Face modeling and animation for MPEG-4 compliant model based video coding

Abstract

3D face synthesis has been frequently used in model based video coding applications and became popular in various multimedia applications. In this paper a 3D face model with three different resolutions, its adaptation algorithm and animation are presented to solve several 3D estimation problems in model based video coding. We are successfully estimating the primary facial expressions of the face. The experimental results show that the proposed model and the proposed adaptation algorithm increases the visual quality of the synthesized face during animation of the head, while achieving a PSNR value of up to 35dB.