Animated heads from ordinary images: A least-squares approach

We show that we can effectively fit arbitrarily complex animation models to noisy data extracted from ordinary face images. Our approach is based on l east-squares adjustment, using of a set of progressively finer control tria ngulations and takes advantage of three complementary sources of informatio n: stereo data, silhouette edges, and 2D feature points. In this way, compl ete head models-including ears and hair-can be acquired with a cheap and en tirely passive sensor, such as an ordinary video camera. They can then be f ed to existing animation software to produce synthetic sequences. (C) 1999 Academic Press.