Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis
Abstract
In the last few years, Facial Expression Synthesis (FES) has been a flourishing area of research driven by applications in character animation, computer games, and human computer interaction. This paper proposes a photo-realistic FES method based on Bilinear Kernel Reduced Rank Regression (BKRRR). BKRRR learns a high-dimensional mapping between the appearance of a neutral face and a variety of expressions (e.g. smile, surprise, squint). There are two main contributions in this paper: (1) Propose BKRRR for FES. Several algorithms for learning the parameters of BKRRR are evaluated. (2) Propose a new method to preserve subtle person-specific facial characteristics (e.g. wrinkles, pimples). Experimental results on the CMU Multi-PIE database and pictures taken with a regular camera show the effectiveness of our approach.
Cite
Text
Huang and De la Torre. "Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15552-9_27Markdown
[Huang and De la Torre. "Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/huang2010eccv-bilinear/) doi:10.1007/978-3-642-15552-9_27BibTeX
@inproceedings{huang2010eccv-bilinear,
title = {{Bilinear Kernel Reduced Rank Regression for Facial Expression Synthesis}},
author = {Huang, Dong and De la Torre, Fernando},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {364-377},
doi = {10.1007/978-3-642-15552-9_27},
url = {https://mlanthology.org/eccv/2010/huang2010eccv-bilinear/}
}