Self-Supervised Deep Learning for Fisheye Image Rectification
B. T. Chao, Pin-Lun Hsu, Hung-yi Lee, Yu-Chiang Frank Wang
Abstract
To rectify fisheye distortion from a single image, we advance self-supervised learning strategies and propose a unique deep learning model of Fisheye GAN (FE-GAN). Our FE-GAN learns pixel-level distortion flow from sets of fisheye distorted images and distortion-free ones (but not requiring such correspondences), with unique cross-rotation and intra-warping consistency introduced. With such novel self-supervised learning techniques, our FEGAN is able to recover the distortion-free image directly from the single fisheye image input. Our experiments quantitatively and qualitative confirm the effectiveness and robustness of our proposed model, which performs favorably against recent GAN-based image translation models.