Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images

The increasing application of underwater robotic systems in deep-sea exploration, inspection, and resource extraction has created a strong demand for reliable visual perception under challenging conditions. However, image quality is severely degraded in low-light underwater environments due to the c...

Full description

Saved in:
Bibliographic Details
Main Authors: Dechuan Kong, Jinglong Mao, Yandi Zhang, Xiaohu Zhao, Yanyan Wang, Shungang Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/6/1092
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167761515315200
author Dechuan Kong
Jinglong Mao
Yandi Zhang
Xiaohu Zhao
Yanyan Wang
Shungang Wang
author_facet Dechuan Kong
Jinglong Mao
Yandi Zhang
Xiaohu Zhao
Yanyan Wang
Shungang Wang
author_sort Dechuan Kong
collection DOAJ
description The increasing application of underwater robotic systems in deep-sea exploration, inspection, and resource extraction has created a strong demand for reliable visual perception under challenging conditions. However, image quality is severely degraded in low-light underwater environments due to the combined effects of light absorption and scattering, resulting in color imbalance, low contrast, and illumination instability. These factors limit the effectiveness of visual-based autonomous operations. We propose ATS-UGAN, a Dual-domain Adaptive Synergy Generative Adversarial Network for low-light underwater image enhancement to confront the above issues. The network integrates Multi-scale Hybrid Attention (MHA) that synergizes spatial and frequency domain representations to capture key image features adaptively. An Adaptive Parameterized Convolution (AP-Conv) module is introduced to handle non-uniform scattering by dynamically adjusting convolution kernels through a multi-branch design. In addition, a Dynamic Content-aware Markovian Discriminator (DCMD) is employed to perceive the dual-domain information synergistically, enhancing image texture realism and improving color correction. Extensive experiments on benchmark underwater datasets demonstrate that ATS-UGAN surpasses state-of-the-art approaches, achieving 28.7/0.92 PSNR/SSIM on EUVP and 28.2/0.91 on UFO-120. Additional reference and no-reference metrics further confirm the improved visual quality and realism of the enhanced images.
format Article
id doaj-art-ece026c43c3346259f01fb7dbf941648
institution OA Journals
issn 2077-1312
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-ece026c43c3346259f01fb7dbf9416482025-08-20T02:21:07ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-01136109210.3390/jmse13061092Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater ImagesDechuan Kong0Jinglong Mao1Yandi Zhang2Xiaohu Zhao3Yanyan Wang4Shungang Wang5National and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Artificial Intelligence, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870, ChinaNational and Local Joint Engineering Laboratory of Internet Application Technology on Mine, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Artificial Intelligence, Henan Institute of Science and Technology, Xinxiang 453003, ChinaSchool of Artificial Intelligence, Henan Institute of Science and Technology, Xinxiang 453003, ChinaThe increasing application of underwater robotic systems in deep-sea exploration, inspection, and resource extraction has created a strong demand for reliable visual perception under challenging conditions. However, image quality is severely degraded in low-light underwater environments due to the combined effects of light absorption and scattering, resulting in color imbalance, low contrast, and illumination instability. These factors limit the effectiveness of visual-based autonomous operations. We propose ATS-UGAN, a Dual-domain Adaptive Synergy Generative Adversarial Network for low-light underwater image enhancement to confront the above issues. The network integrates Multi-scale Hybrid Attention (MHA) that synergizes spatial and frequency domain representations to capture key image features adaptively. An Adaptive Parameterized Convolution (AP-Conv) module is introduced to handle non-uniform scattering by dynamically adjusting convolution kernels through a multi-branch design. In addition, a Dynamic Content-aware Markovian Discriminator (DCMD) is employed to perceive the dual-domain information synergistically, enhancing image texture realism and improving color correction. Extensive experiments on benchmark underwater datasets demonstrate that ATS-UGAN surpasses state-of-the-art approaches, achieving 28.7/0.92 PSNR/SSIM on EUVP and 28.2/0.91 on UFO-120. Additional reference and no-reference metrics further confirm the improved visual quality and realism of the enhanced images.https://www.mdpi.com/2077-1312/13/6/1092dual-domain synergyadaptive enhancementlow-light underwater image enhancementgenerative adversarial network
spellingShingle Dechuan Kong
Jinglong Mao
Yandi Zhang
Xiaohu Zhao
Yanyan Wang
Shungang Wang
Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
Journal of Marine Science and Engineering
dual-domain synergy
adaptive enhancement
low-light underwater image enhancement
generative adversarial network
title Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
title_full Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
title_fullStr Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
title_full_unstemmed Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
title_short Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images
title_sort dual domain adaptive synergy gan for enhancing low light underwater images
topic dual-domain synergy
adaptive enhancement
low-light underwater image enhancement
generative adversarial network
url https://www.mdpi.com/2077-1312/13/6/1092
work_keys_str_mv AT dechuankong dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages
AT jinglongmao dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages
AT yandizhang dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages
AT xiaohuzhao dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages
AT yanyanwang dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages
AT shungangwang dualdomainadaptivesynergyganforenhancinglowlightunderwaterimages