Underwater Image Restoration via Contrastive Learning and a Real-world Dataset

TL;DR

This paper introduces a large-scale real underwater image dataset and a novel contrastive learning-based method for underwater image restoration, demonstrating superior performance over existing approaches.

Contribution

The paper provides a new real-world dataset for benchmarking and develops an unsupervised contrastive learning framework for underwater image restoration.

Findings

The dataset contains 2000 reference images and 6003 unpaired underwater images.

The proposed method outperforms recent approaches in restoration quality.

Extensive experiments validate the effectiveness of the contrastive learning framework.

Abstract

Underwater image restoration is of significant importance in unveiling the underwater world. Numerous techniques and algorithms have been developed in the past decades. However, due to fundamental difficulties associated with imaging/sensing, lighting, and refractive geometric distortions, in capturing clear underwater images, no comprehensive evaluations have been conducted of underwater image restoration. To address this gap, we have constructed a large-scale real underwater image dataset, dubbed `HICRD' (Heron Island Coral Reef Dataset), for the purpose of benchmarking existing methods and supporting the development of new deep-learning based methods. We employ accurate water parameter (diffuse attenuation coefficient) in generating reference images. There are 2000 reference restored images and 6003 original underwater images in the unpaired training set. Further, we present a novel method for underwater image restoration based on unsupervised image-to-image translation framework. Our proposed method leveraged contrastive learning and generative adversarial networks to maximize the mutual information between raw and restored images. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method. Our code and dataset are publicly available at GitHub.