Performance-driven facial animation
SIGGRAPH '90 Proceedings of the 17th annual conference on Computer graphics and interactive techniques
Active shape models—their training and application
Computer Vision and Image Understanding
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
3-D Motion Estimation in Model-Based Facial Image Coding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face Recognition by Elastic Bunch Graph Matching
CAIP '97 Proceedings of the 7th International Conference on Computer Analysis of Images and Patterns
Deformable Model-Based Shape and Motion Analysis from Images Using Motion Residual Error
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Universal capture: image-based facial animation for "The Matrix Reloaded"
ACM SIGGRAPH 2003 Sketches & Applications
Spacetime faces: high resolution capture for modeling and animation
ACM SIGGRAPH 2004 Papers
| Hi-index | 0.00 |
Creating an animation of a realistic and expressive human face is clearly one of greatest challenges in computer graphics. The human face is an extremely complex biomechanical system that is very difficult to model. Human skin has unique reflectance properties that are challenging to simulate accurately. Moreover the face can convey subtle emotions through minute motions. We do not know the control mechanism of these motions.This course focuses on animating the face, ignoring rendering issues. Although the subject is contentious, some people feel that manual keyframe animation may never capture the subtleties of real facial movement. A more practical viewpoint is that while some animators may be able to produce realistic facial animation, the consistent production of large amounts of flawless animation is expensive and probably not practical.On the other hand, the ideal "input device" for driving facial animation is probably the face itself --- simply mimicking the desired expression is far faster, easier, and more natural than adjusting dozens of sliders. Thus comes the idea of performance-driven facial animation: drive the animation directly from a person's captured facial performance.