Facial Expression Synthesis Using MALS-based Bilinear Factorization Model

Authors

Jiaci Guo, 1. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China; ;2. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China;
Shuling Dai, 1. State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China; ;2. School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China;

Abstract

Abstract: Study on the facial expression synthesis is a constructive and creative subject in the field of virtual reality technology. The bilinear model is used for facial expression synthesis by separating the identity factor and the expression factor. The translation procedure in the bilinear model always requires a repetitive computation of matrix inverse operations to reach the identity factor and the expression factor. This computation may be instable when the observation data has the correlation or noisy information. In order to increase the stability of the bilinear model for expression synthesis, the modified iterative least square (MALS) regression is introduced into the translation procedure to stabilize the computation. Experimental results demonstrate the effectiveness of the method.

Recommended Citation

Guo, Jiaci and Dai, Shuling (2019) "Facial Expression Synthesis Using MALS-based Bilinear Factorization Model," Journal of System Simulation: Vol. 31: Iss. 4, Article 9.
DOI: 10.16182/j.issn1004731x.joss.17-0144
Available at: https://dc-china-simulation.researchcommons.org/journal/vol31/iss4/9

First Page

671

Revised Date

2017-05-16

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.17-0144

Last Page

678

CLC

TP391.9

Recommended Citation

Guo Jiaci, Dai Shuling. Facial Expression Synthesis Using MALS-based Bilinear Factorization Model[J]. Journal of System Simulation, 2019, 31(4): 671-678.

DOI

10.16182/j.issn1004731x.joss.17-0144