论文信息 - Synthesis of facial images with lip motion from several real views

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.

[1] Christoph Bregler,et al. Video Rewrite: Driving Visual Speech with Audio , 1997, SIGGRAPH.

[2] John Yen,et al. Emotionally expressive agents , 1999, Proceedings Computer Animation 1999.

[3] Keith Waters,et al. Computer facial animation , 1996 .

[4] Yuichi Ohta,et al. Synthesis of Arbitrary Orientation Views from Two Face Images , 1995 .

[5] Andrew Blake,et al. Separability of pose and expression in facial tracking and animation , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[6] Stephen M. Omohundro,et al. Nonlinear manifold learning for visual speech recognition , 1995, Proceedings of IEEE International Conference on Computer Vision.

[7] Lance Williams,et al. Performance-driven facial animation , 1990, SIGGRAPH.

[8] Timothy F. Cootes,et al. Building and using flexible models using grey-level information , 1993, ICCV 1993.

[9] Yuichi Ohta,et al. Face Synthesis with Arbitrary Pose and Expression from Several Images - An Integration of Image-Based and Model-Based Approaches , 1998, ACCV.