@article{Fu_Lin_Yang_Chai_Sun_Huang_Ding_2022, title={Unsupervised Underwater Image Restoration: From a Homology Perspective}, volume={36}, url={https://ojs.aaai.org/index.php/AAAI/article/view/19944}, DOI={10.1609/aaai.v36i1.19944}, abstractNote={Underwater images suffer from degradation due to light scattering and absorption. It remains challenging to restore such degraded images using deep neural networks since real-world paired data is scarcely available while synthetic paired data cannot approximate real-world data perfectly. In this paper, we propose an UnSupervised Underwater Image Restoration method (USUIR) by leveraging the homology property between a raw underwater image and a re-degraded image. Specifically, USUIR first estimates three latent components of the raw underwater image, i.e., the global background light, the transmission map, and the scene radiance (the clean image). Then, a re-degraded image is generated by randomly mixing up the estimated scene radiance and the raw underwater image. We demonstrate that imposing a homology constraint between the raw underwater image and the re-degraded image is equivalent to minimizing the restoration error and hence can be used for the unsupervised restoration. Extensive experiments show that USUIR achieves promising performance in both inference time and restoration quality.}, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Fu, Zhenqi and Lin, Huangxing and Yang, Yan and Chai, Shu and Sun, Liyan and Huang, Yue and Ding, Xinghao}, year={2022}, month={Jun.}, pages={643-651} }