基于运动传播和Isomap分析的三维人脸动画编辑与合成  

Editing and Synthesis of 3D Facial Animation by Motion Propagation and Isomap Analysis

作　　者：王玉顺[1] 肖俊[1] 庄越挺[1] 王宇杰[1] 

机构地区：[1]浙江大学计算机学院人工智能研究所,杭州310027

出　　处：《计算机辅助设计与图形学学报》2008年第12期1590-1595,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家杰出青年科学基金(60525108);国家科技支撑计划课题(2006BAH11B03-4)

摘　　要：提出一种三维人脸动画数据编辑与合成的有效方法,使用户可以在三维人脸模型上选定控制点,并在二维平面上指定表情动作的约束条件.根据人脸动画数据训练一个先验概率模型,将较少的用户约束传播到人脸网格的其他部分,从而生成完整生动的人脸表情;通过Isomap学习算法对三维人脸动画知识进行建模,并结合用户指定的关键帧拟合高维曲面上的平滑测地线,以自动合成新的人脸动画序列.实验结果表明,该方法可以直观地对人脸动画的生成进行交互式控制,并能生成较为逼真的表情动画.3D facial animation is a highly effective approach on editing and synthesis important but difficult task in computer graphics area. An of 3D facial animation is proposed. By the approach, users are enabled to assign constraints of facial movement through simple interaction in 2D screen space. A prior probahilistic model is trained by our system using facial animation data. With such a prior model, we propagate the user constraints to the whole 3D facial mesh to generate complete and lifelike facial expressions. By using Isomap learning algorithm, we model the knowledge of 3D facial animation. Incorporating the user specified key frames as end points, a smooth geodesic curve on the high dimensional space of facial animation data is approximated to produce novel animation sequence. Experimental results show that by the proposed method we can intuitively control the synthesis of facial animation and produce vivid expressional animation.

关 键 词：人脸动画 动画编辑 运动传播 Isomap分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]