Realistic speech animation based on observed 3D face dynamics

An efficient system for realistic speech animation is proposed. The system supports all steps of the animation pipeline, from the capture or design of 3D head models up to the synthesis and editing of the performance. This pipeline is fully 3D, which yields high flexibility in the use of the animated character. Real detailed 3D face dynamics, observed at video frame rate for thousands of points on the face of speaking actors, underpin the realism of the facial deformations. These are given a compact and intuitive representation via independent component analysis (ICA). Performances amount to trajectories through this ´viseme space´. When asked to animate a face, the system replicates the ´visemes´ that it has learned, and adds the necessary coarticulation effects. Realism has been improved through comparisons with motion captured groundtruth. Faces for which no 3D dynamics have been observed can be animated nonetheless. Their visemes are adapted automatically to their physiognomy by localising the face in a ´face space´.