电子学报2025，Vol.53Issue(12)：4349-4363,15.DOI:10.12263/DZXB.20250429
基于双域特征交互和局部相关性上采样的单幅图像去雾方法
Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing
摘要
Abstract
Suspended particulates of the atmosphere in hazy weather markedly degrade the imaging quality of visible light systems,which manifests as reduced image contrast,color distortion,and loss of fine-grained details.Such image dete⁃rioration substantially impairs the performance of computer vision tasks.Consequently,image dehazing is commonly em⁃ployed as a preprocessing step for high-level visual tasks to furnish processes with high-quality visual data.U-Net-based im⁃age dehazing architecture has garnered widespread attention due to its efficiency,detail-oriented feature extraction,and lightweight characteristics.However,current U-Net-based networks realize image dehazing based on features extracted from space domain,ignoring the impact of features in frequency domain.In addition,the decoder of U-Net-based networks always realizes feature upsampling by nearest neighbor interpolation.It may cause spatial information loss and impact se⁃mantic information transmission from high-level to low-level,which adversely affects clear image restriction.To address the above issues,this paper proposes a novel image dehazing algorithm with dual-domain feature interaction and local corre⁃lation upsampling.Specifically,the dual-domain feature interaction module,including dual-path feature fusion submodule and frequency domain feature enhancement sub-module,is designed to extract and fuse the spatial domain and frequency domain features of the image.It can enhance the ability to capture the structural features of the image by introducing fre⁃quency domain information.Local correlation upsampling module embedded in decoder of U-Net is designed to capture the intrinsic correlation of local information of each feature map by attention mechanism,and transmit the high-level features with the compensatory information the low-level features simultaneously.In addition,we propose a contrast analysis meth⁃od based on heat maps to visually the dehazing performance of different methods,which uses color gradients to quantitative⁃ly measure the differences in the dehazing effect.It can effectively reflect the performance differences of various dehazing methods in terms of image detail restoration.The experimental results demonstrate that the dehazing effect of our proposed method is superior to that of the compared method in both quantitative and qualitative evaluations.The peak signal noise ra⁃tio(PSNR)and structural similarity index measure(SSIM)values on the SOTS-Indoor,SOTS-Outdoor and Hzae4K datas⁃ets achieve 41.46 dB and 0.994 3,37.73 dB and 0.993 6,34.72 dB and 0.993,respectively.关键词
图像去雾/U型网络结构/空间域与频域特征交互/局部相关性上采样/信息融合Key words
image dehaze/U-Net-based architecture/spatial and frequency domain feature interaction/local correla⁃tion upsampling/information fusion分类
信息技术与安全科学引用本文复制引用
刘明杰,吕梦琳,刘平,陈俊生,朴昌浩,康宗绪..基于双域特征交互和局部相关性上采样的单幅图像去雾方法[J].电子学报,2025,53(12):4349-4363,15.基金项目
重庆市技术创新与应用发展专项重大项目(No.CSTB2023TIAD-STX0035) Chongqing Municipal Major Project for Technological Innovation and Application Develop-ment(No.CSTB2023TIAD-STX0035) （No.CSTB2023TIAD-STX0035）
