From Regular Images to Animated Heads: A Least Squares Approach

Abstract. We show that we can e ectively t arbitrarily complex animation models to noisy image data. Our approach is based on leastsquares adjustment using of a set of progressively ner control triangulations and takes advantage ofthree complementary sources of information: stereo data, silhouette edges and 2 D feature points. In this way, complete head models|including ears and hair|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.

• Type: Conference
• Year: 1998
• Where: ECCV
• Authors: Pascal Fua, C. Miccio
• Keywords: Complex Animation Models, Computer Vision, ECCV 1998, Head Models|including Ears, Ner Control Triangulations, Noisy Image Data, Ordinary Video Camera