Learning a Generalized Physical Face Model From Data

• Published in: ACM transactions on graphics Vol. 43; no. 4; pp. 1 - 14
• Main Authors: Yang, Lingchen, Zoss, Gaspard, Chandran, Prashanth, Gross, Markus, Solenthaler, Barbara, Sifakis, Eftychios, Bradley, Derek
• Format: Journal Article
• Language: English
• Published: New York, NY, USA ACM 19.07.2024
• Subjects: Computing methodologies; Computing methodologies / Artificial intelligence; Computing methodologies / Artificial intelligence / Computer vision; Computing methodologies / Artificial intelligence / Computer vision / Image and video acquisition; Computing methodologies / Artificial intelligence / Computer vision / Image and video acquisition / 3D imaging; Computing methodologies / Computer graphics; Computing methodologies / Computer graphics / Animation; Computing methodologies / Computer graphics / Animation / Physical simulation; Computing methodologies / Computer graphics / Animation / Procedural animation; Computing methodologies / Computer graphics / Shape modeling; Computing methodologies / Computer graphics / Shape modeling / Mesh models; digital humans; deep learning; physically-based facial animation; differentiable physics
• ISSN: 0730-0301; 1557-7368
• DOI: 10.1145/3658189

Physically-based simulation is a powerful approach for 3D facial animation as the resulting deformations are governed by physical constraints, allowing to easily resolve self-collisions, respond to external forces and perform realistic anatomy edits. Today's methods are data-driven, where the actuations for finite elements are inferred from captured skin geometry. Unfortunately, these approaches have not been widely adopted due to the complexity of initializing the material space and learning the deformation model for each character separately, which often requires a skilled artist followed by lengthy network training. In this work, we aim to make physics-based facial animation more accessible by proposing a generalized physical face model that we learn from a large 3D face dataset. Once trained, our model can be quickly fit to any unseen identity and produce a ready-to-animate physical face model automatically. Fitting is as easy as providing a single 3D face scan, or even a single face image. After fitting, we offer intuitive animation controls, as well as the ability to retarget animations across characters. All the while, the resulting animations allow for physical effects like collision avoidance, gravity, paralysis, bone reshaping and more.