Papers.

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

Disney Research Blender plugin built on a general motion model lets artists generate and edit full motion sequences by manipulating sparse handles, poses, window lengths and noise sampling.

Rigging / Motion Synthesis

Rob Garcia

Light Labs technical artist Rob Garcia details a modular, procedural Rig Factory built in Houdini for high volume character production.

Rigging

Alexandre Mercier-Aubin, Teseo Schneider, Paul G. Kry, Sheldon Andrews

Automatically partitions an elastic solid into affine and elastic regions during simulation, cutting compute up to 17 times while keeping localized deformation detail.

CFX / ML Deformation

Jeanne-Emma Lefevre, Theo Cheynel, Omar El Khalifi, Thomas Daniel, Baptiste Bellot-Gurlet

Style adaptive auto rigging learns an artist's rigging conventions from a single example, formalizes the control rig as a pose representation, and recovers controllers via rig inversion.

Rigging / Retargeting

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

Jacob Brooks, David Eberle, Alan Browning

For Toy Story 5's Blaze, Pixar built a grooming structure for interactive curl design and deployed Fizt Strands, built atop their Fizt cloth solver, improving collision and stability.

CFX

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

Daeyong Kim, Gyuseok Yi, Ri Yu

Detects heel and toe contact directly from video and feeds it into a reinforcement learning framework with a two segment foot model for realistic gait reconstruction.

Motion Synthesis / Retargeting

Tomer Koren, Adi Rosenthal, Doron Friedman, Ariel Shamir

A cross attention model fuses interlocutor audio, text, and gesture cues so one character can generate both speaking and listening gestures in dialogue.

Motion Synthesis

Kiki Poh, Kris Campbell, Alan Browning, Michael Jefferies

Pixar adapted Houdini's hair grooming system for the many bird species in Hoppers, adding controllable secondary motion that complements wing animation and shading for patterned feathers.

CFX

Haim Sawdayee, Chuan Guo, Bing Zhou, Jian Wang, Guy Tevet, Amit H. Bermano

LoRA-MDM adapts a motion diffusion prior with only a few style samples, shifting the motion manifold so unseen actions inherit the style while staying editable.

Motion Synthesis

Yutong Liang, Shiyi Xu, Yulong Zhang, Bowen Zhan, He Zhang, Libin Liu

Low cost capture rig using dense character coded marker patches to track fingers through severe self occlusion, released with the DexterHand manipulation dataset.

Retargeting / Motion Synthesis

Rupesh Kumar, Sabhya Khurana, Rahul Narain

Introduces a two way coupled dynamics model that superposes a base cloth surface and a spatially varying wrinkle amplitude and frequency field for interactive coarse mesh cloth.

CFX

Jeremie Talbot, William Sheffler, Fernando de Goes

Pixar talk using curvenets as a sparse geometric proxy to author parametrization contours whose weights are interpolated across the face mesh to drive articulation, shown on Hoppers.

Facial / Rigging

Xinya Ji, Sebastian Weiss, Manuel Kansy, Jacek Naruniec, Xun Cao, Barbara Solenthaler, Derek Bradley

Feed forward method generates high quality 3D Gaussian head avatars from only a few input images while supporting real time facial animation.

Facial / 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

Jiaxin Wang, Dongxin Lyu, Zeyu Cai, Zhiyang Dou, Cheng Lin, Anpei Chen, Yuliang Xiu

Compresses temporally consistent Gaussians into free form skelebones via mean curvature skeleton extraction and partwise motion matching, beating linear blend skinning reanimation quality.

Rigging / ML Deformation

Alvaro G. Inesta, Mattia Ryffel, Amit H. Bermano, Robert W. Sumner, Martin Guay

Best Paper Award winner, a generative diffusion framework with a dual objective loss that decouples skeletal integrity from drumstick precision to generalize to in the wild audio.

