Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-030-01270-0_1 | COMPUTER VISION - ECCV 2018, PT XVI |
Keywords | DocType | Volume |
Face recognition, Face rectification, Homography transformation | Conference | 11220 |
ISSN | Citations | PageRank |
0302-9743 | 6 | 0.43 |
References | Authors | |
21 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Erjin Zhou | 1 | 430 | 17.83 |
Zhimin Cao | 2 | 521 | 22.27 |
Jian Sun | 3 | 25842 | 956.90 |