Single Underwater Image Restoration by Contrastive Learning

TL;DR

This paper introduces a novel unsupervised contrastive learning approach for underwater image restoration, achieving state-of-the-art results and providing a large dataset for training.

Contribution

It proposes a new contrastive learning-based method for underwater image restoration and releases a large-scale dataset for training and evaluation.

Findings

Achieves state-of-the-art restoration quality

Demonstrates superiority over recent approaches

Provides a large real underwater image dataset

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.