Motion Synthesis

Max Rose

SideFX's Max Rose builds a fully dynamic Jack in the Box character rig in Houdini 22, driving spring animation from two keyframes with Apex.

Rigging / Motion Synthesis

Henry Dean

SideFX's Henry Dean rigs a character starting from no geometry or topology, demonstrating procedural KineFX rigging and animation in Houdini 22.

Rigging

Yuefan Shen, Yican Dong, Xiufeng Huang, Zhongtian Zheng, Youyi Zheng, Kui Wu

Anchors strand generation on Large Reconstruction Model mesh priors and a Dual Orientation AutoEncoder to resolve global occlusion and local curl directionality when reconstructing strand-level hair.

CFX

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

Astitva Srivastava, Hsiao-Yu Chen, Ryan Goldade, Philipp Herholz, Zhongshi Jiang, Gene Wei-Chin Lin, Lingchen Yang, Nikolaos Sarafianos, Tuur Stuyck, Doug Roble, Avinash Sharma, Egor Larionov

A reduced space neural dynamics simulator with coarse and fine hypernetwork conditioned components predicts fast, physically plausible bone driven garment motion.

CFX

Dalton Omens, Allise Thurman, Jihun Yu, Ronald Fedkiw

Uses volumetric morphing and Simon Says calibration expressions so tracker and target share one rig framework, fine tuning the rig for semantically meaningful retargeted controls.

Facial / Retargeting

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

Scheduled inpainting is an inference only technique that extends pretrained generative motion models to interactively edit, extend, stitch and composite animation clips without extra training.

Motion Synthesis

Armin Bruderlin, Joshua Beveridge, Irene Hernandez

Sony Pictures Imageworks talk on the Chibi facial system for KPop Demon Hunters, a swappable toolkit of exaggerated facial features that frees expressions from the base model geometry.

Facial / Rigging

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

Taeyeon Kim, Youngju Na, Jumin Lee, Sebin Lee, Minhyuk Sung, Sung-Eui Yoon

Given a monocular video and a rigged target character, directly optimizes target morphology and pose to reproduce observed motion without source 3D reconstruction.

Retargeting / Motion Synthesis

Tingwu Wang, Olivier Dionne, Michael De Ruyter, David Minor, Davis Rempe, Kaifeng Zhao, Mathis Petrovich, Ye Yuan, Chenran Li, Zhengyi Luo, Brian Robison, Xavier Blackwell, Bernardo Antoniazzi, Xue Bin Peng, Yuke Zhu, Simon Yuen

MotionBricks is a real-time generative motion framework: a modular latent backbone models over 350,000 clips in one network and a smart-primitive interface authors navigation and object interaction plug-and-play, reaching 15,000 FPS at 2ms latency and deployed zero-shot to a Unitree G1 humanoid.

Motion Synthesis / Retargeting

Gene Wei-Chin Lin, Egor Larionov, Hsiao-Yu Chen, Doug Roble, Tuur Stuyck

A compact, fully self supervised neural network generates strand level dynamic hair deformations from boundary condition history, running fast enough for lower end devices.

CFX

Chao Wang, Guangyao Ma, John Doublestein, Junming Chen, Yiming Lin, Zhaoen Su, Xiaomin Luo, Shiyang Cheng, Jie Shen, Doug Roble

Converts a static surface only character mesh into a FACS rig with up to 155 blendshapes and procedurally fitted teeth, gums, and tongue with no manual setup.

Facial / Rigging

Xiaotang Zhang, Ziyi Chang, Qianhui Men, Hubert P. H. Shum

Uses progressive neural networks with automatically assigned experts to track stable two character interactions like boxing and grappling under frequent physical contact.

Motion Synthesis

Juan Sebastian Montes Maestre, Ladislav Kavan, Edmond Boyer, Ryan Goldade, Stelian Coros, Bernhard Thomaszewski

Finite element framework using prismatic solid shell elements and continuum skin ligaments models viscoelastic facial skin to produce contact induced wrinkles matching real footage.

