articleIEEE Transactions on Image ProcessingJan 1, 2023Closed access

U-Shape Transformer for Underwater Image Enhancement

LPLintao PengCZChunli ZhuLBLiheng Bian

Beijing Institute of Technology

PubMed
Indexed incrossrefpubmed

Abstract

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we built a large scale underwater image (LSUI) dataset, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets. The dataset contains 4279 real-world underwater image groups, in which each raw image's clear…

Citation impact

705
total citations
FWCI
79.73
Percentile
100%
References
71
Citations per year

Authors

3

Topics & keywords

Topics
Keywords
  • Underwater
  • Computer science
  • Artificial intelligence
  • Computer vision
  • RGB color model
  • Transformer
  • Segmentation
  • Color space
UN Sustainable Development Goals
  • Life below water
No related works found for this paper.

Funding