电子学报2025，Vol.53Issue(3)：926-940,15.DOI:10.12263/DZXB.20240375
基于渐进式边缘感知交互的多退化暗光图像增强
Progressive Edge-Aware Interactive Network for Multi-Degraded Low-Light Image Enhancement
摘要
Abstract
Images captured in low-light scenes are susceptible to multiple degradations such as darkness,noise,and blur,resulting in poor visibility and visual perception.Multi-degraded low-light image enhancement poses challenges to ex-isting image enhancement methods as follows:on the one hand,low-light image enhancement or deblurring methods cannot handle all three types of degradation,and the effect of the combination strategy is limited by the increased computational cost and error accumulation.On the other hand,the existing multi-degraded low-light image enhancement method adopts the strategy of enhancing brightness first and then removing blur,and this sequential processing manner increases the risk of losing feature cues and is not conducive to detail recovery.To cope with the above challenges,this paper proposes the pro-gressive edge-aware interactive enhancement network(PEIE-Net),which reduces the loss of feature details by designing a step-by-step enhancement process.Specifically,our network consists of an image enhancement branch and an edge informa-tion prediction branch.In each enhancement stage of the image enhancement branch,a self-attention modulation prediction module is designed to extract the global information,which is used for adaptive modulation in the channel modulation mod-ule and multi-scale restoration module.In the edge information prediction branch,the spatial-frequency domain feature transformation module is developed to extract the edge perceptual information.The edge perceptual information is used to predict the edges of high-quality images while also fused with the image enhancement features,simulating the interaction between different perceptions within the human visual system.In addition,we propose scene brightness estimation loss to coordinate the multiple progressive enhancement stages.Experiments on synthetic and real datasets demonstrate the effec-tiveness and sophistication of our method for enhancing low-light,noisy,and blur-degraded images,and can be used for low-light image enhancement and super-resolution tasks.关键词
图像增强/多退化图像/暗光增强/去模糊/特征调制Key words
image enhancement/multi-degraded image/low-light enhancement/deblurring/feature modulation分类
信息技术与安全科学引用本文复制引用
李悦洲,牛玉贞,李富晟,柯逍,施逸青..基于渐进式边缘感知交互的多退化暗光图像增强[J].电子学报,2025,53(3):926-940,15.基金项目
国家自然科学基金(No.U21A20472,No.62072110,No.61972097) （No.U21A20472,No.62072110,No.61972097）
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.62072110,No.61972097) （No.2021H6022）
Major Science and Technology Projects in 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 University Cooperation Project(No.2021H6022) （No.2021H6022）
