Issue No. 02 - March-April (2012 vol. 32)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MCG.2012.41
Yuxu Lin , Zhejiang Univ., Hangzhou, China
Mingli Song , Zhejiang Univ., Hangzhou, China
Dao Thi Phuong Quynh , Nanyang Technol. Univ., Singapore, Singapore
Ying He , Nanyang Technol. Univ., Singapore, Singapore
Chun Chen , Zhejiang Univ., Hangzhou, China
Computer animation researchers have been extensively investigating 3D facial-expression synthesis for decades. However, flexible, robust production of realistic 3D facial expressions is still technically challenging. A proposed modeling framework applies sparse coding to synthesize 3D expressive faces, using specified coefficients or expression examples. It also robustly recovers facial expressions from noisy and incomplete data. This approach can synthesize higher-quality expressions in less time than the state-of-the-art techniques.
Face recognition, Animation, Three dimensional displays, Robustness, Computational modeling, Facial animation, Noise measurement
Yuxu Lin, Mingli Song, Dao Thi Phuong Quynh, Ying He and Chun Chen, "Sparse Coding for Flexible, Robust 3D Facial-Expression Synthesis," in IEEE Computer Graphics and Applications, vol. 32, no. 2, pp. 76-88, 2012.