao, Zhenhua Song, Yuyang Zhou, Tenglong Ao, Baoquan Chen, Libin Liu

VQ-VAE with model-based RL learns scalable discrete motion codes enabling universal tracking, interactive control, and GPT-based motion generation.

Motion Synthesis

Epic Games

Explores the toolset behind the Game Animation Sample project, detailing how Motion Matching's pose search schema drives responsive character locomotion in UE5.4.

Motion Synthesis / Retargeting

Songnan Li, Yuchen Liao

Tencent TiMi Studio combined Motion Matching with a VAE-based in-betweening system encoding leg movement to reduce foot skating, enabling high-quality low-cost locomotion and transition animation in games.

Motion Synthesis / ML Deformation

Mianlun Zheng, Jernej Barbic

Deep network generates multi-resolution skeleton-driven soft-body shapes at sub-millisecond speeds for real-time game applications.

ML Deformation / Skinning

Jingwen Ren, Hongwei Lin

Applies high-order continuous B-spline surfaces from isogeometric analysis to cloth deformation, reducing DOFs while capturing nonlinear behavior.

CFX

Takara Everest Truong, Michael Piseno, Zhaoming Xie, C. Karen Liu

Diffusion policy for physics-based animation trained with RL corrective actions, demonstrated on perturbation recovery and text-to-motion tracking.

Motion Synthesis

Libo Sun, Rui Tian, Wenhu Qin

Hierarchical control with a muscle layer and trajectory layer reconstructs physically plausible character motion from monocular video.

Muscles / Motion Synthesis

Jacob Speirs, Christian Hoffman, Michael Nieves, Brenda Lin Zhang

Overview of rig solutions for Inside Out 2, including curvenet cloth controls giving Animation direct garment control in individual shots.

Rigging

Sichun Wu, Kazi Injamamul Haque, Zerrin Yumak

Two-stage VQ-VAE learns motion priors; probabilistic codebook sampling produces diverse non-deterministic emotion-controllable facial animations.

Facial / Motion Synthesis

Jiayi Eris Zhang, Doug L. James, Danny M. Kaufman

Progressive simulation framework for cloth and thin shells dynamically balancing accuracy and speed during animation production workflows.

CFX

Yuchen Chu, Zeshi Yang

Data-driven framework generating diverse kinematic in-between motions with explicit user control over duration, path, and style at runtime.

Motion Synthesis

Stevo Rackovic, Dusan Jakovetic, Claudia Soares

Inverse rig solver combines l1 sparsity and temporal roughness penalties to produce high-fidelity, smooth blendshape weight sequences.

Facial / Rigging

Paul Marius Boursin, Yannis Kedadry, Victor B. Zordan, Paul G. Kry, Marie-Paule Cani

Relative-feature modifications to GAIL's discriminator observation enable agile physics-based character control from a single motion cycle.

Motion Synthesis

Autodesk

Autodesk University class on integrating the Maya ML Deformer into production pipelines, covering pose generation, training workflows, parameter fine-tuning, and use cases for interactive deformation approximation.

ML Deformation / Rigging

Dhruv Agrawal, Jakob Buhmann, Dominik Borer, Robert W. Sumner, Martin Guay

Neural motion inbetweening that reasons about skeleton structure for intuitive, physics-plausible gap filling between sparse keyframes.

Motion Synthesis / Rigging

Kelian Baert, Shrisha Bharadwaj, Fabien Castan, Benoit Maujean, Marc Christie, Victoria Abrevaya, Adnane Boukhayma

Self-supervised personalized face capture reconstructing a relightable avatar from multiple unconstrained videos, with real-time tracking of unseen footage.

Facial

Autodesk

Official Autodesk video introducing the Maya ML Deformer, which uses machine learning to approximate complex character deformations for interactive playback speeds during animation, blocking, and crowd work.

ML Deformation / Skinning

Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng

Progressive distillation from thousands of RL expert policies into a single real-time controller covering over 5,000 language-specified skills.

Motion Synthesis

Tianxing Li, Rui Shi, Qing Zhu, Takashi Kanai

Frequency-domain supervision enables a unified neural model to generate dynamic deformations for garments with arbitrary topology and looseness.

CFX / ML Deformation

Rui Chen, Mingyi Shi, Shaoli Huang, Ping Tan, Taku Komura, Xuelin Chen

Conditional autoregressive motion diffusion model enabling real-time diverse character animation from high-level user control with a single unified model.

Motion Synthesis

Christopher Rutledge, Magnus Mollernous

Grin Machine and Tumblehead animators present a behind-the-scenes look at character rigging using Houdini 20.5's APEX system for a short film, demonstrating KineFX-based production workflows.

Rigging

Zhengyi Luo, Jinkun Cao, Josh Merel, Alexander Winkler, Jing Huang, Kris Kitani, Weipeng Xu

PULSE learns a universal motion imitator from large unstructured mocap then builds a comprehensive physics-based motion representation.

Motion Synthesis / Retargeting

Epic Games

In-depth look at how LEGO Fortnite characters were rigged and animated in UE5.4, and how Motion Matching was used to reinvent Fortnite Battle Royale locomotion.

Motion Synthesis / Rigging / Retargeting

Peizhuo Li, Sebastian Starke, Yuting Ye, Olga Sorkine-Hornung

Vector-quantized periodic autoencoder learns a shared phase manifold across different morphologies for unsupervised motion alignment and transfer.

Retargeting / Motion Synthesis

Ben Porter, Jacob Speirs, Fernando de Goes

Curvenet-based wig rig that shares and reuses hair grooms across Emotion characters of different shapes using surface and volumetric deformations.

CFX / Rigging

Dale Newton

Framestore Animation Supervisor details the performance capture pipeline, facial sculpting, and scale-bridging animation process to transpose Hugh Grant's performance onto the Oompa Loompa in Wonka.

Retargeting / Facial

Shigeng Yang, Mengxiao Yin, Ming Li, Guiqing Li, Kan Chang, Feng Yang

Edge-convolution network extracts skeleton and rigid weights, then diffuses smooth weight fields before deforming source mesh to a reference pose.

Skinning / Retargeting

Tianyu Li, Jungdam Won, Alexander Clegg, Jeonghwan Kim, Akshara Rai, Sehoon Ha

Adversarial correspondence learning retargets human motion to nonhuman characters with different body structure and proportions.

Retargeting

Lingchen Yang, Gaspard Zoss, Prashanth Chandran, Paulo Gotardo, Markus Gross, Barbara Solenthaler, Eftychios Sifakis, Derek Bradley

Implicit neural face model coupling expression controls with physics simulation, enabling expression-driven and style-varied realistic facial deformation.

Facial / Muscles

Seunghwan Lee, Yifeng Jiang, C. Karen Liu

High-fidelity FEM simulation of the human torso with detailed muscle, organ, and tissue anatomy for realistic breathing and movement.

Muscles

Bruno Velazquez, David Gibson, Mehdi Yssef, Erica Pinto

Santa Monica Studio animation leads share quickfire breakdowns covering cinematic storytelling, dismemberment systems, and directorial challenges across God of War Ragnarok's character animation.

Retargeting / Rigging

Chris Landreth

JALI Research masterclass on facial muscle anatomy, subtext observation, rigging principles, and real-time JALI demonstrations showing how accurate lip sync improves character performance in games.

Facial

JC Delannoy

EA retrospective on five years of shipping motion matching across multiple titles, covering system evolution, production lessons, and how the technique was adapted for diverse game types.

Motion Synthesis

Stuart Adcock

Introduces Weta FX's Anatomically Plausible Facial System, an evolution of FACS controls that replicates actor facial performance for Avatar: The Way of Water beyond previous techniques.

Facial

Iñaki Navarro, Dario Kneubuehler, Tijmen Verhulsdonck, Eloi du Bois, William Welch, Charles Shang, Ian Sachs, Morgan McGuire, Victor B. Zordan, Kiran Bhat

Combines video and audio streams via two specialized networks to drive facial character rigs in real time on low-end devices.

Facial / Motion Synthesis

Xiao Zhai, Eston Schweickart, Nikolay Ilinov, Joel Wretborn, Alexey Stomakhin, John Homer, Jefri Haryono, Julian Butler

Production talk on cloth, hair, and coupled simulation for Avatar 2, covering solver integration and artist workflow at Weta FX.

CFX

Christoph Sprenger, Tobias Mack, Alexey Stomakhin, Florian Fernandez

ML-driven character deformation pipeline used in Avatar 2 production, combining optimization-based and learned approaches for hero characters.

Skinning / ML Deformation

Zhiyang Dou, Xuelin Chen, Qingnan Fan, Taku Komura, Wenping Wang

Divides heterogeneous motion into homogeneous subsets for training a conditional adversarial model that controls diverse skill behaviors.

Motion Synthesis

Chen Tessler, Yoni Kasten, Yunrong Guo, Shie Mannor, Gal Chechik, Xue Bin Peng

Jointly learns a physics-based control policy and motion encoder for diverse, directable character behavior from mocap via imitation learning.

Motion Synthesis

Rickey Cloudsdale, Aruna Inversin, Peter Rabel

Digital Domain adapted feature-film facial capture technology to handle 30 hours of performance for The Quarry, automating emotion transfer onto digital puppets at game-scale workloads.

Facial / Retargeting

Jinbo Xing, Menghan Xia, Yuechen Zhang, Xiaodong Cun, Jue Wang, Tien-Tsin Wong

Reformulates speech-driven facial animation as code-query in a learned discrete codebook of realistic facial motion priors, reducing cross-modal mapping uncertainty.

Facial / Motion Synthesis

Pei Xu, Xiumin Shang, Victor Zordan, Ioannis Karamouzas

GAN-based decoupled multi-discriminator framework learns composite body-part motions from multiple references without manual annotation.

Motion Synthesis

Dan Lipson, Jose Velasquez

Curve-based fabric authoring workflow supporting custom weave patterns and fiber thicknesses from fine threads to thick yarns, used for Strange World's costumes.

CFX

Courtney Chun, Jose Velasquez, Haixiang Liu

Houdini-supplemented XGen groom pipeline for Strange World's dog Legend, translating French-Belgian comic book fur aesthetics into a production groom.

CFX

Mario Marengo, Amit Khanna, Folks VFX

Crowd optimization pipeline for Cabinet of Curiosities, detailing KineFX-based agent replacement workflows and render-time procedural techniques for fur-bearing crowd characters.

CFX / Retargeting

Yudi Li, Min Tang, Yun Yang, Ruofeng Tong, Bailin An, Shuangcai Yang, Yao Li, Qilong Kou

Decomposes cloth deformation into static skinning, coarse dynamic, and wrinkle components predicted by three sequential network stages.

CFX / ML Deformation / Skinning

Jonathan Tseng, Rodrigo Castellon, C. Karen Liu

Transformer diffusion model paired with Jukebox audio features for physically plausible, editable music-driven dance generation.

Motion Synthesis

Weiyu Li, Xuelin Chen, Peizhuo Li, Olga Sorkine-Hornung, Baoquan Chen

Generative motion matching framework combining motion database search with generative models for smooth diverse motion synthesis.

Motion Synthesis

Xin Chen, Biao Jiang, Wen Liu, Zilong Huang, Bin Fu, Tao Chen, Gang Yu

Motion Latent Diffusion (MLD) compresses motion into a VAE latent space before diffusion, achieving two-orders-of-magnitude speedup over raw-sequence diffusion.

Motion Synthesis

Anna-Christine Lykkegaard, Ana G. Lacaze, Jonathan Page

Pipeline for Win or Lose characters with unconnected floating facial features, combining 2D graphic expressiveness with 3D environment integration.

Facial / Rigging

Stefan Stan, Kazi Injamamul Haque, Zerrin Yumak

Diffusion model for generating diverse and expressive 3D facial animations driven by speech audio input.

Facial / Motion Synthesis

Otman Benchekroun, Jiayi Eris Zhang, Siddhartha Chaudhuri, Eitan Grinspun, Yi Zhou, Alec Jacobson

Fast complementary dynamics simulation using skinning eigenmodes as a reduced subspace for secondary jiggle effects on skinned characters.

Skinning / ML Deformation

Shrisha Bharadwaj, Yufeng Zheng, Otmar Hilliges, Michael J. Black, Victoria Fernandez-Abrevaya

Creates animatable, relightable mesh avatars from monocular video using differentiable rasterization and learned blendshapes, compatible with standard rendering pipelines.

Facial / CFX

Marilyn Keller, Keenon Werling, Soyong Shin, Scott Delp, Sergi Pujades, C. Karen Liu, Michael J. Black

SKEL model couples a biomechanical skeleton to a SMPL surface, enabling pose estimation with anatomically constrained joint axes and soft-tissue deformation.

Rigging / Muscles / Skinning

Matt Estela, CG Wiki

Production case study on transitioning a studio to Houdini with KineFX, exploring stylized character animation workflows and practical lessons learned for riggers and FX artists.

Rigging / Retargeting / Motion Synthesis

Epic Games

Live demonstration of MetaHuman Animator's monocular facial performance capture, shown with a Hellblade actor transferring facial animation to a MetaHuman in real time.

Facial / Retargeting

Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, Philipp Slusallek

First framework to synthesize full-body character motion with 3D objects from text-based intent labels, supporting single and two-handed interactions.

Motion Synthesis

Gilles Daviet

Local-global ADMM solver for Discrete Elastic Rods with Coulomb friction fully parallelized on GPU, reproducing stick-slip behavior at interactive rates for high-resolution hair.

CFX

Yash Kant, Aliaksandr Siarohin, Riza Alp Guler, Menglei Chai, Jian Ren, Sergey Tulyakov, Igor Gilitschenski

Combines a pose-conditioned invertible network with differentiable LBS to animate implicit surfaces while preserving surface correspondences, outperforming state-of-the-art reposing methods.

Skinning / ML Deformation

Tenghao Wang

Santa Monica Studio described a systematic joint-based rig following muscle fiber curves for volume preservation, plus dynamic bone techniques approximating muscle, fat, and skin jiggle in combat.

Skinning / Muscles

Simon Giebenhain, Tobias Kirschstein, Markos Georgopoulos, Martin Runz, Lourdes Agapito, Matthias Niessner

Neural parametric head model using an ensemble of local MLPs in canonical SDF space with forward deformation field, trained on 5,200+ scans from 255 subjects.

Facial

Tobias Kleanthous, Antonio Martini

Motion matching approach with Lipschitz-constrained networks and sparse mixture of experts for robust, scalable learned motion synthesis.

Motion Synthesis

Emmanuel Ian Libao, Myeongjin Lee, Sumin Kim, Sung-Hee Lee

Improved graph neural network approach for cloth simulation with better generalization to unseen garment shapes and body poses.

CFX / ML Deformation

Matt Stoneham, Epic Games

End-to-end walkthrough of the ML Deformer framework, showing how muscle, flesh, and cloth simulation training data drives real-time deformation for MetaHuman characters.

ML Deformation / Facial / Skinning

Raffaele Fragapane, Matt Stoneham

Epic Games demonstrated end-to-end MetaHuman assembly and the UE5 ML Deformer workflow, training networks on full muscle, flesh, and cloth simulation data to approximate high-fidelity deformation at runtime.

ML Deformation / Skinning / Facial

Daniel Shamota

3SISTERS studio presents a 4D volumetric capture pipeline for creating Sharon Stone's digital double, coupled with a PDG and KineFX-driven mocap retargeting workflow in Houdini.

Retargeting / Facial

Yusen Feng, Xiyan Xu, Libin Liu

Integrates fatigue dynamics into Hill-type muscle model and trains a VAE motion controller from large unstructured datasets.

Muscles / Motion Synthesis

Tobias Kirschstein, Shenhan Qian, Simon Giebenhain, Tim Walter, Matthias Niessner

Dynamic neural radiance fields via hash ensemble deformation for high-fidelity head reconstruction, paired with a 4,700+ sequence multi-view capture dataset.