Facial / CFX

Yuanhang Lei, Tao Cheng, Xingxuan Li, Boming Zhao, Siyuan Huang, Ruizhen Hu, Peter Yichen Chen, Hujun Bao, Zhaopeng Cui

Learns continuous, mesh free skinning weight fields from static geometry alone via physics informed self supervision, enabling real time physics based animation.

Skinning / ML Deformation

Christoph Genzwuerker, Alex Rothwell, Philippe Mongeau, Quentin Sanchez

Framestore production talk on an end-to-end anatomy simulation platform that automates constraint construction through geometric labeling, converging rigging and creature FX into anatomically accurate muscle and tissue deformation.

Muscles / Rigging

Nikitas Chatzis, Marios Loizou, Evangelos Kalogerakis

Jointly models geometry and rig through coupled surface and skeleton latents, decoding mesh, joint hierarchy, and skinning weights together for image conditioned generation.

Rigging

Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou

Learns rig and motion jointly from raw mesh sequences with no rig annotations, encoding per vertex deformation into separate Gaussian bone and motion latent spaces.

Rigging / Motion Synthesis

Shichong Peng, Yanshu Zhang, Ke Li

Auto rigs a static point rendered reconstruction and drives it under linear blend skinning from one fixed viewpoint video, recovering a reposable 3D asset.

Rigging / Skinning

Gerrit Nolte, Fabian Kemper, Ulrich Schwanecke, Mario Botsch

Trains a network to predict per element deformation gradients for skeleton driven anatomical human animation, staying robust to element inversion and volume drift.

Muscles / ML Deformation

Tomohiko Mukai, Takafumi Taketomi

Formulates skin penetration removal as multi target inverse kinematics on skeleton subspace deformation, clustering penetrated vertices by deformation gradient similarity for stable interactive correction.

Skinning

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

Reframes skinning weight regression as discrete token sequence prediction, enabling TokenRig to autoregressively generate skeleton and skin weights together in one sequence.

Rigging / Skinning

Egor Larionov, Igor Santesteban, Hsiao-yu Chen, Wei-Chin Gene Lin, Philipp Herholz, Ryan Goldade, Ladislav Kavan, Doug Roble, Tuur Stuyck

Automatically generates production quality skinning weights from a mesh and skeleton in canonical pose, with direct sparsity control over bone influences per vertex.

Skinning

Soojin Choi, Seokhyeon Hong, Chaelin Kim, Junghyun Nam, Junhyuk Jeon, Junyong Noh

KAIST retargeting framework dynamically repositions proximity anchors onto reachable regions of a target character to preserve self-contact and near-body interaction semantics across differing body shapes.

Retargeting / Skinning

Eduardo Alvarado, Emily Kim, Gerrit Nolte, Friedemann Runte, Mario Botsch, Marc Habermann, Christian Theobalt

Infers spatio temporal muscle bulging and skin sliding from multiview RGB surface signals using cascaded U-Nets, the first method to recover muscle deformation from video.

Muscles / ML Deformation

Jun Saito, Jiefeng Li, Michael de Ruyter, Miguel Guerrero, Edy Lim, Ehsan Hassani, Roger Blanco Ribera, Hyejin Moon, Magdalena Dadela, Marco Di Lucca, Qiao Wang, Xueting Li, Jan Kautz, Simon Yuen, Umar Iqbal

SOMA introduces a canonical body topology and universal rig, reducing cross-model adapter complexity from O(M^2) to O(M) via inverse-LBS pose solving and FK optimization.

Retargeting / Skinning / Rigging

Ruipeng Wang, Langkun Zhong, Miaowei Wang

A self supervised framework generates temporally consistent skeletons and skinning weights directly from animated mesh sequences without manual rig supervision.

Rigging

Eneko Atxa Landa, Igor Rodriguez, Elena Lazkano, Taras Kucherenko

Releases about six hours of idle motion capture from fifty non-actor subjects with an evaluation protocol and baseline transition concatenation model for idle animation synthesis.

