Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs

Underwater images suffer from color distortion, low contrast and blurring caused by the attenuation, refraction, and scattering of light. For many maritime operations, underwater image enhancement is essential. This paper proposes an underwater image enhancement method based on transformer, attentio...

Full description

Saved in:
Bibliographic Details
Main Authors: Liqiong Lu, Dong Wu, Liuyin Wang, Wanzhen Zhang, Tonglai Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11025830/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217901048463360
author Liqiong Lu
Dong Wu
Liuyin Wang
Wanzhen Zhang
Tonglai Liu
author_facet Liqiong Lu
Dong Wu
Liuyin Wang
Wanzhen Zhang
Tonglai Liu
author_sort Liqiong Lu
collection DOAJ
description Underwater images suffer from color distortion, low contrast and blurring caused by the attenuation, refraction, and scattering of light. For many maritime operations, underwater image enhancement is essential. This paper proposes an underwater image enhancement method based on transformer, attention and multi-color-space inputs. First, transformer block is embedded into ResNet-50 as the backbone network. Combining this backbone network and multi-scale feature fusion forms the fundamental framework of our method. This framework contributes to mine the rich features of different scene underwater image and outputs a feature map of the same size as the input image. Then, multi-dimensional attention mechanism is added to the feature maps of different scales to mine key areas that require enhancement in underwater images and calculate the enhancement value of each pixel. Finally, multi-color-space inputs including RGB, HSV and LAB as the inputs for CNN to enhancement images from various aspects such as color deviation, brightness and saturation. The comparison of image quality evaluation metrics, visual enhancement performance evaluation and impact on the performance of underwater object detection with other underwater enhancement methods on datasets including SUIM-E, UIEB, EUVP, RUIE-RIQS, RUIE-UCCS and URPC-2018 prove the good performance of our underwater image enhancement method.
format Article
id doaj-art-5a94105c9feb443e89d2e323a4337e01
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-5a94105c9feb443e89d2e323a4337e012025-08-20T02:07:57ZengIEEEIEEE Access2169-35362025-01-011310368210369610.1109/ACCESS.2025.357700511025830Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space InputsLiqiong Lu0https://orcid.org/0000-0003-0413-2097Dong Wu1Liuyin Wang2Wanzhen Zhang3Tonglai Liu4https://orcid.org/0000-0002-1845-5623School of Computer Science and Intelligence Education, Lingnan Normal University, Zhanjiang, ChinaSchool of Computer Science and Intelligence Education, Lingnan Normal University, Zhanjiang, ChinaSchool of Computer Science and Intelligence Education, Lingnan Normal University, Zhanjiang, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, ChinaCollege of Information Science and Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, ChinaUnderwater images suffer from color distortion, low contrast and blurring caused by the attenuation, refraction, and scattering of light. For many maritime operations, underwater image enhancement is essential. This paper proposes an underwater image enhancement method based on transformer, attention and multi-color-space inputs. First, transformer block is embedded into ResNet-50 as the backbone network. Combining this backbone network and multi-scale feature fusion forms the fundamental framework of our method. This framework contributes to mine the rich features of different scene underwater image and outputs a feature map of the same size as the input image. Then, multi-dimensional attention mechanism is added to the feature maps of different scales to mine key areas that require enhancement in underwater images and calculate the enhancement value of each pixel. Finally, multi-color-space inputs including RGB, HSV and LAB as the inputs for CNN to enhancement images from various aspects such as color deviation, brightness and saturation. The comparison of image quality evaluation metrics, visual enhancement performance evaluation and impact on the performance of underwater object detection with other underwater enhancement methods on datasets including SUIM-E, UIEB, EUVP, RUIE-RIQS, RUIE-UCCS and URPC-2018 prove the good performance of our underwater image enhancement method.https://ieeexplore.ieee.org/document/11025830/Underwater image enhancementtransformer blockCNNResNet-50multi-dimensional attention mechanismmulti-color-space inputs
spellingShingle Liqiong Lu
Dong Wu
Liuyin Wang
Wanzhen Zhang
Tonglai Liu
Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
IEEE Access
Underwater image enhancement
transformer block
CNN
ResNet-50
multi-dimensional attention mechanism
multi-color-space inputs
title Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
title_full Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
title_fullStr Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
title_full_unstemmed Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
title_short Underwater Image Enhancement Based on Transformer, Attention, and Multi-Color-Space Inputs
title_sort underwater image enhancement based on transformer attention and multi color space inputs
topic Underwater image enhancement
transformer block
CNN
ResNet-50
multi-dimensional attention mechanism
multi-color-space inputs
url https://ieeexplore.ieee.org/document/11025830/
work_keys_str_mv AT liqionglu underwaterimageenhancementbasedontransformerattentionandmulticolorspaceinputs
AT dongwu underwaterimageenhancementbasedontransformerattentionandmulticolorspaceinputs
AT liuyinwang underwaterimageenhancementbasedontransformerattentionandmulticolorspaceinputs
AT wanzhenzhang underwaterimageenhancementbasedontransformerattentionandmulticolorspaceinputs
AT tonglailiu underwaterimageenhancementbasedontransformerattentionandmulticolorspaceinputs