GridFace: Face Rectification via Learning Local Homography Transformations

08/19/2018
by   Erjin Zhou, et al.
6

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset