Self-Supervised Deep Learning for Fisheye Image Rectification

Chun-Hao 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.
BibTeX
@inproceedings{chao2020self,
  author = {Chun-Hao Chao and Pin-Lun Hsu and Hung-Yi Lee and Yu-Chiang Frank Wang},
  title = {{Self-Supervised Deep Learning for Fisheye Image Rectification}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2020},
  doi = {10.1109/icassp40776.2020.9054191},
}

Loading related content...

Figure