Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Instructional instruments for Web group learning systems: the grouping, intervention, and strategy
Proceedings of the 5th annual SIGCSE/SIGCUE ITiCSEconference on Innovation and technology in computer science education
Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Computer generated animation of faces
ACM '72 Proceedings of the ACM annual conference - Volume 1
Learning controls for blend shape based realistic facial animation
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
Vision-based control of 3D facial animation
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
A Theory of Networks for Approximation and Learning
A Theory of Networks for Approximation and Learning
Spacetime faces: high resolution capture for modeling and animation
ACM SIGGRAPH 2004 Papers
Mood swings: expressive speech animation
ACM Transactions on Graphics (TOG)
Automatic determination of facial muscle activations from sparse motion capture marker data
ACM SIGGRAPH 2005 Papers
A feature-based approach to facial expression cloning: Virtual Humans and Social Agents
Computer Animation and Virtual Worlds - CASA 2005
Geometry-Driven Photorealistic Facial Expression Synthesis
IEEE Transactions on Visualization and Computer Graphics
| Hi-index | 0.00 |
Web-based 3D facial animation is an alternative of face to face communication. Animating 3D human faces is also a difficult task because of the substantive non-rigid facial motions and utmost human familiarity with facial expressions. This paper presents a novel piece-wise learning approach to 3D facial animation driven by facial motion capture data. The pipeline of our algorithm comprises three major parts: (1) data pre-processing, (2) facial region segmentation, and (3) facial deformation. We first present an effective preprocessing algorithm for non-rigid motion extraction and data alignment. Second, based on the statistical and kinematical analysis of motion capture data and the topological analysis of facial mesh, our system segments the facial regions by a two-layer clustering algorithm. The edges of segments are well considered using an adapted plane/space partition algorithm. During runtime, the stream of motion capture data and the 3D face model are efficiently fused by cluster-wise optimization. The experimental results show that our algorithm is not only realistic but also fast enough for real time applications.