Personalized Multi-View Face Animation with Lifelike Textures  

作　　者：柳杨华 徐光祐 

机构地区：[1]Key Laboratory on Pervasive Computing (Tsinghua University) of the Ministry of Education, Department of Computer Science and Technology, Tsinghua University

出　　处：《Tsinghua Science and Technology》2007年第1期51-57,共7页清华大学学报（自然科学版（英文版）

基　　金：the National Natural Science Foundation of China (No. 60673189)

摘　　要：Realistic personalized face animation mainly depends on a picture-perfect appearance and natural head rotation. This paper describes a face model for generation of novel view facial textures with various realistic expressions and poses. The model is achieved from corpora of a talking person using machine learning techniques. In face modeling, the facial texture variation is expressed by a multi-view facial texture space model, with the facial shape variation represented by a compact 3-D point distribution model （PDM）. The facial texture space and the shape space are connected by bridging 2-D mesh structures. Levenberg-Marquardt optimization is employed for fine model fitting. Animation trajectory is trained for smooth and continuous image sequences. The test results show that this approach can achieve a vivid talking face sequence in various views. Moreover, the animation complexity is significantly reduced by the vector representation.Realistic personalized face animation mainly depends on a picture-perfect appearance and natural head rotation. This paper describes a face model for generation of novel view facial textures with various realistic expressions and poses. The model is achieved from corpora of a talking person using machine learning techniques. In face modeling, the facial texture variation is expressed by a multi-view facial texture space model, with the facial shape variation represented by a compact 3-D point distribution model （PDM）. The facial texture space and the shape space are connected by bridging 2-D mesh structures. Levenberg-Marquardt optimization is employed for fine model fitting. Animation trajectory is trained for smooth and continuous image sequences. The test results show that this approach can achieve a vivid talking face sequence in various views. Moreover, the animation complexity is significantly reduced by the vector representation.

关 键 词：face animation point distribution model （PDM） TEXTURE MULTI-VIEW 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]