Facial

Dafei Qin, Jun Saito, Noam Aigerman, Thibault Groueix, Taku Komura

End-to-end deep learning method for automatic rigging and retargeting of arbitrary in-the-wild facial meshes without manual blendshape creation.

Facial / Rigging / Retargeting

Yuda Hong, Zhihao Li, Yaxin Chen, Xuaner Zhang, Mingtao Feng, Yuefang Gao

Reconstructs a high-fidelity 3D facial avatar from a single source image using NeRF, enabling photo-realistic reenactment driven by arbitrary target faces.

Facial

Antoine Maiorca, Hugo Bohy, Youngwoo Yoon, Thierry Dutoit

Validates Frechet Motion Distance as an objective metric for evaluating motion generative models, addressing artifacts like foot skating.

Motion Synthesis

Zhengyi Luo, Jinkun Cao, Alexander Winkler, Kris Kitani, Weipeng Xu

Progressive multiplicative control policy (PMCP) scales physics imitation to 10,000 AMASS clips with real-time fault recovery.

Motion Synthesis / Retargeting

Daniele Reda, Jungdam Won, Yuting Ye, Michiel van de Panne, Alexander Winkler

RL policy retargets sparse VR sensor streams to morphologically diverse characters including non-human avatars in real time.

Retargeting / Motion Synthesis

Yufeng Zheng, Wang Yifan, Gordon Wetzstein, Michael J. Black, Otmar Hilliges

Deformable point cloud head avatar disentangling intrinsic albedo from normal-dependent shading, enabling FLAME-driven animation with topological flexibility.

Facial

Dhruv Agrawal, Martin Guay, Jakob Buhmann, Dominik Borer, Robert W. Sumner

Neural IK solver aware of skeleton topology and pose context, enabling fast and accurate pose and motion editing for character rigs.

Rigging / ML Deformation

Stuart Bryson, Matthew C. Gong, Rob O'Neill, Ted Forgrave, Ben Kwa, Paul DiLorenzo

Overview of DreamWorks' Academy Award-winning Premo system featuring pose-centric sculpting workflows that map edits back to underlying pose shapes.

Rigging

Mingyuan Zhang, Xinying Guo, Liang Pan, Zhongang Cai, Fangzhou Hong, Huirong Li, Lei Yang, Ziwei Liu

Integrates hybrid semantic-kinematic retrieval into a diffusion model to improve rare-motion generation quality.

Motion Synthesis

Rinat Abdrashitov, Kim Raichstat, Jared Monsen, David Hill

Fully automatic two-stage method for transferring skin weights between geometrically dissimilar meshes, outperforming commercial software on garments.

Skinning / Rigging

Wenxuan Zhang, Xiaodong Cun, Xuan Wang, Yong Zhang, Xi Shen, Yu Guo, Ying Shan, Fei Wang

Generates 3DMM motion coefficients for head pose and expression from audio and modulates a 3D-aware face renderer for stylized talking head generation from a single image.

Facial / Motion Synthesis

Jerry Hsu, Tongtong Wang, Zherong Pan, Xifeng Gao, Cem Yuksel, Kui Wu

Four-stage framework computing stable quasistatic configurations for hybrid strand-based hair so simulations start without gravity-induced sag.

CFX

Sunmin Lee, Taeho Kang, Jungnam Park, Jehee Lee, Jungdam Won

Learns an embedding space that disentangles skeleton structure from motion semantics, enabling cross-skeleton motion retargeting.

Retargeting / Motion Synthesis

Duc Nguyen, Jeremie Talbot, William Sheffler, Mark Hessler, Kurt Fleischer, Fernando de Goes

Shaping rig for Pixar's curvenet system that auto-generates surface-aligned animation controls per knot for layered shot-level rigging on Elemental.

Rigging

Jan Philip Cramer

Digital Domain VFX supervisor details facial animation, muscle and cloth simulation for She-Hulk, including Charlatan, a neural network for ML-based face replacement in production.

Facial / ML Deformation / CFX

Nicolas Wagner, Mario Botsch, Ulrich Schwanecke

Computationally efficient physics-based facial animation method integrating soft tissue dynamics with the DECA morphable face model.

Facial / Muscles

Jiong Chen, Fernando de Goes, Mathieu Desbrun

Derives matrix-valued cage coordinates from the Somigliana boundary integral identity, generalizing Green coordinates with elastic volume control.

Skinning

Mohamed Hassan, Yunrong Guo, Tingwu Wang, Michael Black, Sanja Fidler, Xue Bin Peng

RL with adversarial imitation trains physically simulated characters to perform carrying, sitting, and lying down from unstructured mocap data.

Motion Synthesis

Jianrong Zhang, Yangsong Zhang, Xiaodong Cun, Shaoli Huang, Yong Zhang, Hongwei Zhao, Hongtao Lu, Xi Shen

VQ-VAE plus GPT framework for text-to-motion that outperforms diffusion baselines with FID 0.116 on HumanML3D.

Motion Synthesis

Sean Comer, Bernardo Antoniazzi

Infinity Ward and DI4D showed how Light Stage scans and 4D expression data trained rig parameter coefficients, enabling scalable automatic transfer of HMC stereo facial performances without human intervention.

Facial / ML Deformation

Gabriela Salmeron

Framestore's Head of Groom and CFX covers their feather pipeline, complex grooming for furry creatures, and CFX workflows simulating muscles, fat, skin, and hair at episodic scale.

CFX / Muscles

Cameron Black, Christoffer Pedersen

Omni-directional rig for Strange World's alien Splat allowing limbs to serve as both arms and legs, with versatile setup supporting unanticipated character poses.

Rigging

Mia Haapaoja, Simon Klintberg

Production pipeline covering offline blendshape generation from facial scans, sticky-lips correction, and real-time dynamic skin microstructure for digital humans.

Facial / Skinning

Yusun Chung

How The Sims 4 animates fully customizable characters and objects: IK retargeting across body shapes, block modeling, and content verification with the SAGE art graph editor.

Retargeting / Rigging

Ryan Cardinal, Luke Shier, David Wong

EA Sports describes capturing a 90-minute 11v11 professional soccer match with XSens suits to feed the ML Flow machine learning procedural animation system, overcoming traditional optical capture constraints.

Motion Synthesis / Retargeting

Simon Habib

Eidos Montreal used in-house mocap and Faceware batch processing for five main characters, with photogrammetry scanning ensuring anatomically correct expressions at game production volume and quality.

Facial / Retargeting

Byungkuk Choi, Haekwang Eom, Benjamin Mouscadet, Stephen Cullingford, Kurt Ma, Stefanie Gassel, Suzi Kim, Andrew Moffat, Millicent Maier, Marco Revelant, Joe Letteri, Karan Singh

Replaces FACS shapes with a muscle-strain basis for the face, the system behind Weta's Avatar 2 facial pipeline.

Facial / Muscles

Xue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine, Sanja Fidler

Large-scale adversarial skill embedding space for physically simulated characters enabling diverse and composable motion skill reuse.

Motion Synthesis

David Ryberg Lessel

Bacon X Co-head of CG shows how Houdini's FEM and Vellum solvers automate reliable skin and fur simulation for a fully digital baby wild hog creature in a small-studio pipeline.

CFX

Laura Guerreiro, Tommy Toussaint

Unit Image CFX supervisors trace the evolution of their cloth and hair simulation department, covering Houdini-based character FX workflows across multiple cinematic projects.

CFX

Fernando de Goes, William Sheffler, Kurt Fleischer

Spline-based rigging system where artists draw sparse curvenets that profile the surface, producing detail-preserving deformations used in Turning Red.

Rigging / Skinning

Heyuan Yao, Zhenhua Song, Baoquan Chen, Libin Liu

VAE-based framework learns a latent skill space from unstructured mocap and trains a generative physics-based motion controller.

Motion Synthesis

Tony Atherton

The Mill FX Supervisor walks through grooming, muscle and skin creation, and Vellum-based fur simulation in Houdini to produce Hattie the Hyena for an Amazon holiday commercial.

CFX / Muscles

Madeleine Scott-Spencer

Cinesite CG Supervisor details the concept-driven asset pipeline for The Basilisk and Chernobog creatures, covering shape language, anatomy, and adaptability between concept and final shot.

Rigging

Sebastian Starke, Ian Mason, Taku Komura

Periodic Autoencoder extracts unsupervised spatial-temporal phase features from large unstructured motion datasets, winning SIGGRAPH 2022 Best Paper.

Motion Synthesis

Ying Wang, Jasper Verheul, Sang-Hoon Yeo, Nima Khademi Kalantari, Shinjiro Sueda

Incorporates muscle inertia into musculoskeletal simulation via a chain-of-Jacobians formulation enabling gradient-based optimization.

Muscles

Jose Velasquez, Alexander Alvarado, Ying Liu, Maryann Simmons

Procedural Houdini workflow modeling individual cloth fibers and binding them to clothing geometry via XGen, supporting embroidery styles for Encanto costumes.

CFX

Radek Danecek, Michael J. Black, Timo Bolkart

Introduces a deep perceptual emotion consistency loss during monocular 3D face reconstruction training, significantly improving the fidelity of reconstructed facial expressions over prior methods.

Facial

Richard Oud

Guerrilla Games' Gameplay Animation Director detailed supporting animation systems for Horizon Forbidden West covering player mechanics, robotic creatures, and human adversaries while preserving series visual identity.

Motion Synthesis / Rigging

Yingruo Fan, Zhaojiang Lin, Jun Saito, Wenping Wang, Taku Komura

Transformer autoregressive model encoding long-term audio context with biased cross-modal attention and self-supervised speech representations for 3D facial animation.

Facial / Motion Synthesis

Lizhen Wang, Zhiyuan Chen, Tao Yu, Chenguang Ma, Liang Li, Yebin Liu

Coarse-to-fine 3DMM built from 60K RGB-D images and 2K high-fidelity scans, with controllable StyleGAN-based detail generation for both base and fine modules.

Facial

Prashanth Chandran, Gaspard Zoss, Markus Gross, Paulo Gotardo, Derek Bradley

Transformer-based model disentangling facial identity and motion for retargeted animation of novel characters from a reference performance.

Facial / ML Deformation

Wan-Duo Kurt Ma, Muhammad Ghifary, John P. Lewis, Byungkuk Choi, Haegwang Eom

Deep learning facial performance system combining controllability and retargetability for production-quality digital human faces.

Facial / ML Deformation / Retargeting

Chuan Guo, Shihao Zou, Xinxin Zuo, Sen Wang, Wei Ji, Xingyu Li, Li Cheng

Introduces HumanML3D dataset (14,616 clips, 44,970 descriptions) and a temporal VAE text-to-motion pipeline.

Motion Synthesis

Eduardo Alvarado, Damien Rohmer, Marie-Paule Cani

Neural method generating reactive upper-body secondary motion for locomoting characters navigating dynamic obstacles in real time.

Motion Synthesis / Rigging

Jungnam Park, Sehee Min, Phil Sik Chang, Jaedong Lee, Moon Seok Park, Jehee Lee

A deep RL network controls 304 Hill-type musculotendons across a 618-dimensional anatomy-condition space, generating healthy and pathological gaits in real-time physics simulation.

Muscles / Motion Synthesis

Haixiang Liu

Optimization algorithm that preloads hair rest shapes to compensate for gravitational sag, preserving the groomed design shape during simulation.

CFX

Jean-Marc Thiery, Tamy Boubekeur

Extends Green coordinates to quadrilateral cage faces in 3D, providing quasi-conformal deformations with closed-form expressions for production cages.

Skinning

Marco Romeo, Carlos Monteagudo Manas, Hristo Arabadzhiyski, Isabela Rovira, Srijith Vasudevan, Matt Traynar

Groom style interpolation technique preserving strand features during blending between different hairstyles for digital creature effects.

CFX

Brandon Montell, Fernando de Goes, Jacob Brooks

Describes Pixar's style-guide system for art-directing millions of hair and fur curves to reflect characters' emotional states in Turning Red.

CFX

Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, Amit H. Bermano

Transformer-based diffusion model for text-to-motion and action-to-motion synthesis achieving state-of-the-art while predicting samples not noise.

Motion Synthesis

Yufeng Zheng, Victoria Fernandez Abrevaya, Marcel C. Buhler, Xu Chen, Michael J. Black, Otmar Hilliges

Implicit head avatar learning from monocular video via neural blendshapes and skinning fields in canonical space with end-to-end analytical gradient training.

Facial

Prashanth Chandran, Loic Ciccone, Markus Gross, Derek Bradley

Retargets facial performances across diverse rigs using local anatomical constraints that preserve expression fidelity and prevent implausible deformations.

Facial / Retargeting

Steve Lesser, Alexey Stomakhin, Gilles Daviet, Joel Wretborn, John Edholm, Noh-Hoon Lee, Eston Schweickart, Xiao Zhai, Sean Flynn, Andrew Moffat

Weta's unified solver where muscles, flesh, cloth, hair, and fluids all couple in one framework instead of chained single-physics passes.

Muscles / CFX

Sebastian Starke

Four years of Edinburgh and EA research on deep learning for character control, covering quadruped locomotion, scene interactions, basketball, and martial arts from motion capture training data.

Motion Synthesis / ML Deformation

Yinglin Duan

NetEase Games presented a lightweight real-time motion completion network that generates smooth game animation without a large pre-built motion library, outperforming interpolation and standard motion matching.

Motion Synthesis / ML Deformation

Jorge del Val Santos

Embark Studios shows reinforcement learning where user-created creatures autonomously learn locomotion, treating animation as an emergent property of anatomy derived from robotics principles.

Motion Synthesis / ML Deformation

Stephen Bailey, Jeremy Riviere, Morten Mikkelsen, James F. O'Brien

Deep learning pipeline for monocular video facial capture that matches expressions from RGB input to rigged face models at production quality.

Facial

Daoye Wang, Prashanth Chandran, Gaspard Zoss, Derek Bradley, Paulo Gotardo

Extends NeRF into a generative morphable model producing multiview-consistent photorealistic head images with controllable identity parameters.

Facial

Zhan Xu, Yang Zhou, Li Yi, Evangelos Kalogerakis

Rigs and animates 3D character meshes by encoding motion cues from single-view point cloud streams of a performing subject.

Rigging

Autodesk

Overview of MotionBuilder 2023 updates including Python 3 migration, new animation layer colour hints, custom key sets for character rigs, and improved pose controls for mocap data transfer workflows.

Retargeting / Motion Synthesis

Industrial

Practical walkthrough of MotionBuilder HumanIK characterization and full-body mocap retargeting, covering biped joint mapping, HIK solve settings, and baking animation onto custom character skeletons.

Retargeting

Meng Zhang, Duygu Ceylan, Niloy J. Mitra

Motion-conditioned neural model generalizes garment dynamics to unseen body shapes and motions by disentangling body and garment representations.

CFX / ML Deformation

Industrial

Comprehensive guide to MotionBuilder essentials covering biped and quadruped characterization differences, HumanIK retargeting configuration, and animation baking for export-ready mocap data.

Retargeting / Motion Synthesis

Guy Tevet, Brian Gordon, Amir Hertz, Amit H. Bermano, Daniel Cohen-Or

Aligns a 3D human motion auto-encoder latent space with CLIP, enabling out-of-domain text and image-driven motion synthesis.

Motion Synthesis

Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, Ziwei Liu

First diffusion-based text-driven motion framework enabling fine-grained body-part control and arbitrary-length synthesis.

Motion Synthesis

Yudi Li, Min Tang, Yun Yang, Zi Huang, Ruofeng Tong, Shuangcai Yang, Yao Li, Dinesh Manocha

Graph convolution on arbitrary-topology cloth and obstacle meshes predicts plausible 3D cloth deformation at 30-45 fps for up to 100K triangles.

