Synthesis of facial images with lip motion from several real views

The synthesis of facial images by computer graphics is very important for many applications such as the human interface and visual entertainment. Lip motion is an essential factor in synthesizing the image sequence of conversation. We propose a new method for synthesizing facial images with lip motion. The key feature of our system is that it does not need any models of lip motion. Arbitrary lip shapes are expressed by the combination of several real views. By using several images with basic lip shapes, a facial image sequence with lip motion in conversation can be generated well by their linear combination