Analysis and reproduction of facial expressions for realistic communicating clones

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