Analysis and Reproduction of Facial Expressions for Realistic Communicating Clones

This paper presents a novel view-based approach to quantify and reproduce facial expressions, by systematically exploiting the degrees of freedom allowed by a realistic face model. This approach embeds e cient mesh morphing and texture animations to synthesize facial expressions. We suggest using eigenfeatures, built from synthetic images, and designing an estimator to interpret the responses of the eigenfeatures on a facial expression in terms of animation parameters.