基于分频式生成对抗网络的非成对水下图像增强
FD-GAN:Frequency-Decomposed Generative Adversarial Network for Unpaired Underwater Image Enhancement
摘要
Abstract
Enhancing the quality of underwater images is crucial for advancements in the fields of underwater explo-ration and underwater rescue.Existing underwater image enhancement methods typically rely on paired underwater images and reference images for training.However,obtaining corresponding reference images for underwater images is challenging in practice.In contrast,acquiring high-quality unpaired underwater images or images captured on land are relatively more straightforward.Furthermore,existing techniques for underwater image enhancement often struggle to address a variety of distortion types simultaneously.To avoid the reliance on paired training data,reduce the difficulty of acquiring training da-ta,and effectively handle diverse types of underwater image distortions,in this paper,we propose a novel unpaired underwa-ter image enhancement method based on the frequency-decomposed generative adversarial network(FD-GAN).We design a dual-branch generator based on high and low frequencies to reconstruct high-quality underwater images.Specifically,fea-ture-level wavelet transform is introduced to separate the features into low-frequency and high-frequency parts.Then the separated features are processed by a cycle-consistent generative adversarial network,so as to simultaneously enhance the color and luminance in the low-frequency component and details in the high-frequency part.More specific,the low-frequen-cy branch employs an encoder-decoder structure with a low-frequency attention mechanism to enhance the color and bright-ness of the image.The high-frequency branch utilizes parallel high-frequency attention mechanisms to enhance various high-frequency components,thereby achieving the restoration of image details.Experimental results on multiple datasets show that the proposed method trained with unpaired high-quality underwater images or unpaired high-quality underwater images and on-land images,can effectively generate high-quality underwater enhanced images and the proposed method is superior to the state-of-the-art underwater image enhancement methods in terms of effectiveness and generalization.关键词
水下图像增强/生成对抗网络/小波变换/注意力机制/高低频双分支生成器Key words
underwater image enhancement/generative adversarial networks/wavelet transform/attention mecha-nism/dual-branch generator based on high and low frequencies分类
信息技术与安全科学引用本文复制引用
牛玉贞,张凌昕,兰杰,许瑞,柯逍..基于分频式生成对抗网络的非成对水下图像增强[J].电子学报,2025,53(2):527-544,18.基金项目
国家自然科学基金(No.U21A20472,No.61972097) （No.U21A20472,No.61972097）
国家重点研发计划(No.2021YFB3600503) （No.2021YFB3600503）
福建省科技重大专项(No.2021HZ022007) （No.2021HZ022007）
福建省自然科学基金(No.2023J01067,No.2020J01494) （No.2023J01067,No.2020J01494）
福建省科技厅高校产学合作项目(No.2021H6022) National Natural Science Foundation of China(No.U21A20472,No.61972097) （No.2021H6022）
National Key Research and Development Program of China(No.2021YFB3600503) （No.2021YFB3600503）
Major Science and Technology Project of Fujian Province(No.2021HZ022007) （No.2021HZ022007）
Natural Science Foundation of Fujian Province(No.2023J01067,No.2020J01494) （No.2023J01067,No.2020J01494）
Fujian Provincial Department of Science and Technology University Industry-Academy Cooperation Project(No.2021H6022) （No.2021H6022）
