Paper Info
Title
Underwater Image Restoration via Contrastive Learning and a Real-World Dataset
Abstract
Underwater image restoration is of significant importance in unveiling the underwater world. Numerous techniques and algorithms have been developed in recent 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 with regard to underwater image restoration. To address this gap, we constructed a large-scale real underwater image dataset, dubbed Heron Island Coral Reef Dataset ('HICRD'), for the purpose of benchmarking existing methods and supporting the development of new deep-learning based methods. We employed an accurate water parameter (diffuse attenuation coefficient) to generate the reference images. There are 2000 reference restored images and 6003 original underwater images in the unpaired training set. Furthermore, we present a novel method for underwater image restoration based on an 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 both publicly available.
Year
DOI
Venue
2022
10.3390/rs14174297
REMOTE SENSING
Keywords
DocType
Volume
underwater image restoration, underwater image enhancement, underwater image dataset, image restoration
Journal
14
Issue
ISSN
Citations 
17
2072-4292
0
PageRank 
References 
Authors
0.34
0
10
Name
Order
Citations
PageRank
Junlin Han101.35
Mehrdad Shoeiby201.69
Tim Malthus300.34
Elizabeth Botha400.34
Janet Anstee500.68
Saeed Anwar68012.28
Ran Wei700.34
Mohammad Ali Armin803.72
Hongdong Li91724101.81
Lars Petersson1020227.62