In this paper, we propose a 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.
@article{arxiv.1808.06210,
title = {GridFace: Face Rectification via Learning Local Homography Transformations},
author = {Erjin Zhou and Zhimin Cao and Jian Sun},
journal= {arXiv preprint arXiv:1808.06210},
year = {2018}
}