Bézier Volume Deformation Model for Facial Animation and Video Tracking

Authors:
Hai Tao;Thomas S. Huang
Affiliations:
-;-
Venue:
CAPTECH '98 Proceedings of the International Workshop on Modelling and Motion Capture Techniques for Virtual Environments
Year:
1998

Citing 7
Cited 1

Free-form deformation of solid geometric models

SIGGRAPH '86 Proceedings of the 13th annual conference on Computer graphics and interactive techniques
Performance-driven facial animation

SIGGRAPH '90 Proceedings of the 17th annual conference on Computer graphics and interactive techniques
Realistic modeling for facial animation

SIGGRAPH '95 Proceedings of the 22nd annual conference on Computer graphics and interactive techniques
Computer generated animation of faces

ACM '72 Proceedings of the ACM annual conference - Volume 1
The Integration of Optical Flow and Deformable Models with Applications to Human Face Shape and Motion Estimation

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Animating facial expressions

SIGGRAPH '81 Proceedings of the 8th annual conference on Computer graphics and interactive techniques
Analysis, interpretation and synthesis of facial expressions

Analysis, interpretation and synthesis of facial expressions

Bootstrap Initialization of Nonparametric Texture Models for Tracking

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Capturing real motions from video sequences is a powerful approach to automatically build facial deformation model. In this paper, a 3D Bézier volume deformation model is proposed for both synthesis and analysis of facial movements. Since this model is independent of the mesh structure provided the feature points are given, it is capable of animating geometric facial models of different shapes and structures. Of the same importance, the linear property of this model implies a simple and robust analysis algorithm, from which a customized facial deformation model is derived. Experimental results on animation and video analysis are demonstrated in this paper.