Physically‐based facial modelling, analysis, and animation

TLDR

The paper introduces a new 3D hierarchical model of the human face and a method to estimate muscle contractions from video for realistic animation. The model employs a physically‑based tissue approximation with anatomically motivated muscle actuators, and the estimated muscle contractions serve as dynamic control inputs. The model runs at interactive rates on a high‑end workstation, and the muscle‑estimation technique accurately reconstructs expressions from dynamic face videos.

Abstract

Abstract We develop a new 3D hierarchical model of the human face. The model incorporates a physically‐based approximation to facial tissue and a set of anatomically‐motivated facial muscle actuators. Despite its sophistication, the model is efficient enough to produce facial animation at interactive rates on a high‐end graphics workstation. A second contribution of this paper is a technique for estimating muscle contractions from video sequences of human faces performing expressive articulations. These estimates may be input as dynamic control parameters to the face model in order to produce realistic animation. Using an example, we demonstrate that our technique yields sufficiently accurate muscle contraction estimates for the model to reconstruct expressions from dynamic images of faces.