Single Underwater Image Restoration by Contrastive Learning
Abstract
Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method.
Cite
@article{arxiv.2103.09697,
title = {Single Underwater Image Restoration by Contrastive Learning},
author = {Junlin Han and Mehrdad Shoeiby and Tim Malthus and Elizabeth Botha and Janet Anstee and Saeed Anwar and Ran Wei and Lars Petersson and Mohammad Ali Armin},
journal= {arXiv preprint arXiv:2103.09697},
year = {2021}
}
Comments
Accepted to IGARSS 2021 as oral presentation. Code is available at https://github.com/JunlinHan/CWR