CFX / ML Deformation

Hugo Bertiche, Meysam Madadi, Sergio Escalera

First unsupervised deep learning framework for garment dynamics using physics-inspired losses without ground-truth simulation data.

CFX

Philip-William Grassal, Malte Prinzler, Titus Leistner, Carsten Rother, Matthias Niessner, Justus Thies

Hybrid avatar representation combining a coarse morphable face model with two networks predicting mesh vertex offsets and view- and expression-dependent textures.

Facial

Yuwei Li, Longwen Zhang, Zesong Qiu, Yingwenqi Jiang, Nianyi Li, Yuexin Ma, Yuyao Zhang, Lan Xu, Jingyi Yu

Parametric hand model comprising 20 bone meshes and 7 tetrahedral muscle groups built from annotated MRI data, enabling anatomy-aware hand pose estimation.

Muscles / Skinning

Jordan Juravsky, Yunrong Guo, Sanja Fidler, Xue Bin Peng

Combines NLP with physics-based character control so natural language commands specify tasks and low-level motion skills.

Motion Synthesis

Jungdam Won, Deepak Gopinath, Jessica Hodgins

Conditional VAE latent space over motion clips drives a physics controller, enabling goal-directed interactive locomotion from unstructured data.

Motion Synthesis

Alexander Winkler, Jungdam Won, Yuting Ye

Deep RL drives a full-body simulated avatar in real time using only VR headset and controller signals as input.

Motion Synthesis / Retargeting

Qing Lyu, Menglei Chai, Xiang Chen, Kun Zhou

Neural interpolation between precomputed hair simulation snapshots achieves real-time performance while preserving physically accurate dynamic behavior.

CFX / ML Deformation

Christine Waggoner, Fernando de Goes

Reviews the evolution of Pixar's cloth authoring tools from 2001 and presents the updated tailoring pipeline deployed on Turning Red and Lightyear.

CFX

Daniel Sheerin, Joshua Beveridge, Enoch Ihde, Stirling Duguid, Brian Casper, Andrea Parkhill, Ed Lee, Carlos Fraiha

Procedural length-preserving rope rig handling over 5000 ropes on the hero tall ship in The Sea Beast with intuitive animator controls.

Rigging / CFX

Mianlun Zheng, Bohan Wang, Jingtao Huang, Jernej Barbic

Builds a volumetric musculoskeletal hand model from MRI data that matches scanned geometry across the full range of motion.

Muscles

Stefano Nuvoli, Nico Pietroni, Paolo Cignoni, Riccardo Scateni, Marco Tarini

Composes new rigged and skinned characters by mixing body parts from production-ready animated models.

Rigging / Skinning

Igor Santesteban, Miguel A. Otaduy, Dan Casas

Physics-based self-supervised loss recasts implicit integration as optimization, training garment networks without labeled data at two orders of magnitude faster than supervised methods.

CFX / ML Deformation

Sofya Ogunseitan

Procedural groom tools for generating braids, curls, and edge hairs along hand-sculpted source curves, creating Lightyear characters' hairstyles.

CFX

Ahmed A. A. Osman, Timo Bolkart, Dimitrios Tzionas, Michael J. Black

SUPR jointly trains a full-body and part-specific models from 1.2 million scans, introducing a novel kinematic foot model with contact-aware deformations.

Skinning / ML Deformation

Mathis Petrovich, Michael J. Black, Gül Varol

Variational transformer encodes text and motion into a joint latent space, generating diverse motion sequences from a single description.

Motion Synthesis

Yan Zhang, Siyu Tang

GAMMA decomposes long-term scene-aware human motion into generative body-marker primitives with a policy for perpetual goal-directed navigation.

Motion Synthesis

Wojciech Zielonka, Timo Bolkart, Justus Thies

MICA predicts metric-accurate FLAME face shapes from single images using supervised learning on 2,000+ identities with face recognition features.

Facial

William Sheffler

Presents Pixar's profile mover and curve-net system deployed on Panda Mei, achieving surface-detail-preserving deformations controlled by sparse bezier or Catmull-Rom curve networks.

Rigging

Saeed Ghorbani, Ylva Ferstl, Daniel Holden, Nikolaus F. Troje, Marc-Andre Carbonneau

Zero-shot speech-driven full-body gesture generation using example style references, trained on a diverse high-quality motion dataset.

Motion Synthesis / Facial

Bernhard Egger, Will Smith, Yash Tewari, Stefanie Wuhrer, Michael Zollhoefer, Thabo Beeler, Florian Bernard, Timo Bolkart, Adam Kortylewski, Sami Romdhani, Christian Theobalt, Volker Blanz, Thomas Vetter

Comprehensive survey of 3D morphable face models from the original Basel Face Model to neural variants, covering fitting and applications.

Facial

Mianlun Zheng, Yi Zhou, Duygu Ceylan, Jernej Barbic

Graph-network ODE emulator adds vivid secondary dynamics to skinned characters over 30x faster than full FEM simulation with topology-independent inference.

ML Deformation / CFX

Sandy Kao, Mike Amos, Bill Otsuka, Amy Kwa, Charles Edward Billingsley, Michael Amorozo, Jason Dengler, Isabela Rovira, Alexander Paz, Marc Scott, Ariel Chisholm

End-to-end pipeline for 2D-style multiples and smear geometry on 3D characters, inspired by Looney Tunes, deployed on Boss Baby: Family Business.

Rigging

Mathis Petrovich, Michael J. Black, Gül Varol

ACTOR uses a Transformer VAE to synthesize variable-length SMPL motion sequences conditioned on action category labels.

Motion Synthesis

Xue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine, Angjoo Kanazawa

Adversarial motion prior enabling physics-based characters to reproduce diverse motion styles from unstructured motion clip datasets.

Motion Synthesis

Sida Peng, Junting Dong, Qianqian Wang, Shangzhan Zhang, Qing Shuai, Xiaowei Zhou, Hujun Bao

Introduces neural blend weight fields driven by a skeletal deformation to map observation space to a canonical NeRF, enabling free-viewpoint video of dynamic humans.

ML Deformation / Skinning

Ilkka Kuusela, Ville Ruusutie

Remedy Entertainment details building a custom motion-matching animation system for Control from scratch after middleware became unavailable, covering pipeline, debugging tools, and cinematic transitions.

Motion Synthesis / Rigging

Autodesk

Official Autodesk overview of MotionBuilder 2022 new features including Python 3 support, expanded Python API, FCurve quaternion visualization, Character Extension improvements, and Story tool stability fixes.

Retargeting / Motion Synthesis

Wasim Khan

Naughty Dog technical overview of The Last of Us Part II character pipeline covering artist-driven shader workflows, gore tools, and live-production optimisations without destructive asset changes.

Skinning / Facial

Minchen Li, Danny M. Kaufman, Chenfanfu Jiang

Extends IPC to shells, rods, and particles coupled seamlessly, enabling unified interpenetration-free simulation of cloth, hair, and volumetric bodies together.

CFX

Ruben Villegas, Duygu Ceylan, Aaron Hertzmann, Jimei Yang, Jun Saito

A geometry-conditioned recurrent network with encoder-space optimization preserves self-contacts and prevents interpenetration when retargeting motion across different character bodies.

Retargeting

Vladimir Mastilovic

Epic Games VP of Digital Humans Technology presents MetaHuman Creator, detailing the high-fidelity facial rigging system and workflow for generating realistic real-time digital humans.

Facial / Rigging

Binh Huy Le, Keven Villeneuve, Carlos Gonzalez-Ochoa

Compresses DDM models into a two-layer LBS representation using continuous pose-space example data to minimize approximation error.

Skinning

Meng Zhang, Tuanfeng Y. Wang, Duygu Ceylan, Niloy J. Mitra

Neural network predicts pose-dependent dynamic wrinkle details for garments directly from skeletal motion without explicit cloth simulation.

CFX / ML Deformation

Keith Paciello, Christian Wohlwend

Naughty Dog presented a systemic emotion pipeline spanning rigging, animation, dialogue, and design to deliver up to 20 emotions for 65 characters across 13 languages in gameplay.

Facial / Rigging

Vismay Modi, Lawson Fulton, Alec Jacobson, Shinjiro Sueda, David I.W. Levin

Scalable FEM-quality muscle simulator handling heterogeneous materials including soft muscles, tendons, and bones without geometric coarsening.

Muscles

Manne Ohrstrom, Leo Hills, Theodore Jones

Portable real-time rig deformation framework providing production-quality character deformation in interactive and game contexts.

Rigging / Skinning

Hoseok Ryu, Minseok Kim, Seunghwan Lee, Moon Seok Park, Kyoungmin Lee, Jehee Lee

Transfers musculature from a reference anatomical model to bodies of different proportions while preserving functionality and producing simulation-ready results.

Muscles / Retargeting

Zhen Luo, Tianxing Li, Takashi Kanai

Two-stream network predicts body-fitted garment mesh deformation conditioned on pose and parameterized fabric material properties.

CFX / ML Deformation

Huamin Wang

Regular-grid GPU cloth at millions of vertices resolving submillimeter wrinkles, exploiting structured memory access for high-resolution character garment simulation.

CFX

Xiaoyu Pan, Jiancong Huang, Jiaming Mai, He Wang, Honglin Li, Tongkui Su, Wenjun Wang, Xiaogang Jin

Builds a heterogeneous graph over mesh vertices and skeletal bones with a HollowDist metric, predicting production-quality skin weights for arbitrary character topologies.

Skinning / ML Deformation

Cyril Corvazier, Thomas Robert

Analysis of how rig design decisions directly affect animator workflow, productivity, and the quality of resulting performances.

Rigging

Donal Egan, George Fletcher, Yiguo Qiao, Darren Cosker, Rachel McDonnell

Neural network approach to enhance keyframed or procedural quadruped animations with learned natural motion characteristics.

Motion Synthesis / ML Deformation

Matt Courtois

Technical tour of MotionBuilder's Story Tool as a non-linear mocap editor, covering clip blending, pose library, track management, and the workflow advantages for real-time motion editing and cut-scene assembly.

Motion Synthesis / Retargeting

Tarun Yenamandra, Ayush Tewari, Florian Bernard, Hans-Peter Seidel, Mohamed Elgharib, Daniel Cremers, Christian Theobalt

First deep implicit 3DMM of full heads including hair, using signed distance functions and disentangled geometry and color latent spaces.

Facial

Rinat Abdrashitov, Seungbae Bang, David I.W. Levin, Karan Singh, Alec Jacobson

Volumetric segmentation approach assigns every point in a character volume to muscle, fat, or bone, with interactive muscle-curve-driven authoring tools.

Muscles / Rigging

Jongmin Kim, Yeongho Seol, Taesoo Kwon

Unified deformation-based framework preserves spatial relationships among multiple characters and environment during real-time interactive retargeting.

Retargeting

Jeff Wagner, SideFX

Comprehensive KineFX masterclass for Houdini users, covering procedural rigging concepts, skeleton workflows, constraint systems, and animation retargeting in SOP context.

Rigging / Retargeting / Skinning

Yao Feng, Haiwen Feng, Michael J. Black, Timo Bolkart

DECA reconstructs a detailed animatable 3D face from a single image using a detail-consistency loss to disentangle person-specific wrinkles from expression-dependent deformations.

Facial

Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, Baoquan Chen

Neural blend shapes learned jointly with skeleton articulations, producing pose-dependent non-linear deformations from a single neutral-pose mesh.

Skinning / ML Deformation

Yu Ding

NetEase presents a deep learning system generating full-body NPC animation including lips, facial expression, head rotation, and gestures from speech in under 500ms, eliminating manual mocap processing.

Motion Synthesis / Facial

Will Telford

Senior Product Owner Will Telford presents the Maya 2022 rigging updates including Component Tags, Deformer Falloffs, and topology-independent procedural workflows for character deformation.

Rigging / Skinning

Alexander Richard, Michael Zollhoefer, Yandong Wen, Fernando de la Torre, Yaser Sheikh

Disentangles audio-correlated and audio-uncorrelated facial motion via a categorical latent space and cross-modality loss for full-face animation.

Facial / Motion Synthesis

Michal Mach, Maksym Zhuravlov

Naughty Dog technical animators documented the challenges and solutions of shipping motion matching in The Last of Us Part II, from early excitement through production hurdles to final acclaim.

Motion Synthesis

Sebastian Starke, Yiwei Zhao, Fabio Zinno, Taku Komura

Neural animation layering system enabling real-time synthesis of complex martial arts movements by composing motion layers with learned networks.

Motion Synthesis

Sida Peng, Yuanqing Zhang, Yinghao Xu, Qianqian Wang, Qing Shuai, Hujun Bao, Xiaowei Zhou

Anchors per-frame neural radiance latent codes to a deformable SMPL mesh so that sparse-view observations are integrated across time for dynamic human reconstruction.

ML Deformation / Skinning

Hugo Bertiche, Meysam Madadi, Sergio Escalera

Formulates physics-based simulation as an implicit deep learning loss to unsupervisedly learn garment pose space deformation bases for dressed humans, matching PBS quality in comparable training time.

CFX / ML Deformation

Pei Xu, Ioannis Karamouzas

Particle filtering policy network enabling continuous control of physically simulated characters with improved robustness and diversity.

Motion Synthesis

George Brown, Rahul Narain

Upsampling approach that adds high-resolution wrinkle detail to low-resolution cloth simulations using physics-inspired priors for game use.

CFX

Marc Habermann, Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Gerard Pons-Moll, Christian Theobalt

Real-time neural character deformation combining skeleton-driven skinning with learned dynamic detail including cloth and soft-tissue effects.

ML Deformation / Skinning

Ferris Webby, Todd Hill, Brian Anderson, Chris Pagoria, Christian Haniszewski, Daniel Lima

Blue Sky Studios' Universal Mesh-centered pipeline integrating automated rig landmark placement, geometry-driven rigging tools, and stylized simulation-based deformation.

Rigging / Skinning

Riham Toulan, Epic Games

A closer look at MetaHuman rigs in Maya and Unreal Engine, covering customization workflows for high-fidelity digital human characters.

Rigging / Facial / Skinning

Ze Yang, Shenlong Wang, Sivabalan Manivasagam, Zeng Huang, Wei-Chiu Ma, Xinchen Yan, Ersin Yumer, Raquel Urtasun

Jointly learns implicit shape, skeleton topology, and skinning weight fields from data, enabling animation and novel view synthesis from RGB or LiDAR input.

Skinning / ML Deformation / Rigging

Shunsuke Saito, Jinlong Yang, Qianli Ma, Michael J. Black

Converts raw 3D scans of clothed humans into animatable avatars using locally pose-aware implicit functions for pose-dependent correctives without mesh registration.

Skinning / CFX / ML Deformation

Lucio Moser, Chinyu Chien, Mark Williams, Jose Serra, Darren Hendler, Douglas Roble

Unsupervised image-to-image translation learns a shared latent space from video, then a supervised linear mapping drives character facial animation coefficients for production.

Facial / Retargeting

Industrial

Step-by-step guide to configuring the MotionBuilder Live Link plugin for streaming real-time mocap and character animation from MotionBuilder 2022 directly into Unreal Engine 5 for virtual production previsualization.

Retargeting / Motion Synthesis

Eston Schweickart, Xiao Zhai

Production cloth simulator using bilinear quad elements, improving stability and artist controllability over traditional triangle-based approaches.

CFX

Enric Corona, Albert Pumarola, Guillem Alenya, Gerard Pons-Moll, Francesc Moreno-Noguer

An implicit function conditioned on SMPL parameters and a semantically interpretable latent code generates clothing of diverse topologies including open jackets, skirts, and shoes.

CFX / ML Deformation

Xu Chen, Yufeng Zheng, Michael J. Black, Otmar Hilliges, Andreas Geiger

Proposes forward skinning for neural implicit surfaces via iterative root finding with analytical implicit-differentiation gradients, enabling end-to-end training from posed meshes.