Motion Synthesis

Jose Luis Ponton, Eduardo Alvarado, Lin Geng Foo, Nuria Pelechano, Carlos Andujar, Marc Habermann

Reconstructs full body locomotion from insoles carrying an IMU and sixteen pressure sensors, free of line of sight limits and unconstrained by a mocap suit.

Motion Synthesis / Retargeting

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

Skydance Animation

Skydance Animation's FX team explains how fire, water and destruction effects were blended into a single character for the film Swapped.

CFX

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

A Graph CVAE compresses heterogeneous kinematic chains into a shared latent motion manifold, letting motion captured from monocular video be retargeted to characters with arbitrary unseen skeletal topologies.

Retargeting / Motion Synthesis

Magnus Moller, Tumblehead

Tumblehead unveils TumbleRig, a 30 plus node Apex based rigging package, demonstrated by building a cartoony frog character in Houdini 22.

Rigging

Fatemeh Zargarbashi, Zehong Qiu, Dhruv Agrawal, Stelian Coros, Robert Sumner, Martin Guay, Jakob Buhmann

Two stage generative diffusion model trained purely on quadruped motion converts ordinary human motion into plausible controllable quadruped puppeteering with limb level control.

Retargeting / Motion Synthesis

Chengfeng Zhao, Junbo Qi, Yulou Liu, Zhiyang Dou, Minchen Li, Taku Komura, Ziwei Liu, Wenping Wang, Yuan Liu

Learns an instance specific neural deformation field mapping 3D points to offsets, animating complex garments on unseen poses in real time without topology handling.

CFX / Skinning

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

Fatma Ben Ayed, Giorgio Becherini, Justus Thies, Vanessa Sklyarova

Reconstructs a strand based three dimensional hairstyle from ordinary video footage, producing simulation ready hair geometry for character work.

CFX

Honglin Chen, Karran Pandey, Rundi Wu, Matheus Gadelha, Yannick Hold-Geoffroy, Ayush Tewari, Niloy J. Mitra, Changxi Zheng, Paul Guerrero

Distills motion priors from a pretrained video diffusion model to discover the plausible pose manifold of an auto rigged mesh, preventing anatomical hyperextension.

Rigging / Motion Synthesis

Fatemeh Zargarbashi, Dhruv Agrawal, Jakob Buhmann, Martin Guay, Stelian Coros, Robert W. Sumner

Residual vector quantized autoencoders learn a coarse to fine motion representation, then quantized code swapping transfers style at inference without fine tuning for unseen styles.

Motion Synthesis

Eric Saindon, Dan Barrett, Nicky Muir, Richard Baneham

Production session on Avatar Fire and Ash detailing the APFS proprietary facial performance system and the Bodyopt full-body deformation tool used across 146 characters and 2,539 shots.

Facial / Skinning

Felix Menguy, Tommy Toussaint

Unit Image's Felix Menguy and Tommy Toussaint present the studio's in house CFX pipeline, covering setup implementation and variation management for character work.

CFX

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

Jinhyung Park, Javier Romero, Shunsuke Saito, Fabian Prada, Takaaki Shiratori, Yichen Xu, Federica Bogo, Shoou-I Yu, Kris Kitani, Rawal Khirodkar

Parametric body model trained on 600k scans that grounds the mesh in an explicit skeletal basis, decoupling bone length and shape from soft-tissue deformation for independent anatomical control.

Muscles / ML Deformation

Framestore

Framestore Houdini Connect breakdown of crafting Appa's realistic fur groom and Momo's creature design for Netflix's live-action Avatar, plus storm and water FX.

CFX

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

Liesbeth Levick

Liesbeth Levick shows the muscle target shape workflow in the Otis solver, allowing multiple target shapes per muscle for sculpted control.

