Animatomy: an Animator-centric, Anatomically Inspired System for 3D Facial Modeling, Animation and Transfer SIGGRAPH Asia 2022
BYUNGKUK CHOI1, HAEKWANG EOM1, BENJAMIN MOUSCADET1, STEPHEN CULLINGFORD2, KURT MA1, STEFANIE GASSEL1, SUZI KIM1, ANDREW MOFFAT1, MILLICENT MAIER1, MARCO REVELANT2, JOE LETTERI2, KARAN SINGH1,3
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 the film "Avatar: The Way of Water". We report feedback from these users as qualitative evaluation of our system.
We are thankful to the many people besides the authors of this
paper who contributed to Animatomy. Luca Fascione, Stuart Adcock,
and David Luke were particularly influential in supervising and
designing a research-oriented as well as production-friendly facial
system. Christoph Sprenger, Muhammad Ghifary, Gergely Klár,
Stephen Ward, Yeongho Seol, Tobias Schmidt, and Daniel Lond each
contributed multiple years of research to make Animatomy a robust
system. Matt Penman, Braden Jennings, Alex Telford, Leon Woud,
Ben Goldberg, Nivedita Goswami, Sebastian Gassel, Josh Hardgrave,
and Matthew Jeng put a tremendous amount of development effort
into Animatomy to complete large-scale production requirements.
We are also thankful for leadership and management support from
Tom Buys, Joerg Fluegge, Kenneth Gimpelson, Derrick Auyoung,
Dejan Momcilovic, Daniel Hodson, and Julia Jones. Many talented
artists have worked closely with the Facial Research team. Thank
you to Marco Barbati, Rachel Hydes, Bex Leybourne, and Allison
Orr from the Facial Models and Motion departments.
Animatomy is a high-end facial animation pipeline built on a novel face parameterization using contractile muscle curves. We present the construction and fitting of the muscle curves to a set of dynamic 3D scans for an actor (a), using a passive muscle simulation (b). Muscle contractions (strains) parameterize these scans and are used to learn a manifold of plausible facial expressions (c). The strains, in turn, control skin deformation (d) and readily transfer expression from an actor to characters. In production, the strains can be animated by performance capture (e) and animator interaction (f). ©Wētā FX.