Skinning / ML Deformation

Levi Fussell, Kevin Bergamin, Daniel Holden

Supervisory signal method for physics-based motion tracking that enables simulated characters to closely follow diverse motion reference clips.

Motion Synthesis

Chris Lewin, James Power, James Cobb

First shipped game neural cloth system predicting jersey deformations and normal-map details from skeleton pose at real-time rates in Madden NFL 21.

CFX / ML Deformation

Damien Rohmer, Marco Tarini, Niranjan Kalyanasundaram, Faezeh Moshfeghifar, Marie-Paule Cani, Victor Zordan

Per-vertex deformations derived from skeletal linear and angular velocities add cartoon squash-and-stretch effects on top of standard skinning in real time.

Skinning

Avneet Kaur, Johann Francois Coetzee

Novel techniques for simulating Southeast Asian wrapped garments (sampot, dhoti, bust-wraps) outside the standard seam-based pattern pipeline in Raya.

CFX

Ning Jin, Yilin Zhu, Zhenglin Geng, Ron Fedkiw

Represents garment deformations as UV-space images enabling convolutional neural networks to predict pose-dependent clothing deformation efficiently.

CFX / ML Deformation

Steven L. Song, Weiqi Shi, Michael Reed

Deep network for approximating complex face rig computations using differential subspace reconstruction for real-time face deformation.

Facial / ML Deformation

Yuzhu Dong, Andreas Aristidou, Ariel Shamir, Moshe Mahler, Eakta Jain

CycleGAN on motion words transfers adult mocap into child motion style without temporal alignment of training sequences.

Motion Synthesis / Retargeting

Kristopher Campbell, Jonas Jarvers

Hybrid simulation and animation rig for Onward's Dad character using tetrahedral volumes with rest-state deformation and animator-controllable targeting.

CFX / Rigging

Hung Yu Ling, Fabio Zinno, George Cheng, Michiel van de Panne

Learns autoregressive conditional VAEs of human motion whose latent space serves as action space for deep reinforcement learning controllers achieving goal-directed locomotion.

Motion Synthesis

Nuttapong Chentanez, Miles Macklin, Matthias Muller, Stefan Jeschke, Tae-Yong Kim

Triangle mesh CNN regresses clothing deformation from character poses and hand skin deformation from joint angles on manifold meshes.

CFX / ML Deformation / Skinning

Stephen Lombardi, Jason Saragih, Tomas Simon, Yaser Sheikh

Neural avatars for telepresence using variational autoencoders to encode facial expressions into compact latent codes for real-time rendering.

Facial / ML Deformation

Jiayi Eris Zhang, Seungbae Bang, David I. W. Levin, Alec Jacobson

Enriches rig animations with elastodynamic secondary motion in the subspace orthogonal to rig displacements.

ML Deformation / Muscles

Bohan Wang, Jernej Barbic

GPU CUDA implementation of reduced-coordinate deformable-body simulation with optimized memory layout for real-time character deformation.

ML Deformation

Gaspard Zoss, Eftychios Sifakis, Markus Gross, Derek Bradley, Thabo Beeler

Data-driven method to extract and separately compose secondary dynamic effects from facial performance capture for enhanced realism.

Facial

Theodore Kim, David Eberle

Course covering Pixar's Fizt simulator improvements for speed, robustness, and generality deployed across Coco, Cars 3, and Onward.

CFX / ML Deformation

Jiaman Li, Zheng-Fei Kuang, Yajie Zhao, Mingming He, Karl Bladin, Hao Li

Generates personalized blendshapes, physically-based textures, and full facial rig from a single face scan automatically.

Facial / Rigging

Emma Carrigan, Eduard Zell, Cedric Guiard, Rachel McDonnell

Integer optimization selects a minimal set of scanning poses with non-overlapping blendshapes for efficient blendshape transfer.

Facial

Renjie Li

NetEase presents a differentiable neural renderer that translates a single face photo into RPG character rig parameters, enabling automatic character creation from real faces.

Facial / ML Deformation

Sarah Radzihovsky, Fernando de Goes, Mark Meyer

Machine learning method that approximates complex facial rig deformations, reducing evaluation cost and enabling portability of proprietary Pixar rigs.

Facial / ML Deformation

Curtis Andrus, Junghyun Ahn, Michele Alessi, Abdallah Dib, Philippe Henri Gosselin, Cedric Thebault, Louis Chevallier, Marco Romeo

Scalable facial performance capture system for VFX using deep learning to track and solve detailed facial motion at production scale.

Facial

Haotian Yang, Hao Zhu, Yanru Wang, Mingkai Huang, Qiu Shen, Ruigang Yang, Xun Cao

18,760 pore-level textured 3D faces from 938 subjects with 20 expressions, with a riggable 3D face prediction method from single images.

Facial

Mengjiao Wang, Derek Bradley, Stefanos Zafeiriou, Thabo Beeler

Global-local multilinear model synthesizes identity-preserving facial expressions that extrapolate well beyond the training data pool.

Facial

Stephen W. Bailey, Dalton Omens, Paul DiLorenzo, James F. O'Brien

Fast neural network deformer for production facial rigs approximating complex corrective shapes with real-time performance.

Facial / ML Deformation

Alex Rothwell, Manne Öhrström

Framestore's highly parallel dynamics solver for fur and feathers that reduced manual post-simulation fixing by 80% in creature productions.

CFX

Nick Augello, Michael Juarez, Kelly Shay, Arunachalam Somasundaram

Production techniques for a wide range of passive and active hair effects across diverse musical troll tribes in Trolls World Tour.

CFX

Georg Sperl, Rahul Narain, Chris Wojtan

Homogenization approach capturing yarn-level cloth mechanics in a continuum shell model, balancing fidelity and computational cost.

CFX

Minchen Li, Zachary Ferguson, Teseo Schneider, Timothy Langlois, Denis Zorin, Daniele Panozzo, Chenfanfu Jiang, Danny M. Kaufman

Guaranteed intersection- and inversion-free frictional contact for deformables via barrier-augmented incremental potential, independent of time step or material stiffness.

CFX

Aurel Gruber, Marco Fratarcangeli, Gaspard Zoss, Roman Cattaneo, Thabo Beeler, Markus Gross, Derek Bradley

Interactive face sculpting tool guided by an anatomical model of skull, fat, and tissue, producing physiologically plausible digital faces.

Facial / Rigging

Emma Carrigan, Katja Zibrek, Rozenn Dahyot, Rachel McDonnell

Perceptual study and predictive model ranking facial blendshape importance for games to enable efficient rig compression; won MIG 2020 Best Short Paper.

Facial

Luiz Kruel, SideFX

Introduction to KineFX character tools for game development, covering geometry-level rigging, motion editing, and animation retargeting to refine motion libraries.

Rigging / Retargeting

Daniel Holden, Oussama Kanoun, Maksym Perepichka, Tiberiu Popa

Compresses motion matching into neural networks, keeping its controllability with a fraction of the memory.

Motion Synthesis

Qianli Ma, Jinlong Yang, Anurag Ranjan, Sergi Pujades, Gerard Pons-Moll, Siyu Tang, Michael J. Black

CAPE trains a conditional Mesh-VAE-GAN to generate pose-dependent clothing deformations as an additive term on SMPL, introducing the first large-scale dynamic clothed human mesh dataset.

CFX / ML Deformation

Sebastian Starke, Yiwei Zhao, Taku Komura, Kazi Zaman

Local phase representation per body part enabling neural networks to learn multi-contact character movements without global phase ambiguity.

Motion Synthesis

Simon Clavet

Ubisoft Montreal trained a deep reinforcement learning agent to follow motion-matching output while self-balancing physically, advancing toward interactive ragdoll characters that recover from disturbances.

Motion Synthesis / Muscles

Daniel Holden

Shows neural network approximations of interactive cloth and physics simulations achieving 300-5000x speedup, enabling new simulation budgets without replacing conventional physics solvers.

ML Deformation / CFX

Patrick Coleman, Laura Murphy, Markus Kranzler, Max Gilbert

Describes the pipeline for Soul's volumetric characters, procedurally generating volumes and linework from standard surface geometry rigs on the renderfarm.

Rigging

Haegwang Eom, Daseong Han, Joseph S Shin, Junyong Noh

Physics-based character animation using model predictive control paired with a visuomotor perception system for reactive locomotion.

Motion Synthesis

Cristian Romero, Miguel A. Otaduy, Dan Casas, Jesus Perez

Hybrid SMPL-FEM avatar with custom nonlinear anisotropic material; skin thickness and mechanical properties optimized from 4D captures.

Skinning / Muscles

Gustav Eje Henter, Simon Alexanderson, Jonas Beskow

Autoregressive normalising-flow model produces diverse, controllable locomotion sequences trained with exact maximum likelihood.

Motion Synthesis

SangBin Kim, Inbum Park, Seongsu Kwon, JungHyun Han

Unsupervised temporal dilated convolution network retargets motion across humanoids of different skeleton proportions while preserving high-frequency detail.

Retargeting

Marco Romeo, Carlos Monteagudo, Daniel Sanchez-Quiros

Extends XPBD to muscle fibers and fascia constraints, enabling fast controllable character muscle and superficial fascia simulation without FEM complexity.

Muscles / CFX

Justus Thies, Mohamed Elgharib, Ayush Tewari, Christian Theobalt, Matthias Niessner

Audio-driven facial video synthesis via a latent 3D face model space, enabling video dubbing and cross-person reenactment with temporal stability.

Facial

Autodesk

Autodesk University class covering Maya 2020 rigging additions including Offset Parent Matrix, UV Pin, Proximity Pin, Rivet, Motion Library, and animation workflow enhancements for facial and character pipelines.

Rigging / Retargeting

Timothy Jeruzalski, David I. W. Levin, Alec Jacobson, Paul Lalonde, Mohammad Norouzi, Andrea Tagliasacchi

Uses a pose-conditioned neural network to invert LBS deformations, enabling efficient canonical-space queries such as signed distance lookups for deformed characters.

Skinning / ML Deformation

Fabrizio Corda, Jean-Marc Thiery, Marco Livesu, Enrico Puppo, Tamy Boubekeur, Riccardo Scateni

Couples cage and skeleton deformation spaces into a unified real-time framework, accessing poses unreachable by either control structure alone.

Skinning / Rigging

Kevin Bergamin

GDC talk presenting DReCon-based production system combining motion matching and physics control for responsive game character animation.

Motion Synthesis

Zhan Xu, Yang Zhou, Evangelos Kalogerakis, Chris Landreth, Karan Singh

Neural network predicting skeleton topology and skinning weights from 3D character meshes, automating the character rigging process.

Rigging / ML Deformation

Felix Harvey, Mike Yurick, Christopher Pal, Derek Nowrouzezahrai

Recurrent neural network for robust keyframe-to-keyframe motion inbetweening producing natural transitions across long time spans.

Motion Synthesis

Fernando de Goes, Patrick Coleman, Michael Comet, Alonso Martinez

Suite of geometric tools for sculpt generation and reuse in character rigs: sculpt transfer, surface reconstruction, and relaxation, showcased on Onward and Soul.

Rigging / Skinning

Gergely Klár, Andrew Moffat, Ken Museth, Eftychios Sifakis

Constitutive model for active elasticity that drives simulated flesh and muscle toward target shapes with production-friendly artist controls.

Muscles

Jeremy Riviere, Paulo Gotardo, Derek Bradley, Abhijeet Ghosh, Thabo Beeler

Single-shot facial capture combining polarized spherical gradient illumination with stereo to recover geometry and skin reflectance simultaneously.

Facial

Kfir Aberman, Peizhuo Li, Dani Lischinski, Olga Sorkine-Hornung, Daniel Cohen-Or, Baoquan Chen

Skeleton-aware graph network for motion retargeting that adapts motion to diverse skeleton proportions while preserving stylistic details.

Retargeting / ML Deformation

Igor Santesteban, Elena Garces, Miguel A. Otaduy, Dan Casas

Recurrent network regresses real-time soft-tissue dynamics as a function of body shape and motion encoded in a nonlinear deformation subspace.

Skinning / ML Deformation

Ahmed A. A. Osman, Timo Bolkart, Michael J. Black

STAR learns spatially local pose-corrective blend shapes with sparse joint influence, reducing SMPL parameters by 80% while improving deformation realism.

Skinning / ML Deformation

Dave Hunt

Unity presented Freeform Animation, a non-destructive technique to preserve motion content while restructuring control rigs, reducing counter-animation work and bottlenecks in standard rigging workflows.

Rigging

Tingwu Wang, Yunrong Guo, Maria Shugrina, Sanja Fidler

Single neural controller masters thousands of motion styles by training on large-scale mocap, showing strong transfer to unseen motions and characters.

Motion Synthesis

Kfir Aberman, Yijia Weng, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen

Encodes motion into disentangled content and style latent codes, applying temporally invariant AdaIN to transfer style extracted directly from RGB video onto 3D animation.

Retargeting / Motion Synthesis

Noah Alzayer

Insomniac Games described integrating approximately 150 vendor-supplied facial rigs for Spider-Man, with streamlined tooling to minimize overhead on character-specific revisions and delivery cycles.

Facial / Rigging

Daniel Holden

Ubisoft La Forge presented neural networks for automatic mocap cleanup, end-to-end facial animation from video, and a machine learning system generating facial animation directly from raw audio.

Facial / ML Deformation

Mike Cozens

Described Weta's FACS-plus-deep-learning performance capture pipeline used to translate Rosa Salazar's performance onto the hyper-stylised Alita character.

Facial / Retargeting

Bruno Velazquez

Santa Monica Studio detailed how they rebuilt Kratos's animation pipeline to convey humanity and narrative depth, transforming the franchise's approach to character performance.

Motion Synthesis / Rigging

Daniel Cudeiro, Timo Bolkart, Cassidy Laidlaw, Anurag Ranjan, Michael J. Black

VOCA: speech-driven 3D facial animation system trained on 29 minutes of 4D scans at 60 fps from 12 speakers, generalizing across identities.

Facial / Motion Synthesis

Binh Huy Le, J. P. Lewis

Folds the iterative delta mush smoothing into a single precomputed direct skinning operator, making it real-time and game-ready.

Skinning

Kevin Bergamin, Simon Clavet, Daniel Holden, James Forbes

Physics-based character controller combining motion matching for reference generation with tracking control for responsive, physically plausible animation.

Motion Synthesis

Autodesk

Demonstrates the Offset Parent Matrix attribute in Maya 2020, which drives transforms via a single matrix connection, eliminating offset group nodes and reducing scene complexity for lighter rigs.

Rigging

Georgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. Osman, Dimitrios Tzionas, Michael J. Black

SMPL-X unifies body, face, and fully articulated hands into a single 10,475-vertex parametric model with 54 joints and a learned variational pose prior.

Facial / Retargeting / Skinning

Justus Thies

Presented real-time facial performance capture and face reenactment using commodity RGB cameras, demonstrating practical applications for character animation.

Facial / Retargeting

Jing Li, Tiantian Liu, Ladislav Kavan

Projective dynamics method for simulating deformable character bodies coupled to articulated skeletons with robust contact handling.

Skinning / Muscles

Bohan Wang, George Matcuk, Jernej Barbic

Acquires complete hand bone anatomy in multiple poses via stabilized MRI and builds animation-ready volumetric hand rigs from medical imaging data.

Muscles / Skinning

Michael Bao, Matthew Cong, Stephane Grabli, Ronald Fedkiw

Makes a muscle-based facial system fully differentiable by coupling it with a blendshape basis, enabling both optimization and learning-based performance capture.

Facial / Muscles

Hayley Iben, Jacob Brooks, Christopher Bolwyn

Practical force and constraint techniques for art-directing hair simulation shape across Brave, Inside Out, Good Dinosaur, Coco, and Incredibles 2.

CFX

Autodesk

Autodesk AREA tutorial on MotionBuilder character retargeting, covering characterization, merging source and target skeletons, IK Blend settings, fixing retargeting errors, and baking animation to a character.