Muscles

Farnoosh Koleini, Muhammad Usama Saleem, Pu Wang, Hongfei Xue, Ahmed Helmy, Abbey Fenwick

Three-stage pipeline combining multi-query mesh recovery, neural inverse kinematics, and 2D-informed refinement to produce biomechanically plausible human poses from monocular video.

Retargeting / Muscles

Yuhan Wu, Nobuyuki Umetani

BlendSim shifts physics-based animation from discrete frame-by-frame solves to continuous interpolation trajectories built on blendshapes, representing each vertex path with continuous parametric Bezi

Facial / CFX

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

James Pedlingham, Fanny Chaleon, Christian Aguilera, Gary Jones, Arielle Martin, Thibaut Van Waeyenbergh

Foundry introduces the UsdSuperLayer node in Katana, providing a procedural on-demand approach that prevents full stage recomposition when editing large character and shading graphs.

Rigging

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

Josee Chapdelaine, Marc-Antoine Paquin

Rodeo FX's Josee Chapdelaine and Marc Antoine Paquin detail the procedural grooming, fur and feather pipeline built for the creatures of Netflix's The Sandman season 2.

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

Romain Brégier, Guénolé Fiche, Laura Bravo-Sánchez, Thomas Lucas, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez, Fabien Baradel

Anny is a scan-free open-source parametric body model using anthropometric phenotype parameters: gender, age, height, weight, calibrated from WHO population statistics.

Rigging / Skinning / Retargeting

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

Jose Antonio Fernandez-Fernandez, Ryan Goldade, Ladislav Kavan, Jan Bender, Philipp Herholz

Layers real-time thin-shell simulation and contact onto an existing facial rig, with no anatomical priors or extra artist work, adding plausible skin dynamics and self-contact that run interactively on consumer hardware.

Facial / CFX

Gabriela Salmeron

Framestore Head of Groom and Creature FX presents a full creature FX pipeline from muscle simulation through tissue and skin to fur coat dynamics in KineFX.

CFX

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

Aaron Ferguson, Ahmed A. A. Osman, Berta Bescos, and 44 additional authors

Meta's MHR combines a decoupled skeleton/shape paradigm with a modern rig and pose-corrective system, culminating 9 years of anatomically inspired body model work.

Rigging / Skinning / Retargeting

Josh Karlin

SideFX's Josh Karlin gives a beginner overview of machine learning in Houdini, breaking down a muscle deformer example for character effects.

ML Deformation / Muscles

Roy Kristoffersen

Roy Kristoffersen walks through modeling, rigging and animating a character end to end, showing Houdini as a procedural character pipeline.

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

Yan Xia, Xiaowei Zhou, Etienne Vouga, Qixing Huang, Georgios Pavlakos

HSMR: first end-to-end image-to-SKEL regressor, jointly recovering the biomechanically accurate skeleton and body mesh from a single photograph.

Skinning / Muscles / Retargeting

Tetsuya Takahashi, Christopher Batty

This paper introduces a rest shape optimization framework that produces sag-free simulations of discrete elastic rods under gravity.

CFX

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

Untold Studios

Untold Studios breaks down the CFX pipeline for Disney's The Boy and the Octopus, simulating eight independently moving, shapeshifting, color changing tentacles.

CFX / Skinning

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

Arunachalam Somasundaram, DreamWorks Animation

Grooming and moving feathers at DreamWorks had been a technically complicated and specialized process, and the feathered characters of Kung Fu Panda 4 and The Wild Robot prompted a re-imagin

CFX

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

Juan Raul Padron-Griffe, Dario Lanza, Adrian Jarabo, Adolfo Munoz

This work proposes a practical surface-based appearance model for pennaceous feathers, representing far-field appearance with a BSDF that implicitly captures light scattering from the main b

CFX

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

Yunchen Yu, Andrea Weidlich, Bruce Walter, Eugene d'Eon, Steve Marschner

This work builds appearance models for biological iridescence using bird feathers as a case study, covering several distinct types of feathers with different structural coloration mechanisms

CFX

Weta FX

Apteryx is a Weta FX feather toolset that provides a complete workflow of procedural generation, hand sculpting and grooming for feathered creatures and costumes.

