https://scholars.lib.ntu.edu.tw/handle/123456789/559360
標題: | Self-Supervised Deep Learning for Fisheye Image Rectification | 作者: | Chao, C.-H. Hsu, P.-L. YU-CHIANG WANG HUNG-YI LEE |
關鍵字: | deep learning; fisheye camera; generative adversarial network; image rectification; self-supervised learning | 公開日期: | 2020 | 卷: | 2020-May | 起(迄)頁: | 2248-2252 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | 摘要: | 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. © 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85089218645&partnerID=40&md5=42a4846e2e68d99d140f770d8afc6918 https://scholars.lib.ntu.edu.tw/handle/123456789/559360 |
DOI: | 10.1109/ICASSP40776.2020.9054191 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。