Retargeting / Motion Synthesis

Yeongho Seol, Michael Cozens

Interactive system for editing performance-captured facial animation, allowing artists to intuitively adjust and correct captured data.

Facial

Jean-Sebastien Campagna, Olivier Dionne, Dave Hunt

Unity showcased predefined constraints for procedurally controlling character deformations, physics-based secondary motion simulation, and runtime blending within their Animation Rigging package.

Rigging / Skinning

Lawson Fulton, Vismay Modi, David Duvenaud, David I.W. Levin, Alec Jacobson

Autoencoder neural network defines a nonlinear reduced space for deformable solid dynamics, solving implicit integration in latent space.

ML Deformation

Tuanfeng Y. Wang, Tianjia Shao, Kai Fu, Niloy J. Mitra

Encodes garment deformations in a low-dimensional intrinsic space learned from simulation, enabling interactive authoring and blending of garment animations.

CFX

Jungdam Won, Jehee Lee

Parametric physics-based controller generalizes locomotion across characters with different heights, weights, and body proportions.

Motion Synthesis

Kfir Aberman, Rundi Wu, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

Disentangled motion representation separating content from style enabling video-to-video motion retargeting without 3D reconstruction.

Retargeting / ML Deformation

Igor Santesteban, Miguel A. Otaduy, Dan Casas

Recurrent neural network predicts garment drape and wrinkles as a function of body shape and dynamics in a few milliseconds.

CFX / ML Deformation

Will Telford

Will Telford introduces the Proximity Pin node in Maya 2020, which tracks a transform to the closest point on a deforming surface to support facial rigging and secondary attachment workflows.

Rigging

Will Telford

Senior Maya Product Owner Will Telford demonstrates the GPU-accelerated Proximity Wrap deformer introduced in Maya 2020, which binds geometry by proximity without requiring a rest-pose and is topology-independent.

Skinning / Rigging

Fabio Zinno

EA covered the gap between motion matching and full synthesis, detailing Phase-Functioned and Mode-Adaptive Neural Networks as practical next steps for animation system design in games.

Motion Synthesis / ML Deformation

Ylva Ferstl, Michael Neff, Rachel McDonnell

GAN framework maps speech to 3D conversational gesture motion using separate adversaries for dynamics, joint plausibility, and diversity.

Motion Synthesis / Facial

Sebastian Starke, He Zhang, Taku Komura, Jun Saito

Neural state machine for character-scene interaction synthesis generating contextual motions like sitting, picking up objects, and navigating environments.

Motion Synthesis

Lijuan Liu, Youyi Zheng, Di Tang, Yi Yuan, Changjie Fan, Kun Zhou

Deep graph network for automatic skinning weight prediction generalizing to production characters from learned geometric and topological features.

Skinning / ML Deformation

Pascal Berard, Derek Bradley, Markus Gross, Thabo Beeler

Multi-view imaging system and parametric rig estimate person-specific eyeball shape, rotation center, and visual axis at submillimeter accuracy.

Rigging / Facial

Vincent Barrielle, Nicolas Stoiber

First real-time physics-based facial animation method driven by performance capture, using projective dynamics on volumetric skin.

Facial

Stephen Shaw

Ubisoft ALICE studios showed how neural networks can fully automate motion capture cleanup and delivery, covering implementation challenges and practical integration into capture studio workflows.

Motion Synthesis / ML Deformation

Maksym Perepichka, Daniel Holden, Sudhir P. Mudur, Tiberiu Popa

Automatic method for repairing missing and noisy marker trajectories in mocap data using kinematic skeleton as a reference.

Retargeting

Seunghwan Lee, Moonseok Park, Kyoungmin Lee, Jehee Lee

Two-level imitation learning drives a full-body model with 346 muscles to reproduce diverse locomotion skills at interactive rates.

Muscles / Motion Synthesis

Cameron Black, Nicholas Burkard, Dmitriy Pinskiy

Scriptable CFX framework integrating cloth, hair, and secondary dynamics into a unified character effects pipeline.

CFX / Rigging

Fernando de Goes, Doug L. James

Extends Kelvinlet sculpting with a multi-scale convolution scheme enabling cusp-like elastic edits with sharp, localised falloff profiles.

Rigging / Skinning

Nicholas Augello, Arunachalam Somasundaram

DreamWorks production fur dynamics system driving secondary motion on characters through efficient simulation and procedural techniques.

CFX

James Gu, Ozgur Aydogdu, Steven Song

Head rig for Spies in Disguise pigeons where beak and facial features slide freely on curved head volumes, enabling 2D-inspired expressions on 3D characters.

Rigging / Facial

Miles Macklin, Kier Storey, Michelle Lu, Pierre Terdiman, Nuttapong Chentanez, Stefan Jeschke, Matthias Muller

Shows that many small substeps with simple per-step constraint projection outperforms fewer large-step implicit integration for cloth and soft bodies.

CFX

Sehee Min, Jungdam Won, Seunghwan Lee, Jungnam Park, Jehee Lee

Simulates and controls deformable invertebrate characters using muscle-like actuators with contact-rich locomotion.

Muscles / Motion Synthesis

Daniel Holden, Bang Chi Duong, Sayantan Datta, Derek Nowrouzezahrai

Neural network trained in a learned subspace to replace expensive physics simulation with fast interactive deformation for characters.

ML Deformation / Skinning

Jesus R. Nieto, Charlie Banks, Ryan Chan

Framework for abstracting core rigging concepts to build extensible, future-proof character rigging systems for production.

Rigging

Rebecca Hallac, Christopher Moore

System for continuously monitoring rig performance health metrics at Blue Sky Studios, enabling real-time rig evaluation during production using ChopRig and Conduit.

Rigging

Gaspard Zoss, Derek Bradley, Pascal Berard, Thabo Beeler

Empirically derived rig for realistic jaw animation, capturing biomechanical jaw motion from data for use in facial character rigs.

Facial / Rigging

Jie Li, Gilles Daviet, Rahul Narain, Florence Bertails-Descoubes, Matthew Overby, George E. Brown, Laurence Boissieux

Implicit frictional contact solver integrated with adaptive remeshing for robust, stable cloth simulation under complex contact scenarios.

CFX

Richard Oud

Guerrilla Games covered the full machine character pipeline for Horizon Zero Dawn, from pre-production prototyping to final polish including animation-tech, AI behavior, and motion style.

Rigging / Motion Synthesis

Fernando de Goes, William Sheffler, Michael Comet, Alonso Martinez, Aimei Kutt

Course covering Pixar's full costume pipeline from design through tailoring and simulation, illustrated with examples from Coco and Incredibles 2.

CFX

Taeil Jin, Meekyoung Kim, Sung-Hee Lee

Volumetric aura mesh surrounding each character encodes proximity relationships, preserving interaction semantics during motion retargeting.

Retargeting

Darren Hendler, Lucio Moser, Rishabh Battulwar, David Corral, Phil Cramer, Ron Miller, Rickey Cloudsdale, Doug Roble

Direct Drive retargeting system used on Thanos in Avengers, bypassing traditional blendshape solvers by learning a direct mapping from actor performance to character.

Facial

David Eberle

Improves Pixar's Fizt cloth solver with enhanced collision handling and performance gains, addressing the high cloth demand of Coco's skeleton cast.

CFX

Daniel Holden

Ubisoft La Forge demonstrated how neural networks can build scalable animation systems for games, covering Phase-Functioned and Mode-Adaptive Neural Networks for character locomotion.

Motion Synthesis / ML Deformation

Daniel S. Lima

Blue Sky Studios technique that fragments character geometry into independently-evaluating pieces processed in parallel, then recombined via SubDeform to hit 24 fps targets.

Rigging

Audrey Wong, David Eberle, Theodore Kim

Applies volume simulation to character meshes before cloth simulation to eliminate self-intersections, used in production on Pixar's short Bao.

CFX

Chris Lewin

EA presented a predictive-contact approach to cloth self-collision that supports large simulation timesteps with only a single collision sweep, costing a few milliseconds per CPU thread.

CFX

Steve Caulkin

Cubic Motion CEO traces the evolution of their markerless facial tracking and mocap-solving AI across three real-time digital human projects, showing advances in performance fidelity.

Retargeting / Facial

Xinyi Zhang, Michiel van de Panne

Autoregressive RNN conditioned on target keyframes automatically completes motions matching sparse user-specified poses; won MIG 2018 Best Paper.

Motion Synthesis

Stephen Lombardi, Tomas Simon, Jason Saragih, Yaser Sheikh

Deep generative model for face appearance and geometry enabling photorealistic rendering and synthesis of facial expressions.

Facial / ML Deformation

Xue Bin Peng, Pieter Abbeel, Sergey Levine, Michiel van de Panne

Physics-based character controller using deep RL to imitate reference motion clips, achieving diverse athletic skills with natural-looking dynamics.

Motion Synthesis

Fernando de Goes, Doug L. James

Real-time physically based secondary animation using analytic elastodynamic solutions, enabling compressive and shear wave effects on characters.

Rigging / ML Deformation

Stephen W. Bailey, Dave Otte, Paul Dilorenzo, James F. O'Brien

Neural networks learn a film rig's nonlinear deformations so approximated characters run interactively, the paper that opened the ML deformer era.

ML Deformation / Skinning

Seung-Hwan Jung, Sung-Hee Lee

Reconstructs simulatable strands from artist-created hair meshes and applies style-specific simulation per cluster for efficiency.

CFX

Avneet Kaur, Maryann Simmons

Introduces hierarchical sculpting controls into Disney's hair pipeline for layered art-direction of hair motion across varying simulation scales.

CFX

Stuart Bryson, Esteban Papp

Dual-representation graph engine that separates authoring nodes from evaluation tasks, achieving a 100x authoring speedup over LibEE v1 in the Premo system.

Rigging

Jay Busch, Mike Seymour

Presented the pipeline behind the MEETMIKE real-time avatar: performance capture, solver, and photorealistic rendering in a live interactive context.

Facial / Retargeting

He Zhang, Sebastian Starke, Taku Komura, Jun Saito

Mode-adaptive neural network with learned gating for quadruped locomotion control handling diverse gaits and transitions.

Motion Synthesis

Simon Clavet, David Rosen

Follow-up GDC bootcamp session expanding motion matching with advanced trajectory control and production implementation strategies.

Motion Synthesis

Richard Andrew Roberts, J P Lewis, Ken Anjyo, Jaewoo Seo, Yeongho Seol

Optimal keyframe selection algorithm for motion capture data that minimizes reconstruction error while enabling interactive artist-driven control.

Retargeting

Ian Comley

Surveyed ILM's multi-decade evolution in photoreal character and digital human creation, from early tests through modern deep-learning-assisted pipelines.

Facial / Skinning

Fernando de Goes, William Sheffler, Michael Comet, Alonso Martinez, Aimei Kutt

Transfers a desired edge-loop patch layout from a reference mesh to deformed meshes via decal-map-weighted relaxation, used on Bao and Incredibles 2.

Rigging / Skinning

Jalpesh Sachania

EA Frostbite explains driven-ragdoll technology blending physics reactivity with animation adherence, covering performance optimisation, multiplayer synchronisation, and emergent procedural motion generation.

Rigging / Muscles

Nuttapong Chentanez, Matthias Muller, Miles Macklin, Viktor Makoviychuk, Stefan Jeschke

Physics-based character controller that imitates motion capture reference with deep reinforcement learning, producing physically plausible results.

Motion Synthesis / Retargeting

Axel Akesson

MPC Asset Supervisor details creation of the photoreal digital Rachael character, presenting techniques for crossing the uncanny valley on a human CG face.

Facial

Ryan Kautzman, Gordon Cameron, Theodore Kim

Addresses Incredibles 2 skin simulation using 2D ray-tracing over mesh surfaces for fast, robust secondary motion on superhero characters.

CFX / Muscles

Xue Bin Peng, Angjoo Kanazawa, Jitendra Malik, Pieter Abbeel, Sergey Levine

Physics-based character learns to imitate athletic motions reconstructed from monocular video using deep RL.

Motion Synthesis

David Minor, David Corral

ADMM-based creature tools for muscle, skin, and fatty tissue simulation achieving anatomically accurate dynamic deformation, demonstrated on Avengers: Infinity War characters.

Muscles / CFX

Zhiguang Liu, Antonio Mucherino, Ludovic Hoyet, Franck Multon

Retargeting method preserving spatial relationships between body surface vertices rather than only skeletal joints.

Retargeting / Skinning

JP Lewis

Compared classical FACS/blend-shape facial pipelines against emerging neural-network approaches for character face deformation at production scale.

ML Deformation / Facial

Jeremy Yates, Almudena Soria

Naughty Dog lead animators cover Uncharted 4's full animation pipeline from previs through motion capture and final polish, plus rapid animation prototyping to accelerate design decisions.

Retargeting

Tero Karras, Timo Aila, Samuli Laine, Antti Herva, Jaakko Lehtinen

End-to-end deep learning system for speech-driven facial animation jointly learning lip sync, head pose, and emotional expression.

Facial / Motion Synthesis

Loic Ciccone, Martin Guay, Maurizio Nitti, Robert W. Sumner

Interactive authoring system for creating cyclic character motions by sketching and blending loop templates via direct manipulation.

Motion Synthesis / Retargeting

Autodesk

Official Autodesk feature demo of the Delta Mush deformer, which acts as a low-pass filter to remove skinning artifacts and restore rest-shape volume on deforming characters.

Skinning / ML Deformation

Gerard Pons-Moll, Sergi Pujades, Sonny Hu, Michael Black

4D scanning system that captures detailed clothing geometry and body motion simultaneously, enabling garment retargeting to new body shapes.

CFX / Retargeting

Meekyoung Kim, Gerard Pons-Moll, Sergi Pujades, Seungbae Bang, Jinwook Kim, Michael J. Black, Sung-Hee Lee

Learns pose-dependent soft-tissue dynamics from FEM simulation data and embeds them in a real-time statistical skin model.

Muscles / Skinning / ML Deformation

Jun Saito, Simon Yuen

Efficient simulation of skin sliding over underlying anatomy, capturing the biomechanical offset behavior of skin relative to muscle.

Skinning / Muscles

Alex Smith, Sven Pohle, Wan-Chun Ma, Chongyang Ma, Xian-Chun Wu, Yanbing Chen, Etienne Danvoye, Jorge Jimenez, Sanjit Patel, Mike Sanders, Cyrus A. Wilson

End-to-end facial performance pipeline for real-time games combining performance capture, blendshape solving, and photoreal rendering.

Facial

Yeara Kozlov, Derek Bradley, Moritz Bächer, Bernhard Thomaszewski, Thabo Beeler, Markus Gross

Augments blendshape rigs with finite-element tissue simulation to add physically plausible secondary dynamics during facial animation.

Facial / Muscles

Roger Blanco i Ribera, Eduard Zell, J. P. Lewis, Junyong Noh, Mario Botsch

Automatically aligns source and target blendshape ranges of motion for retargeting, reducing artist intervention while preserving intended expression style.

Facial / Retargeting

Tianye Li, Timo Bolkart, Michael J. Black, Hao Li, Javier Romero

FLAME model: articulated jaw, neck, and eyeballs with pose-dependent and expression blendshapes trained on 33,000 3D scans.

Facial

Xue Bin Peng, Michiel van de Panne

Systematic study of action space design choices for deep reinforcement learning locomotion controllers for simulated characters.

Motion Synthesis

Lana Lan, Matthew Cong, Ronald Fedkiw

Retrospective on developing and refining a physics-based facial muscle model for production, covering lessons in anatomical modeling.

Muscles / Facial

Lucio Moser, Darren Hendler, Doug Roble

Modular ML pipeline that adds fine-scale wrinkle and expression detail to sparse head-mounted camera marker data, used in Digital Domain's production capture workflow.