CFX

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

Vesa Paakkanen

Remedy Entertainment describes integrating OpenUSD into the Northlight engine for Alan Wake 2, covering character asset modularization and a live-edit pipeline from USD to runtime format.

Rigging

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

Mariana Dias, Pedro Jaime de Coelho, Rui Figueiredo, R. M. Carvalho, Veronica Orvalho, Alexis Roche

Didimo's talk on generating an unbounded cast from a single template, automating the days of manual work one non-player character normally costs.

Rigging / Facial

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

Yilin Zhu, Dalton Omens, Haodi He, Ron Fedkiw

Builds a person-specific facial rig without a light stage by warping real photographs onto a template avatar and projecting them into its texture, then capturing expressions with a Simon Says routine.

Facial / 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

Yuxiao Zhou, Menglei Chai, Daoye Wang, Sebastian Winberg, Erroll Wood, Kripasindhu Sarkar, Markus Gross, Thabo Beeler

Prior-free multi-view hair capture using a neural implicit hair volume that encodes high-resolution 3D orientation and occupancy; best paper award at SIGGRAPH Asia 2024.

CFX

Marilyn Keller, Vaibhav Arora, Abdelmouttaleb Dakri, Shivam Chandhok, Jurgen Machann, Andreas Fritsche, Michael J. Black, Sergi Pujades

HIT is an implicit volumetric function that classifies body interior points as fat, lean tissue, or bone given the SMPL body shape, trained on full-body MRI scans.

Muscles / 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

Jean Jouve, Victor Romero, Rahul Narain, Laurence Boissieux, Theodore Kim, Florence Bertails-Descoubes

Feathers behave in a highly anisotropic way governed by their hierarchical microstructure of barbs clamped onto a rachis and linked by tiny barbules, which prior cloth-strip approximations f

CFX

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

David Schneider, Simon Reiss, Marco Kugler, Alexander Jaus, Kunyu Peng, Susanne Sutschet, M. Saquib Sarfraz, Sven Matthiesen, Rainer Stiefelhagen

MinT: large-scale synthetic dataset of muscle activation sequences enriched from motion capture via OpenSim simulation, covering 227 subjects and 402 muscle strands.

Muscles / Motion Synthesis

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

Chengan He, Xin Sun, Zhixin Shu, Fujun Luan, Sören Pirk, Jorge Alejandro Amador Herrera, Dominik L. Michels, Tuanfeng Y. Wang, Meng Zhang, Holly Rushmeier, Yi Zhou

PCA-based frequency-domain strand disentanglement separates global hair structure from local curl patterns for precise editing and reconstruction as a generic prior.

CFX / ML Deformation

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

Xi Deng, Lifan Wu, Bruce Walter, Ravi Ramamoorthi, Eugene d'Eon, Steve Marschner, Andrea Weidlich

This paper tackles joint reconstruction of shape and appearance for thin translucent objects such as leaves and paper from real photographs, where light transmission complicates capture.

CFX

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

Jonghwan Hwang, Tzung-Da Tsai, Dan Ziegler

Sony Pictures Imageworks rebuilds rough layout for feature films using Unreal Engine with OpenUSD export to other DCCs, reducing per-sequence export time from eight hours to five minutes.

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

Stephan Wenninger, Fabian Kemper, Ulrich Schwanecke, Mario Botsch

Self-supervised volumetric body shape model fitting anatomical template (bones and soft tissue) to surface scans, enabling localized shape manipulation and fast inference.

Muscles / Skinning

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

Keenon Werling, Nicholas A. Bianco, Michael Raitor, Jon Stingel, Jennifer L. Hicks, Steven H. Collins, Scott L. Delp, C. Karen Liu

Open-source cloud service that automates OpenSim skeleton model scaling, marker registration, inverse kinematics, and inverse dynamics from mocap data via bilevel optimization.

