Position‐based facial animation synthesis

Marco Fratarcangeli

Abstract

We propose an integrated facial dynamics model addressing the animation of 3D humanoid faces in real time. The computational model mimics facial motion by reproducing the layered anatomical structure of a human head including the bony structure, overlapping facial muscles and the skin. The model is flexible enough to animate face meshes of various shape, connectivity, and scale. Different from previously proposed approaches based on mass–spring networks, overshooting problems are avoided by simulating the dynamics through a position‐based scheme, which allows for real‐time performance, control, and robustness. Experiments demonstrate that convincing expressive facial animation can be interactively prototyped on consumer class platforms.