Facial

Autodesk

Autodesk walkthrough of two deformation tools added in Maya 2017 Update 3: the Tension deformer for surface-tension effects and the Bake Deformer Tool for converting complex deformers to skin weights for game engine export.

Skinning / Rigging

Antonin Bernardin, Ludovic Hoyet, Antonio Mucherino, Douglas Soares Gonçalves, Franck Multon

Frame-based retargeting using normalized Euclidean distance matrices of inter-joint distances to transfer motion across differently proportioned skeletons.

Retargeting

Alexandru Eugen Ichim, Petr Kadlecek, Ladislav Kavan, Mark Pauly

Simulates facial expressions via nonlinear energies modeling passive flesh, active muscles, and rigid bone; supports inertia, skin sliding, and collision handling.

Facial / Muscles

Daniel Holden, Taku Komura, Jun Saito

A phase-conditioned network that generates real-time locomotion, the breakthrough for neural character controllers.

Motion Synthesis

Michal Mach

Describes Naughty Dog's physics layer on top of gameplay animation in Uncharted 4, enabling cloth and secondary-motion with predictable artist control and minimal visual distortion.

CFX

Samuli Laine, Tero Karras, Timo Aila, Antti Herva, Shunsuke Saito, Ronald Yu, Hao Li, Jaakko Lehtinen

Deep CNN system for production facial performance capture achieving real-time tracking speed with production-quality reconstruction accuracy.

Facial / ML Deformation

Fernando de Goes, Doug L. James

Closed-form elastic sculpting brushes for volume-preserving grab, scale, twist, and pinch used in character pose-space sculpting workflows.

Rigging / Skinning

Jaewon Song, Roger Blanco I Ribiera, Kyungmin Cho, Mi You Seoul, J P Lewis, Byungkuk Choi, Junyong Noh

Optimization method for computing sparse rig parameter values that reproduce animator-specified poses with minimal parameter usage.

Rigging

Marc Thyng, Christopher Evart, Toby Jones, Aleka McAdams

Production pipeline for Moana's complex curly hair with heavy character and environment interaction, introducing a new hair model with overhauled collision handling.

CFX

Brian Missey, Megha Davalath, Arunachalam Somasundaram

Describes the grooming, rigging, and simulation pipeline for character-connected hair shared between conjoined twins in Trolls.

CFX

Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt

Real-time full-body 3D pose estimation from a single RGB camera at over 30fps enabling markerless mocap for interactive applications.

Retargeting

Daniel Holden, Jun Saito, Taku Komura

Convolutional autoencoder for human motion that enables synthesis and editing of character motion sequences in a compact latent space.

Motion Synthesis

Chenglei Wu, Derek Bradley, Markus Gross, Thabo Beeler

Anatomically constrained local deformation model for monocular face capture that prevents physically implausible face reconstructions.

Facial

Kristjan Zadziuk

Ubisoft Toronto presented motion matching as a practical replacement for manually crafted animation trees, demonstrating high-quality fluid locomotion from dense mocap databases.

Motion Synthesis

Dan Lowe

Presents Ubisoft Montreal's scripted mocap automation toolset that reduces manual cleanup and retargeting labour across large-scale game productions with hundreds of characters.

Retargeting

Quentin Avril, Donya Ghafourzadeh, Srinivasan Ramachandran, Sahel Fallahdoust, Sarah Ribet, Olivier Dionne, Martin de Lasa, Eric Paquette

Transfers skeleton structure and skinning weights between characters with different mesh topologies without manual re-rigging.

Rigging / Skinning / Retargeting

Matthew Cong, Kiran S. Bhat, Ronald Fedkiw

Art-directable muscle simulation system for face and body allowing artists to achieve specific looks while respecting physics constraints.

Muscles / Facial

Moritz Bächer, Stelian Coros, Bernhard Thomaszewski

Shape space construction method for planar mechanical design, enabling balanced motion planning for articulated characters and mechanisms.

Rigging

Vincent Barrielle, Nicolas Stoiber, Cedric Cagniart

Treats blendshapes as force bases rather than shape bases, enabling dynamic and physically plausible facial animation and retargeting.

Facial

Alexandru Eugen Ichim, Ladislav Kavan, Merlin Nimier-David, Mark Pauly

System for constructing personalized volumetric facial rigs from scans, combining blendshapes with physics simulation for expressive animation.

Facial / Rigging / Muscles

Min Tang, Huamin Wang, Le Tang, Ruofeng Tong, Dinesh Manocha

GPU cloth pipeline that integrates contact forces into implicit time integration via parallelized sparse matrix assembly for 100-300K triangle garments.

CFX

Yeongho Seol, Wan-Chun Ma, J P Lewis

Pipeline for building a personalized facial rig directly from performance-capture data, fitting blendshape bases to actor-specific motion.

Facial / Rigging

Sheldon Stopsack

Covered MPC techniques for photorealistic digital humans including skin shader behaviour, facial animation, and underlying muscle simulation.

Facial / Muscles / Skinning

Tomohiko Mukai, Shigeru Kuriyama

Low-rank helper bone framework efficiently captures pose-dependent skinning deformations by learning auxiliary joint transforms from examples.

Skinning

Justus Thies, Michael Zollhofer, Marc Stamminger, Christian Theobalt, Matthias Niessner

Real-time face reenactment system transferring facial expressions from a source actor to a target in monocular video using dense tracking.

Facial

Antti Herva, Kevin Margo

Workshop showing DI4D surface capture pipelines for Remedy's Quantum Break and Blur Studio's Agent Six virtual-Angela-Bassett character.

Facial / Retargeting

Ryan Kautzman, Bill Wise, Meng Yu, Per Karlsson, Mark Hessler, Audrey Wong

Describes the simulation rig for Finding Dory's septapus Hank, covering flesh simulation, sucker dynamics, and mantle behavior built on a complex animation rig.

CFX / Rigging

Clifford Roche, Carlos Torres-Cros

Ubisoft replaced reactive foot IK with a predictive biomechanical model for Assassin's Creed, producing more fluid and accurate foot placement that preserves source animation detail.

Rigging / Skinning

Andy Milne, Mark McLaughlin, Rasmus Tamstorf, Alexey Stomakhin, Nicolas Burkhard, Mitch Counsell, Jesus Canal, David Komorowski, Evan Goldberg

Character soft-tissue simulation system for Zootopia scaling from hero to crowd characters, capturing subtle animal flesh and fur dynamics with artistic controls.

Muscles / CFX / Skinning

James Jacobs, Jernej Barbic, Essex Edwards, Crawford Doran, Andy van Straten

Production overview of physics-based character animation combining FEM muscles, skin, and collision for anatomically driven deformation.

Muscles / Skinning

Thomas Geijtenbeek

GDC talk introducing IK Rig architecture for procedural pose correction and layered animation, foundational to Unreal Engine IK framework.

Rigging

Kyunglyul Hyun, Kyungho Lee, Jehee Lee

Uses formal grammar rewriting rules to synthesize structured motion sequences obeying behavioral rules for multiple characters.

Motion Synthesis

Simon Clavet

Ubisoft's nearest-neighbour search through raw mocap that replaced state-machine locomotion in AAA games (For Honor).

Motion Synthesis

Hongyi Xu, Jernej Barbič

Multiple FEM subspace models are precomputed around representative poses and blended at runtime, adding millisecond-cost secondary dynamics to rigged characters.

ML Deformation / Muscles

Binh Huy Le, Jessica Hodgins

Optimizes per-vertex rotation centers for skeletal skinning, nearly eliminating candy-wrapper and volume-loss artifacts in real time.

Skinning

Petr Kadleček, Alexandru-Eugen Ichim, Tiantian Liu, Jaroslav Křivánek, Ladislav Kavan

Reconstructs internal anatomical structures from surface scans to drive physics-based soft-tissue deformation personalized to individual subjects.

Muscles / Skinning

Pablo Garrido, Michael Zollhoefer, Dan Casas, Levi Valgaerts, Kiran Varanasi, Patrick Perez, Christian Theobalt

Builds personalized 3D facial rigs from monocular video, recovering identity-specific blendshapes for downstream animation and editing.

Facial / Rigging

Stephen W. Bailey, Martin Watt, James F. O'Brien

Method for repurposing authored hand animation across different interactive contexts by adaptively retargeting motion to new constraints.

Rigging / Retargeting

Arunachalam Somasundaram

Production cloth technique for selectively smoothing folds and resolving collisions to improve visual quality of dynamic garment animation.

CFX

Steve Caulkin

Detailed how real-time characters Senua, Siren, and Meetmike were built using motion capture solving and Cubic Motion's performance-transfer pipeline.

Facial / Retargeting

Byungkuk Choi, Roger Blanco i Ribiera, J P Lewis, Yeongho Seol, Seokpyo Hong, Haegwang Eom, Sunjin Jung, Junyong Noh

Sketch-based interface for editing articulated character motion, enabling intuitive spatial control over limb trajectories and poses.

Rigging / Retargeting

Xue Bin Peng, Glen Berseth, Michiel van de Panne

Deep reinforcement learning for terrain-adaptive character locomotion that generalizes to novel obstacles without motion capture references.

Motion Synthesis

Marco Fratarcangeli, Valentina Tibaldo, Fabio Pellacini

Parallel randomized Gauss-Seidel via graph coloring for PBD and Projective Dynamics constraints, achieving millisecond per-frame cloth and soft-body solve on GPU.

CFX

Miles Macklin, Matthias Muller, Nuttapong Chentanez

Extended PBD formulation with compliant constraints providing physically consistent stiffness control independent of timestep size.

CFX

Andrew W. Feng, Dan Casas, Ari Shapiro

Reshapes body scans to human proportions and auto-rigs them into skinned virtual characters using a SCAPE deformable model.

Rigging / Skinning

Prashant Sachdeva, Shinjiro Sueda, Susanne Bradley, Mikhail Fain, Dinesh K. Pai

Simulates hand soft tissue and tendons as a coupled tendon-routing system driven by muscle activations, producing anatomically plausible finger motion.

Muscles / Rigging

Damon Shelton

Naughty Dog examines the motion capture pipeline for The Last of Us, covering data acquisition tools, large dataset management, raw data cleanup, and retargeting animation onto character skeletons.

Retargeting

Shunsuke Saito, Zi-Ye Zhou, Ladislav Kavan

Data-driven anatomical body modeling framework assembling muscles, bones, and fat to build parameterized human body shapes from measurements.

Muscles / Skinning

Rick Hankins, Nick Rasmussen, Andrew Johnson, Stephen Bowline, Brice Criswell

Presents ILM's node-based procedural graph system used for hair instancing, geometry, and character crowd pipelines across dozens of productions.

Rigging / CFX

Sven Pohle, Michael Hutchinson, Brent Watkins, Dick Walsh, Stephen Candell, Frederick Nilsson, Jason Reisig

Overview of DreamWorks Animation's facial motion system covering deformation pipeline, blendshape solving, and production integration.

Facial / Rigging

Graham Fyffe, Andrew Jones, Oleg Alexander, Ryosuke Ichikari, Paul Debevec

Drives sub-millimeter facial scans from video-based performance capture by solving blendshape coefficients from tracked video features.

Facial

Gerard Pons-Moll, Javier Romero, Naureen Mahmood, Michael J. Black

Data-driven model of soft-tissue dynamics learned from 4D body scans, capturing pose-dependent deformations beyond standard skinning.

Skinning / ML Deformation

Alexandru-Eugen Ichim, Sofien Bouaziz, Mark Pauly

System for creating personalized animatable 3D face avatars from casual handheld video using blendshape fitting and rig transfer.

Facial / Rigging

Galen Gornowicz, Silviu Borac

Hybrid direct and projective iterative algorithm for hair simulation with a comprehensive elasticity model and stable collision handling.

CFX

Charles Malleson, Jean-Charles Bazin, Oliver Wang, Derek Bradley, Thabo Beeler, Adrian Hilton, Alexander Sorkine-Hornung

Post-production tool allowing directors to blend between different takes of a facial performance, enabling new emotion transitions via image-space blending.

Facial

Matthew Cong, Michael Bao, Jane L. E, Kiran S. Bhat, Ronald Fedkiw

Fast fully-automatic morphing algorithm creates simulatable flesh and muscle models for human and humanoid faces from a target surface mesh alone.

Facial / Muscles

Adam Burr, Steve Gressak, Matthew Doble, Christian Haniszewski, Ignacio Barrios, Brian Anderson, Ferris Webby

UVN-space facial rig for The Peanuts Movie letting features slide along curved head volumes while preserving 2D shape language, developed with Autodesk for Maya.

Facial / Rigging

Daniel Holden, Jun Saito, Taku Komura

Neural network inverts the rig function, mapping low-level joint positions or surface geometry back to animator-friendly rig control values in real time.

Rigging / Retargeting

Daniel Holden, Taku Komura, Jun Saito, Ikhsanul Habibie

Convolutional autoencoder learning a compact motion manifold from raw motion capture data for synthesis and style transfer.

Motion Synthesis

Yann Pinczon Du Sel, Nicolas Chaverou, Michael Rouille

Presents real-time motion retargeting and interactive motion blending within the Golaem Crowd plugin, reducing asset count for production crowd shots.

Retargeting

Nadine Abu Rumman, Marco Fratarcangeli

Two-layer skinning that applies position-based dynamics constraints on top of LBS to achieve volume preservation and soft jiggle in real time.

Skinning

Russell Gillette, Craig Peters, Nicholas Vining, Essex Edwards, Alla Sheffer

Real-time method adding plausible wrinkle details to coarsely simulated or keyframed cloth by using a data-driven wrinkle prediction model.

CFX

Chen Cao, Derek Bradley, Thabo Beeler, Kun Zhou

Real-time system for capturing high-fidelity facial performance from RGB cameras using a personalized blendshape model.

Facial

Ryan Stelzleni, Bret Parker, Tom Hahn, Sarah Shen, Dan McGarry, Chen Shen

Stroke-based posing tool that snaps multiple joints to a drawn silhouette, used heavily on Inside Out for character and cloth-simulation results tuning.

Rigging

Rasmus Tamstorf, Toby Jones, Stephen F. McCormick

Algebraic multigrid method for accelerating cloth simulation on unstructured meshes with varying material properties and collision constraints.

CFX

Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, Michael J. Black

SMPL body model factoring shape and pose-dependent deformations for efficient synthesis of realistic human body shapes and animations.

Skinning / Retargeting

Alexis Vaisse

Ubisoft analyzed cloth simulation performance in Assassin's Creed Unity and Far Cry 4, then ported the system to GPU compute shaders achieving over 10x performance improvement.

CFX

Pablo Garrido, Levi Valgaerts, Hamid Sarmadi, Ingmar Steiner, Kiran Varanasi, Patrick Perez, Christian Theobalt

Monocular face modification system for dubbing, aligning lip motion to dubbed audio by warping the actor's mouth region.

Facial

Menglei Chai, Changxi Zheng, Kun Zhou

Guide-strand reduced model with optimal interpolation relationships simulates 150K hair strands in real time with a hair-correction collision pass.

CFX

Ye Fan, Joshua Litven, Dinesh K. Pai

Eulerian-on-Lagrangian framework simulating volumetric muscles in close contact with volume preservation, large deformation, and active contraction.

Muscles / CFX

Danny M. Kaufman, Rasmus Tamstorf, Breannan Smith, Jean-Marie Aubry, Eitan Grinspun

Stable simulation of large rod assemblies by adapting nonlinearity in collision response, addressing the severe time-step restrictions caused by transversal impacts.

CFX

Shawn Robertson

Irrational Games details the cross-disciplinary animation, systemic, and narrative techniques that gave BioShock Infinite's Elizabeth the illusion of humanity through art, design, and systems collaboration.

Facial / Retargeting

Joe Mancewicz, Matt L. Derksen, Hans Rijpkema, Cyrus A. Wilson

Rhythm and Hues' detail-preserving smoothing deformer that cleans rough skinning automatically, now a standard node in every DCC.

