Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2013, Vol. 14 Issue (7): 542-550    DOI: 10.1631/jzus.CIDE1307
    
Statistical learning based facial animation
Shibiao Xu, Guanghui Ma, Weiliang Meng, Xiaopeng Zhang
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Statistical learning based facial animation
Shibiao Xu, Guanghui Ma, Weiliang Meng, Xiaopeng Zhang
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
 全文: PDF 
摘要： To synthesize real-time and realistic facial animation, we present an effective algorithm which combines image- and geometry-based methods for facial animation simulation. Considering the numerous motion units in the expression coding system, we present a novel simplified motion unit based on the basic facial expression, and construct the corresponding basic action for a head model. As image features are difficult to obtain using the performance driven method, we develop an automatic image feature recognition method based on statistical learning, and an expression image semi-automatic labeling method with rotation invariant face detection, which can improve the accuracy and efficiency of expression feature identification and training. After facial animation redirection, each basic action weight needs to be computed and mapped automatically. We apply the blend shape method to construct and train the corresponding expression database according to each basic action, and adopt the least squares method to compute the corresponding control parameters for facial animation. Moreover, there is a pre-integration of diffuse light distribution and specular light distribution based on the physical method, to improve the plausibility and efficiency of facial rendering. Our work provides a simplification of the facial motion unit, an optimization of the statistical training process and recognition process for facial animation, solves the expression parameters, and simulates the subsurface scattering effect in real time. Experimental results indicate that our method is effective and efficient, and suitable for computer animation and interactive applications.
关键词： Facial animation;  Motion unit;  Statistical learning;  Realistic rendering;  Pre-integration    
Abstract: To synthesize real-time and realistic facial animation, we present an effective algorithm which combines image- and geometry-based methods for facial animation simulation. Considering the numerous motion units in the expression coding system, we present a novel simplified motion unit based on the basic facial expression, and construct the corresponding basic action for a head model. As image features are difficult to obtain using the performance driven method, we develop an automatic image feature recognition method based on statistical learning, and an expression image semi-automatic labeling method with rotation invariant face detection, which can improve the accuracy and efficiency of expression feature identification and training. After facial animation redirection, each basic action weight needs to be computed and mapped automatically. We apply the blend shape method to construct and train the corresponding expression database according to each basic action, and adopt the least squares method to compute the corresponding control parameters for facial animation. Moreover, there is a pre-integration of diffuse light distribution and specular light distribution based on the physical method, to improve the plausibility and efficiency of facial rendering. Our work provides a simplification of the facial motion unit, an optimization of the statistical training process and recognition process for facial animation, solves the expression parameters, and simulates the subsurface scattering effect in real time. Experimental results indicate that our method is effective and efficient, and suitable for computer animation and interactive applications.
Key words: Facial animation    Motion unit    Statistical learning    Realistic rendering    Pre-integration
收稿日期: 2012-12-29 出版日期: 2013-07-05
CLC:  TP391.9  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Shibiao Xu
Guanghui Ma
Weiliang Meng
Xiaopeng Zhang

引用本文:

Shibiao Xu, Guanghui Ma, Weiliang Meng, Xiaopeng Zhang. Statistical learning based facial animation. Front. Inform. Technol. Electron. Eng., 2013, 14(7): 542-550.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/jzus.CIDE1307    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2013/V14/I7/542

[1] Yao-ye Zhang, Zheng-xing Sun, Kai Liu, Mo-fei Song, Fei-qian Zhang. Extracting 3D model feature lines based on conditional random fields[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(7): 551-560.
[2] Jing Liao, Jin-hui Yu, Long Jia. Procedural modeling of water caustics and foamy water for cartoon animation[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(7): 533-541.