GridFace: Face Rectification via Learning Local Homography Transformations
Abstract
In this paper, we propose a novel method, called GridFace, to reduce facial geometric variations and improve the recognition performance. Our method rectifies the face by local homography transformations, which are estimated by a face rectification network. To encourage the image generation with canonical views, we apply a regularization based on the natural face distribution. We learn the rectification network and recognition network in an end-to-end manner. Extensive experiments show our method greatly reduces geometric variations, and gains significant improvements in unconstrained face recognition scenarios.
Cite
Text
Zhou et al. "GridFace: Face Rectification via Learning Local Homography Transformations." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01270-0_1Markdown
[Zhou et al. "GridFace: Face Rectification via Learning Local Homography Transformations." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/zhou2018eccv-gridface/) doi:10.1007/978-3-030-01270-0_1BibTeX
@inproceedings{zhou2018eccv-gridface,
title = {{GridFace: Face Rectification via Learning Local Homography Transformations}},
author = {Zhou, Erjin and Cao, Zhimin and Sun, Jian},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01270-0_1},
url = {https://mlanthology.org/eccv/2018/zhou2018eccv-gridface/}
}