Skinning

Chen Cao, Qiming Hou, Kun Zhou

Regresses displaced expression shapes from RGB video enabling real-time facial tracking and animation with detailed wrinkle representation.

Facial

Tom Sanocki, Jason Garris Jones

Bungie shared how 42 player-selectable heads across different alien races and genders shared a single facial animation set via parameterized topology and rig design.

Facial / Retargeting

Chen Cao, Yanlin Weng, Shun Zhou, Yiying Tong, Kun Zhou

Large-scale 3D facial expression database with bilinear model fitting enabling data-driven face tracking, synthesis, and editing.

Facial

Amit H. Bermano, Derek Bradley, Thabo Beeler, Fabio Zund, Derek Nowrouzezahrai, Ilya Baran, Olga Sorkine-Hornung, Hanspeter Pfister, Markus Gross

Enhances dynamic facial performance captures by propagating high-frequency detail from a reference scan through the sequence.

Facial

Timothy Costigan, Mukta Prasad, Rachel McDonnell

Learns face-motion retargeting from actor to virtual model using MLP and RBF neural networks trained on small datasets.

Facial / Retargeting

Kevin Wampler, Zoran Popovic, Jovan Popovic

Inverse optimal control framework for generalizing locomotion style to novel animal morphologies by regressing locomotion objectives.

Motion Synthesis / Retargeting

David Hotniansky

Postmortem of Harmonix's object-oriented Maya Python rigging framework, covering the framework's evolution from early failures to a production-proven system for character rig and tool development.

Rigging

John Hable

Custom pipeline processes photogrammetry facial scans and mocap data into real-time blendshapes, delivering high-quality facial animation at moderate cost drawing on EA and Naughty Dog experience.

Facial / Retargeting

J P Lewis, Ken Anjyo, Taehyun Rhee, Mengjie Zhang, Frederic Pighin, Zhigang Deng

State-of-the-art report on blendshape facial models covering theory, practice, workflow, and mathematical foundations used in VFX and games.

Facial

Sofien Bouaziz, Sebastian Martin, Tiantian Liu, Ladislav Kavan, Mark Pauly

Fast implicit simulation framework using local-global constraint projection, unifying cloth, soft bodies, and position-based dynamics.

CFX

Binh Huy Le, Zhigang Deng

Robust skeleton extraction and skinning weight computation from mesh animation sequences using SSDR with improved stability.

Rigging / Skinning

Keith Wilson, Aleka McAdams, Hubert Leo, Maryann Simmons

Describes wind field rigs and simulation integration developed for Frozen, capturing cloth and hair interaction with arctic environmental wind conditions.

CFX

Alec Jacobson, Zhigang Deng, Ladislav Kavan, J P Lewis

Comprehensive SIGGRAPH course covering LBS, DQS, pose-space deformation, and example-based skinning methods for real-time character deformation.

Skinning

Ming Gao, Nathan Mitchell, Eftychios Sifakis

Physics-based surface-only skinning method that captures full volumetric flesh behavior using surface degrees of freedom with collision support.

Skinning / Muscles

Matthias Müller, Nuttapong Chentanez, Tae-Yong Kim, Miles Macklin

PBD extension constraining Green-St Venant strain tensor entries directly, enabling anisotropic cloth behavior without polar decomposition overhead.

CFX

Fabian Hahn, Bernhard Thomaszewski, Stelian Coros, Robert W. Sumner, Forrester Cole, Mark Meyer, Tony DeRose, Markus Gross

Subspace cloth simulation using pose-dependent adaptive bases, enabling fast and plausible garment simulation for animated characters.

CFX

Miles Macklin, Matthias Muller, Nuttapong Chentanez, Tae-Yong Kim

Unified particle system handling cloth, fluids, rigid bodies, and soft bodies in a single GPU-accelerated position-based framework.

CFX

Gabriel Cirio, Jorge Lopez-Moreno, David Miraut, Miguel A. Otaduy

Yarn-level simulation of woven cloth using efficient contact handling between yarns to reproduce fabric appearance and mechanical behavior.

CFX

Chen Cao, Yanlin Weng, Stephen Lin, Kun Zhou

Real-time 3D face shape regression from RGB video, tracking both rigid head pose and non-rigid expression deformation simultaneously.

Facial

Ali-Hamadi Dicko, Tiantian Liu, Benjamin Gilles, Ladislav Kavan, Francois Faure, Olivier Palombi, Marie-Paule Cani

Transfers a full anatomical model (bones, muscles, fat) onto arbitrary character shapes, automating anatomy-based rig setup.

Muscles

Hayley N. Iben, Mark Meyer, Lena Petrovic, Olivier Soares, John Anderson, Andrew P. Witkin

Pixar production hair simulation for curly hair using a novel curl model that preserves artistic intent throughout the simulation.

CFX

Thomas Neumann, Kiran Varanasi, Nils Hasler, Marcus Wacker, Markus Magnor, Christian Theobalt

Multi-camera capture and semi-parametric statistical model of shoulder-arm skin and muscle deformations across subjects and poses.

Muscles / Skinning

Olivier Dionne, Martin de Lasa

Voxelization-based geodesic distance approach automatically computes LBS influence weights tolerating non-manifold and multi-component production meshes.

Skinning / Rigging

Kiran S. Bhat, Rony Goldenthal, Yuting Ye, Ronald Mallet, Michael Koperwas

Contour-based facial animation capture system enabling high-fidelity retargeting of subtle expressions to CG character rigs.

Facial / Retargeting

Rodolphe Vaillant, Loic Barthe, Gael Guennebaud, Marie-Paule Cani, Damien Rohmer, Brian Wyvill, Olivier Gourmel, Mathias Paulin

Implicit surface composition on top of geometric skinning that produces contact and bulge effects at the joints in real time.

Skinning

Doyub Kim, Woojong Koh, Rahul Narain, Kayvon Fatahalian, Adrien Treuille, James O'Brien

Precomputation approach for secondary cloth motion on articulated characters, enabling real-time playback of complex garment dynamics.

CFX

Sofien Bouaziz, Yangang Wang, Mark Pauly

Online 3D morphable model fitting for real-time facial animation from depth sensor input with continuous model adaptation.

Facial

Hao Li, Jihun Yu, Yuting Ye, Chris Bregler

Real-time facial animation system that fits corrective blendshapes on-the-fly from depth input to handle fine wrinkle and contact deformation.

Facial

Jun Saito

Facial blendshape transfer method that enforces smooth contact constraints during deformation to prevent interpenetration artifacts.

Facial / Skinning

Binh H. Le, Zhigang Deng

Compact two-layer representation for dense skinning weights enabling efficient compression while preserving deformation quality.

Skinning

Wan-Chun Ma, Yi-Hua Wang, Graham Fyffe, Jernej Barbic, Bing-Yu Chen, Paul Debevec

Extends blendshape facial models with physics-based collision response so blendshape targets automatically account for contact deformation.

Facial / Skinning

Wan-Chun Ma, Marco Barbati, J P Lewis

Editing tool for blendshape facial rigs enabling composite operations, mixing and retargeting facial expressions for production characters.

Facial

Rahul Narain, Armin Samii, James F. O'Brien

Adaptive cloth remeshing system adding resolution where needed for fine wrinkles while coarsening in flat regions for efficiency.

CFX

Tobias Dahl, Mikael Hogstrom

DICE covers animation philosophy and production challenges for Battlefield 3, addressing single and multiplayer pipeline issues and solutions for their largest and most complex title.

Retargeting

Gaurav Bharaj, Thorsten Thormahlen, Hans-Peter Seidel, Christian Theobalt

Automatically creates skeletons, rigid skin weights, and joint mappings for multi-component 3D characters from shape databases.

Rigging

Ofir Weber, Roi Poranne, Craig Gotsman

Generalizes harmonic coordinates by interpolating boundary derivatives, yielding smoother 2D cage deformations with fewer global distortions.

Skinning

Eder Miguel, Derek Bradley, Bernhard Thomaszewski, Bernd Bickel, Wojciech Matusik, Miguel A. Otaduy, Steve Marschner

Measures complex 3D cloth deformation from physical samples and fits nonlinear simulation model parameters to the observations.

CFX

Christian Schumacher, Bernhard Thomaszewski, Stelian Coros, Sebastian Martin, Robert W. Sumner, Markus H. Gross

Example-based material simulation system enabling artists to specify target deformation examples that guide realistic elastic behavior.

CFX / Skinning

Ladislav Kavan, Olga Sorkine-Hornung

Optimizes LBS and DQS weights to minimize elastic energy, yielding deformations that mimic nonlinear simulation quality.

Skinning

Alec Jacobson, Ilya Baran, Ladislav Kavan, Jovan Popovic, Olga Sorkine

Fast linear optimization over bounded biharmonic weight space for automatic linear blend skinning from sparse user-provided handles.

Skinning

Martin Watt, Lawrence D. Cutler, Alex Powell, Brendan Duncan, Michael Hutchinson, Kevin Ochs

Multithreaded dependency graph architecture for character rig evaluation, enabling scalable parallel computation of complex DreamWorks rigs.

Rigging

Thabo Beeler, Bernd Bickel, Paul Beardsley, Bob Sumner, Markus Gross

Multi-camera performance capture system producing high-quality facial geometry and appearance for direct use in film production.

Facial

Johan Ramstrom

EA DICE built a modular deformation rig combined with the ANT animation system and motion capture to raise character quality across Battlefield 3's large asset volume.

Rigging / Skinning

Bernd Bickel, Peter Kaufmann, Markus Gross, Wojciech Matusik, Paul Beardsley, Thabo Beeler

Fabrication-oriented method for cloning the physical mechanics of a human face into a robotic or animatronic face system.

Facial / Muscles

Bernd Bickel, Peter Kaufmann, Markus Gross, Wojciech Matusik, Paul Beardsley, Thabo Beeler

Physics-based facial rig coupling blendshape controls with a finite-element tissue model for artist-directed, anatomically plausible animation.

Facial / Muscles

Fabian Hahn, Sebastian Martin, Bernhard Thomaszewski, Robert W. Sumner, Stelian Coros, Markus Gross

Runs physical simulation directly in the space of an artist rig's parameters, so secondary motion lands on animator-friendly controls.

Rigging / CFX

Binh Huy Le, Zhigang Deng

SSDR: automatically extracting bone transforms and weights from example animations, widely used for rig conversion and crowd pipelines.

Skinning / ML Deformation

Yeongho Seol, J P Lewis, Jaewoo Seo, Byungkuk Choi, Ken Anjyo, Junyong Noh

Spacetime optimization framework for cloning facial expressions across blendshape rigs while preserving timing and dynamic feel.

Facial / Retargeting

Manmyung Kim, Youngseok Hwang, Kyunglyul Hyun, Jehee Lee

Motion synthesis approach using tiled motion patches for seamlessly transitioning and looping character locomotion in interactive applications.

Motion Synthesis

Gilles Daviet, Florence Bertails-Descoubes, Laurence Boissieux

Hybrid iterative solver robustly handling Coulomb friction in hair dynamics using a Signorini-Coulomb contact model.

CFX

Adam Mechtley

Describes a scripted pipeline that automatically generates character runtime rigs, reducing manual technical director work and improving rig consistency across all character assets in production.

Rigging

Yeongho Seol, Jaewoo Seo, Paul Hyunjin Kim, J P Lewis, Junyong Noh

Retargeting method for facial animation that maps captured motion to diverse character rigs while preserving artistic intent.

Facial / Retargeting

Alec Jacobson, Ilya Baran, Jovan Popovic, Olga Sorkine

Bounded biharmonic weight computation for cage and skeleton deformation providing smooth, localized, non-negative influence functions.

Rigging / Skinning

Jaewoo Seo, Geoffrey Irving, J P Lewis, Junyong Noh

Compression scheme for large blendshape models that preserves direct manipulation capabilities, reducing memory without sacrificing editability.

Facial

Maryann Simmons, Kelly Ward, Hidetaka Yosumi, Hubert Leo, Xinmin Zhao

Hybrid simulation and keyframe approach for art-directing Tangled's hair to match story-driven 2D draw-over targets during complex character interactions.

CFX

Aleka McAdams, Yongning Zhu, Andrew Selle, Mark Empey, Rasmus Tamstorf, Joseph Teran, Eftychios Sifakis

Near-interactive corotational elasticity on hexahedral lattices for character soft-tissue deformation, handling contact and collisions in production at Disney.

Skinning / CFX / Muscles

Jeremy Ernst

Epic Games technical animator presented a universal facial rig pipeline for Gears of War 3 emphasizing speed and efficiency in character facial setup.

Facial / Rigging

Thabo Beeler, Fabian Hahn, Derek Bradley, Bernd Bickel, Paul Beardsley, Craig Gotsman, Robert Sumner, Markus Gross

Passive multi-view facial performance capture using anchor frames for temporal coherence, achieving high-quality reconstruction without active illumination.

Facial

Theodore Kim, Doug L. James

Multi-domain subspace deformation method for real-time physics-based character skinning using model reduction per body segment.

Skinning / Muscles

Thibaut Weise, Sofien Bouaziz, Hao Li, Mark Pauly

Real-time performance-based facial animation driven by depth camera input, enabling live facial retargeting at interactive rates.

Facial

Thabo Beeler, Fabian Hahn, Derek Bradley, Bernd Bickel, Paul Beardsley, Craig Gotsman, Robert Sumner, Markus Gross

Rigid motion stabilization for facial performance capture, separating head pose from expression motion for improved downstream processing.

Facial

Taehyun Rhee, J P Lewis, Ulrich Neumann, Krishna Nayak

Volume animation technique using MRI scan data with locally adaptive articulated registration, enabling realistic volumetric character deformation.

Skinning / Retargeting

Alec Jacobson, Olga Sorkine

Extends LBS bones to support stretch and twist DOF, eliminating candy-wrapper artifacts without extra helper joints.

Skinning / Rigging

Travis McIntosh

Examines partial and additive animation layering, remapping, and flipping techniques that gave Naughty Dog Uncharted characters responsive, feel-good player-controlled movement on PS3.

Retargeting

Bruno Velazquez

Covers God of War III character animation from concept through in-game implementation, including contact-sensitive moves and maintaining Kratos visual consistency across gameplay demands.

Retargeting

Ben Cloward

BioWare described an automated system that selects and blends animator-authored facial performance libraries to handle high-volume dialog in Star Wars: The Old Republic.

Facial / Retargeting

J P Lewis, Ken Anjyo

Direct manipulation interface for blendshape rigs allowing artists to sculpt corrections on the face mesh with automatic weight solving.

Facial

Jonathan M. Kaldor, Doug L. James, Steve Marschner

Adaptive contact linearization for yarn-yarn penalty forces in knitted cloth, exploiting temporal coherence to reduce contact solve cost substantially.

CFX

Hao Li, Thibaut Weise, Mark Pauly

Optimization method for constructing blendshape facial rigs directly from example expression scans using sparse deformation decomposition.

Facial / Rigging

Huamin Wang, Florian Hecht, Ravi Ramamoorthi, James O'Brien

Data-driven wrinkle synthesis adding fine detail to coarse cloth animation using a database of example wrinkle patterns.

CFX

Ladislav Kavan, Peter-Pike Sloan, Carol O'Sullivan

Iterative coordinate-descent algorithm that decomposes arbitrary mesh animations into standard linear blend skinning without manual rigging.

Skinning

Derek Bradley, Wolfgang Heidrich, Tiberiu Popa, Alla Sheffer

Multi-view passive capture system for facial performance without markers, recovering high-resolution dynamic geometry from synchronized cameras.

Facial

Thabo Beeler, Bernd Bickel, Paul Beardsley, Bob Sumner, Markus Gross

Pore-level facial geometry from a single passive stereo shot, the start of the Medusa capture line at Disney Research.