Muscles / 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

Karthik Shetty, Annette Birkhold, Srikrishna Jaganathan, Norbert Strobel, Bernhard Egger, Markus Kowarschik, Andreas Maier

Deformable full-body model integrating skin, organs, and bones trained on 300 CT scans using SMPL architecture, achieving 3.6 mm bone and 8.8 mm organ accuracy.

Muscles / Skinning

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

Yuefan Shen, Shunsuke Saito, Ziyan Wang, Olivier Maury, Chenglei Wu, Jessica Hodgins, Youyi Zheng, Giljoo Nam

CT scanning of real-world wigs creates density volumes used to extract guide strands and populate dense hair via neural interpolation across diverse hairstyles.

CFX

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

Jens Jebens, Steve Agland, Jerran Schmidt, Pal Mezei, Aloys Baillet

SIGGRAPH Asia 2023 course on OpenUSD best practices covering proceduralism, Hydra 2.0, NVIDIA Omniverse Fabric GPU interoperability, and end-to-end pipeline case studies.

Rigging

Amelie Goursat

FOLKS VFX artist presents a Houdini-native procedural pipeline for creating realistic bird plumage, covering feather design, grooming, and integration into creature shots.

CFX

Tianxing Li, Rui Shi, Takashi Kanai

This learning-based clothing deformation method generates rich, plausible detailed deformations for garments worn by bodies of varying shapes across diverse animations using a single unified framework

ML Deformation / CFX

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

Yuxiao Zhou, Menglei Chai, Alessandro Pepe, Markus Gross, Thabo Beeler

First generative model for dense-strand hair using a hierarchical strand-guide-complete VAE architecture; introduces Strands400, 400-subject reconstructed strand dataset.

CFX / ML Deformation

Andriy Bilichenko

Paris HIVE talk on co-designing groom and simulation: how to build hair appearance in Houdini so dynamics enhance the look rather than destroy it across different hair types.

CFX

Vanessa Sklyarova, Egor Zakharov, Otmar Hilliges, Michael J. Black, Justus Thies

Text-driven latent diffusion model generating dense strand-based hairstyles in UV space from VQA-annotated synthetic data, upsampling to 100K strands.

CFX / ML Deformation

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

Vanessa Sklyarova, Jenya Chelishev, Andreea Dogaru, Igor Medvedev, Victor Lempitsky, Egor Zakharov

Two-stage strand-accurate reconstruction from monocular video or multi-view images: coarse volumetric orientation then strand optimization with learned prior.

CFX / ML Deformation

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

Georgios Kyparissous

Untold Studios FX Supervisor describes rebuilding their internal fur workflow in Houdini to deliver the CGI highland cow groom for Virgin Media's Highland Rider commercial.

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

Li Huang, Fan Yang, Chendi Wei, Yu Ju (Edwin) Chen, Chun Yuan, Ming Gao

This hybrid physics-based method targets real-time hair simulation for games, avatar streaming, and metaverse applications.

CFX

Yuhan Wu, Nobuyuki Umetani

This interactive framework unifies skinning transformations and kinematic simulation using position-based dynamics, letting an arbitrarily skinned character be partially manipulated by the user while

Skinning / CFX

Christian Lopez Barron, Chris Rydalch, Neil Hazzard, Nick Porcino, Paolo Emilio Selva, Emily Vo

Multimodal studio course covering USD asset structures, Maya and Houdini API integration, and context-driven production workflows from Animal Logic, Autodesk, Pixar, SideFX, Weta Digital, and WDAS.

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

Cyrus Rahgoshay, Alessandro Bernardi, Jaeeun Cho, Anthony Mazzier, Robin De Lillo, Adeline Aubame

Ubisoft deploys multi-site USD pipelines using BPMN workflow notation and microservices, enabling scalable character and asset interchange across distributed game studios.

Rigging

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