Face Models from Uncalibrated Video Sequences

| We show that we can eeectively t a very complex facial animation models to uncalibrated video sequences , without beneet of targets, structured light o r a n y other active device. Our approach is based on regularized bundle-adjustment followed by least-squares adjustment using a set of progressively ner control triangulations. It takes advantage of three complementary sources of information: stereo data, silhouette edges and 22D feature points. In this way, complete head models can be acquired with a cheap and entirely passive sensor, such as an ordinary video camera. They can then be fed to existing animation software to produce synthetic sequences.