Facial

Huamin Wang, James F. O'Brien, Ravi Ramamoorthi

Coordinate-invariant strain limiting via SVD of the deformation gradient at multiple resolutions, enforcing isotropic inextensibility for cloth and shells.

CFX

John Fuller, Andreas Nilsson

Explains how physics and IK were fused in Just Cause 2 for skydiving, grappling, and vehicle clinging, reducing animation asset creation while enabling novel emergent gameplay interactions.

Rigging

Kelly Ward, Maryann Simmons, Andy Milne, Hidetaka Yosumi, Xinmin Zhao

Production techniques for simulating 70 feet of Rapunzel's hair in Tangled using a mass-spring dynamicWires system with art-direction controls.

CFX

J P Lewis, Nebojsa Dragosavac

Differential IK formulation providing stable, efficient inverse kinematics for complex character rigs with redundant degrees of freedom.

Rigging

Edilson de Aguiar, Leonid Sigal, Adrien Treuille, Jessica K. Hodgins

Data-driven conditional cloth model learned from simulation that enables real-time animation of thousands of garments with approximate collision resolution.

CFX / ML Deformation

Tim Borrelli, Ben Cloward, Seth Gibson

Panel from 5th Cell, BioWare, and 343 Industries covering mocap integration, blendshapes, shader-based deformation, procedural helpers, and muscle systems in character pipelines.

Rigging / Skinning / Muscles

Oleg Alexander, Mike Rogers, William Lambeth, Jen-Yuan Chiang, Wan-Chun Ma, Chuan-Chang Wang, Paul Debevec

USC ICT and Image Metrics cross the uncanny valley with a fully digital photoreal face built from Light Stage scans.

Facial

Hiroki Ueno

Presents full-body IK targeting, physics and animation blending techniques, and character navigation solutions used in UFC 2009 Undisputed for responsive fighter animation.

Rigging

Richard Diamant, Judd Simantov

Naughty Dog details proprietary modeling tools, Maya referencing for skeletal assets, a shared male/female facial rig skeleton, sculpting workflows, and UV seam solutions for Uncharted 2.

Rigging / Facial

Matthias Muller, Nuttapong Chentanez

Attaches a fine-resolution wrinkle mesh to a coarse animated base mesh, solving wrinkle geometry with a static solver at interactive rates.

CFX / Skinning

Nils Hasler, Carsten Stoll, Martin Sunkel, Bodo Rosenhahn, Hans-Peter Seidel

Unified statistical model of human pose and body shape learned from 550 laser scans, capturing pose-dependent muscle deformations.

Skinning / ML Deformation

Edmond S.L. Ho, Taku Komura

Synthesizes complex contact-rich motions such as dressing by embedding topological relationships of body segments into motion coordinates.

Motion Synthesis

Bernhard Thomaszewski, Simon Pabst, Wolfgang Blochinger

Continuum-based strain limiting for cloth simulation that prevents over-stretching while maintaining simulation stability and physical plausibility.

CFX

Aleka McAdams, Andrew Selle, Kelly Ward, Eftychios Sifakis, Joseph Teran

Continuum-based hair simulation using SPH-like discretization preserving fine strand detail while handling large numbers of interacting hairs.

CFX

Rune Skovbo Johansen

Demonstrates semi-procedural techniques for real-time bipedal locomotion, blending keyframe animation with procedural IK to adapt foot placement dynamically on uneven terrain.

Rigging

Cem Yuksel, Scott Schaefer, John Keyser

Mesh-based representation for volumetric hair enabling efficient simulation and rendering of dense hair interacting with the body.

CFX

Andrew Selle, Michael Lentine, Ronald Fedkiw

A practical mass-spring formulation able to simulate full heads of individual hairs with stable contact and collision.

CFX

Daniel Vlasic, Ilya Baran, Wojciech Matusik, Jovan Popovic

Reconstructs articulated character mesh animation from multi-view silhouette sequences enabling markerless performance capture.

Retargeting

Sang Il Park, Jessica K. Hodgins

Data-driven model of coupled skin and muscle deformation learned from 4D scan sequences of real human motion.

Skinning / Muscles

Miklos Bergou, Max Wardetzky, Stephen Robinson, Basile Audoly, Eitan Grinspun

Discrete differential geometry formulation for elastic rod simulation capturing bending and twisting for hair, cables, and filamentary structures.

CFX

Wan-Chun Ma, Andrew Jones, Jen-Yuan Chiang, Tim Hawkins, Sune Frederiksen, Pieter Peers, Marko Vukovic, Ming Ouhyoung, Paul Debevec

Learns polynomial maps from mocap markers to high-res face geometry for wrinkle and pore detail synthesis.

Facial

Ladislav Kavan, Steven Collins, Jiri Zara, Carol O'Sullivan

Dual quaternion blending for skeletal skinning that eliminates the candy-wrapper artifact of LBS at negligible extra computational cost.

Skinning

Yaron Lipman, David Levin, Daniel Cohen-Or

Derives shape-preserving cage coordinates from Green's integral identity, inducing quasi-conformal mappings for realistic mesh deformation.

Skinning

Shinjiro Sueda, Andrew Kaufman, Dinesh K. Pai

Musculotendon simulation for anatomically detailed hand animation, modeling tendon routing and muscle fiber contraction for realistic grasping.

Muscles

Chris Hecker, Bernd Raabe, Ryan W. Enslow, John DeWeese, Jordan Maynard, Kees van Prooijen

Real-time motion retargeting for highly varied character body shapes, enabling game characters with diverse proportions to share animation.

Retargeting

Tao Ju, Qian-Yi Zhou, Michiel van de Panne, Danny Cohen-Or, Ulrich Neumann

Introduces reusable per-joint cage deformation templates that transfer skinning across characters with similar skeletons.

Skinning / Rigging

David Harmon, Etienne Vouga, Rasmus Tamstorf, Eitan Grinspun

Fail-safe collision response that cancels impact but preserves sliding, incorporating Coulomb friction approximation for cloth self-collision at scale.

CFX

Jonathan Kaldor, Doug L. James, Steve Marschner

Yarn-level cloth simulation capturing the mechanical behavior of knitted fabrics through individual yarn dynamics and contact.

CFX

Ilya Baran, Jovan Popovic

Automatic skeleton embedding and skinning weight computation for arbitrary 3D meshes, enabling one-click rigging of novel characters.

Rigging / Skinning

Rony Goldenthal, David Harmon, Raanan Fattal, Michel Bercovier, Eitan Grinspun

Efficient inextensibility constraint formulation for cloth using a fast filter-based approach preventing stretching without sacrificing speed.

CFX

Pushkar Joshi, Mark Meyer, Tony DeRose, Brian Green, Tom Sanocki

Harmonic coordinate space for cage-based character deformation providing non-negative, smooth weights that satisfy the maximum principle.

Rigging / Skinning

Adrien Treuille, Yongjoon Lee, Zoran Popovic

Low-dimensional basis representation over motion capture enables automatic computation of near-optimal real-time character controllers.

Motion Synthesis

Judd Simantov

Naughty Dog's Infinite Pose Combination system enabled facial rigs capable of arbitrary pose combinations, advancing character expressiveness beyond fixed blendshape limits.

Facial / Rigging

Matthias Muller, Bruno Heidelberger, Marcus Hennix, John Ratcliff

Position-based simulation framework for real-time cloth, hair, and deformable bodies widely adopted in games and interactive applications.

CFX

Kangkang Yin, Kevin Loken, Michiel van de Panne

Simple feedback-based bipedal locomotion controller achieving robust walking and running on varied terrain with minimal parameter tuning.

Motion Synthesis

Ladislav Kavan, Steven Collins, Jiri Zara, Carol O'Sullivan

Dual quaternion blending fixes the collapsing-joint and candy-wrapper artifacts of linear blend skinning at almost the same cost.

Skinning

Sang Il Park, Jessica K. Hodgins

Data-driven model of skin and muscle deformation extracted from human motion, enabling realistic soft-tissue dynamics on animated characters.

Skinning / Muscles

Kevin G. Der, Robert W. Sumner, Jovan Popovic

Automated pipeline converts unarticulated example shapes into a controllable articulated reduced-deformable model with intuitive IK-style control.

Rigging / Skinning

Taehyun Rhee, J.P. Lewis, Ulrich Neumann

GPU-parallel example-based pose-space deformation that automatically computes per-vertex blend weights from sample poses.

Skinning

Florence Bertails, Basile Audoly, Marie-Paule Cani, Bernard Querleux, Frederic Leroy, Jean-Luc Leveque

Super-helix model for hair strand dynamics using Kirchhoff elastic rods, capturing natural curl and wave patterns with high physical fidelity.

CFX

Eftychios Sifakis, Igor Neverov, Ronald Fedkiw

FEM-based facial muscle simulation with automatic activation estimation from sparse mocap markers, enabling physics-driven facial animation.

Facial / Muscles

Joseph Teran, Eftychios Sifakis, Silvia S. Blemker, Victor Ng-Thow-Hing, Cynthia Lau, Ronald Fedkiw

Finite element musculoskeletal simulation built from anatomical data, groundwork for the production flesh systems that followed.

Muscles

Daniel Vlasic, Matthew Brand, Hanspeter Pfister, Jovan Popovic

Multilinear model factoring facial identity and expression for transferring performances between individuals and editing facial animation.

Facial / Retargeting

Tomohiko Mukai, Shigeru Kuriyama

Geostatistical approach to motion interpolation using kriging for smooth synthesis of human movement from sparse example motion clips.

Motion Synthesis

Tao Ju, Scott Schaefer, Joe Warren

Extends mean value coordinates to closed triangular meshes in 3D, enabling smooth and natural cage-based space deformations.

Skinning

Robert W. Sumner, Matthias Zwicker, Craig Gotsman, Jovan Popovic

Deformation-gradient feature vectors and nonlinear example span enable direct mesh posing through vertex constraints without an explicit skeleton.

Rigging / Skinning

Joseph Teran, Eftychios Sifakis, Geoffrey Irving, Ronald Fedkiw

Foundational FEM flesh simulation using quasistatic Newton-Raphson iteration robust to element inversion, enabling character soft-tissue deformation.

Muscles

Drago Anguelov, Praveen Srinivasan, Daphne Koller, Sebastian Thrun, Jim Rodgers, James Davis

Statistical body shape model factoring body shape from pose deformation, foundational for parameterized human body models used in vision and animation.

Skinning / Retargeting

Doug L. James, Christopher D. Twigg

Method to extract linear blend skinning weights and skeleton from animated mesh sequences, enabling compact representation of captured deformations.

Skinning

Lucas Kovar, Michael Gleicher

Discovers logically similar motion variants in large capture databases and builds continuous parameterized motion families automatically.

Motion Synthesis / Retargeting

Robert W. Sumner, Jovan Popovic

Transfers the deformation of a source mesh onto a different target mesh, the standard tool behind blendshape and rig transfer.

Retargeting / Skinning

Keith Grochow, Steven L. Martin, Aaron Hertzmann, Zoran Popovic

Gaussian process model for style-aware inverse kinematics generating human-like poses respecting learned stylistic priors.

Rigging / Retargeting

Eitan Grinspun, Anil N. Hirani, Mathieu Desbrun, Peter Schroeder

Discrete differential geometry formulation for thin elastic shells using hinge-angle bending energy, foundational for cloth and thin surface simulation.

CFX

Okan Arikan, David A. Forsyth, James F. O'Brien

User paints a timeline with semantic annotations and the system assembles motion-capture frames via dynamic programming to satisfy them.

Motion Synthesis

Robert Bridson, Sebastian Marino, Ronald Fedkiw

Mixed implicit/explicit integrator with physically correct bending and interface forecasting to preserve folds in cloth-character collisions.

CFX

David Baraff, Andrew Witkin, Michael Kass

Resolves deeply interpenetrating cloth using a global geometry-based untangling approach, essential for garment initialization and collision recovery.

CFX

Lucas Kovar, Michael Gleicher, Frederic Pighin

Builds a graph of transitions inside a mocap corpus so arbitrary streams of motion can be synthesized from clips.

Motion Synthesis

Robert Bridson, Ronald Fedkiw, John Anderson

Robust collision handling for cloth simulation using impulse-based contact resolution and continuous collision detection for stable production use.

CFX

Robert Bridson, Ronald Fedkiw, John Anderson

Foundational algorithm for cloth collision, contact, and Coulomb friction, introduced velocity-filter-style resolution for simultaneous impacts.

CFX

Paul Debevec, Tim Hawkins, Chris Tchou, Haarm-Pieter Duiker, Westley Sarokin, Mark Sagar

Light stage system capturing the full reflectance field of a human face enabling relighting with arbitrary illumination for photoreal CG faces.

Facial

J. P. Lewis, Matt Cordner, Nickson Fong

Corrective shapes interpolated in pose space on top of skeletal skinning, the backbone idea behind modern corrective workflows.

Skinning

Volker Blanz, Thomas Vetter

The 3D morphable face model: a statistical face space fit to images, ancestor of every data-driven face model since.

Facial

David Baraff, Andrew Witkin

Implicit integration makes cloth simulation stable at large time steps, the foundation of production cloth (and of Maya nCloth's lineage).

CFX

Michael Gleicher

Spacetime constraint-based motion retargeting adapting motion capture data to new character proportions while preserving dynamic qualities.

Retargeting

Tony DeRose, Michael Kass, Tien Truong

Introduced subdivision surfaces into Pixar's production pipeline for Geri's Game, enabling smooth deformable character meshes from arbitrary topology.

Rigging / Skinning

Charles Rose, Michael Cohen, Bobby Bodenheimer

Radial basis function interpolation framework for blending motion clips along semantic dimensions like speed and emotion for interactive characters.

Motion Synthesis

Ken Perlin, Athomas Goldberg

Scripting system for interactive character behaviors combining procedural motion layering with behavioral state machines for real-time actors.

Motion Synthesis

Jessica K. Hodgins, Wayne L. Wooten, David C. Brogan, James F. O'Brien

Physics-based simulation of human athletic activities including running, jumping, and gymnastics with reactive balance control.

Motion Synthesis

Zoran Popovic, Andrew Witkin

Motion editing technique warping captured animations to meet user-defined spacetime constraints while preserving dynamic continuity.

Retargeting

Karl Sims

Genetic algorithm evolution of virtual creature morphologies and neural locomotion controllers, pioneering learned physics-based animation.

Motion Synthesis

Lance Williams

Drives a digital face directly from tracked human performance, the founding paper of performance capture.

Facial / Retargeting

John E. Chadwick, David R. Haumann, Richard E. Parent

Layered character model with skeleton, muscle, and skin layers using proximity-based deformation for realistic anatomical character animation.

Skinning / Muscles

Nadia Magnenat-Thalmann, Renato Laperriere, Daniel Thalmann

Introduced joint-dependent local deformations (JLD) for hand animation, an early precursor to pose-space deformation and corrective skinning.

Skinning / Rigging

Andrew Witkin, Michael Kass

Spacetime optimization formulation for physics-based character animation, optimizing motions over time to satisfy user-specified constraints.

Motion Synthesis

Keith Waters

Parameterized face muscle model using linear and sphincter muscle types to animate facial expressions, influencing decades of facial animation research.

Facial / Muscles

Demetri Terzopoulos, John Platt, Alan Barr, Kurt Fleischer

The paper that brought physically based elastic simulation to graphics, ancestor of all cloth and flesh solvers.

CFX / Muscles

Thomas W. Sederberg, Scott R. Parry

Introduces FFD lattices: deforming models by warping the space around them, a foundation for countless rig deformers.

Skinning

Stephen M. Platt, Norman I. Badler

Early muscle-based facial animation system using pseudo-muscles anchored to a facial mesh to drive expression deformations.

Facial / Muscles

Paul Ekman, Wallace V. Friesen

The psychology taxonomy of facial action units that became the de facto vocabulary of every film and game facial rig.

Facial