← ArchivePaper2022
Animatomy: An Animator-Centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer
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.
Abstract
We present Animatomy, a novel anatomic+animator centric representation of the human face. Present FACS-based systems are plagued with problems of face muscle separation, coverage, opposition, and redundancy. We, therefore, propose a collection of muscle fiber curves as an anatomic basis, whose contraction and relaxation provide us with a fine-grained parameterization of human facial expression. We build an end-to-end modular deformation architecture using this representation that enables: automatic optimization of the parameters of a specific face from high-quality dynamic facial scans; face animation driven by performance capture, keyframes, or dynamic simulation; interactive and direct manipulation of facial expression; and animation transfer from an actor to a character. We validate our facial system by showing compelling animated results, applications, and a quantitative comparison of our facial reconstruction to ground truth performance capture. Our system is being intensively used by a large creative team on Avatar: The Way of Water. We report feedback from these users as qualitative evaluation of our system.
How to read this
- Category
- Method: an anatomic, animator-centric facial representation and deformation system
- Contributions
- A muscle-fiber-curve basis whose contraction/relaxation parameterizes facial expression, addressing FACS muscle separation, coverage, opposition and redundancy
- An end-to-end modular deformation architecture supporting per-face parameter optimization from dynamic scans, performance/keyframe/simulation-driven animation, direct manipulation and actor-to-character transfer
- Quantitative comparison of facial reconstruction to ground-truth performance capture plus production-team feedback
- Context
- Reframes the FACS action-unit paradigm (Ekman & Friesen 1978) on an anatomical footing related to Anatomy Transfer (Dicko et al. 2013), substituting muscle-strain fibers for blendshape action units.Builds on: Facial Action Coding System · Anatomy Transfer
- Correctness
- Validated by a quantitative reconstruction comparison to captured ground truth and by qualitative feedback from the Avatar: The Way of Water team; note that 'intensively used in production' is real-world evidence but evaluation leans on one large project's context.
- Clarity
- Conceptually clear at the idea level; the fiber-curve parameterization and deformation optimization reward a careful second pass.
- How to read it
- First pass for the muscle-fiber-versus-FACS argument and the architecture diagram; do a second pass on the parameterization and optimization if you intend to implement or compare against it.
Builds on
Built upon by
Related work
- Animating Facial Expressions 1981 / SIGGRAPH
- Learning an Animatable Detailed 3D Face Model from In-The-Wild Images 2021 / SIGGRAPH
- Anatomically Constrained Implicit Face Models 2024 / CVPR
- Lessons from the Evolution of an Anatomical Facial Muscle Model 2017 / DigiPro
Keywords
This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →