Making Faces

Published in Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, 1998

We have created a system for capturing both the three-dimensionalgeometry and color and shading information for human facial expressions. We use this data to reconstruct photorealistic, 3D animations of the captured expressions. The system uses a large setof sampling points on the face to accurately track the three dimensional deformations of the face. Simultaneously with the trackingof the geometric data, we capture multiple high resolution, registered video images of the face. These images are used to create atexture map sequence for a three dimensional polygonal face modelwhich can then be rendered on standard 3D graphics hardware. Theresulting facial animation is surprisingly life-like and looks verymuch like the original live performance. Separating the capture ofthe geometry from the texture images eliminates much of the variance in the image data due to motion, which increases compressionratios. Although the primary emphasis of our work is not compression we have investigated the use of a novel method to compressthe geometric data based on principal components analysis. Thetexture sequence is compressed using an MPEG4 video codec. Animations reconstructed from 512x512 pixel textures look good atdata rates as low as 240 Kbits per second. Facial animation, facial traction

Download paper here

authors: Brian Guenter and Cindy Grimm and Daniel Wood and Henrique Malvar and Frederic Pighin

Authors: Brian Guenter and Cindy Grimm and Daniel Wood and Henrique Malvar and Frederic Pighin
Download Paper