Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing

LIU Ming-jie; LYU Meng-lin; LIU Ping; CHEN Jun-sheng; PIAO Chang-hao; KANG Zong-xu

doi:10.12263/DZXB.20250429

您当前的位置：

首页 >

文章列表页 >

Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing

PAPERS | 更新时间：2026-04-24

- Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing
- ACTA ELECTRONICA SINICA Vol. 53, Issue 12, Pages: 4349-4363(2025)
- 作者机构：
  
  1.重庆邮电大学自动化学院，重庆 400065
  2.重庆金美通信有限责任公司，重庆 400060
- 作者简介：
- 基金信息：
  
  Chongqing Municipal Major Project for Technological Innovation and Application Development(CSTB2023TIAD-STX0035)
- DOI：10.12263/DZXB.20250429
  CLC： TP391.4;
- Received：28 May 2025，
  
  Accepted：08 December 2025，
  
  Published：25 December 2025
- 稿件说明：
移动端阅览
刘明杰, 吕梦琳, 刘平, 等. 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.

LIU Ming-jie, LYU Meng-lin, LIU Ping, et al. Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing[J]. Acta Electronica Sinica, 2025, 53(12): 4349-4363.
刘明杰, 吕梦琳, 刘平, 等. 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. DOI：10.12263/DZXB.20250429

LIU Ming-jie, LYU Meng-lin, LIU Ping, et al. Dual-Domain Feature Interaction and Local Correlation Upsampling Network for Single Image Dehazing[J]. Acta Electronica Sinica, 2025, 53(12): 4349-4363. DOI：10.12263/DZXB.20250429

摘要

雾霾天大气中的悬浮颗粒会导致可见光系统的成像质量显著降低，产生图像对比度下降、颜色失真、细节信息丢失等图像退化现象.这种退化会严重影响计算机视觉下游任务的性能.因此，通常会把图像去雾作为诸如目标检测、目标分割等高阶视觉任务的预处理过程，旨在为后续任务提供高质量的图像内容信息.基于U型网络的图像去雾架构因具有高效、注重细节特征、轻量化等特点而得到了广泛关注.然而，当前该类架构主要聚焦于通过提取图像的空间域特征达成去雾效果，忽略了频域特征对图像去雾的影响.U型结构中解码层采用的最近邻插值法上采样方法还会导致图像空间信息的丢失，进而影响深层语义信息向浅层的有效传递，使得重构的清晰图像不够理想.针对上述问题，本文以U-Net为基础结构提出一种双域特征交互和局部相关性上采样的单幅图像去雾方法.首先在特征提取部分设计了双域特征交互模块，分别通过双路特征融合子模块和频域特征增强子模块针对图像的空间域与频域特征分别提取，并对这些特征进行交互通过引入频域信息提升模型对图像结构特征的捕捉能力.接着在解码层上采样部分设计局部相关性上采样模块，利用注意力机制捕捉每个特征图中局部信息的内在相关性，并将含有特征补偿的深层语义特征传递至浅层，有效地实现了不同尺度特征中语义信息的提取和融合. 此外，为了直观表征算法的去雾性能，本文提出一种基于热力图的对比分析方法，即通过颜色梯度直观量化去雾效果差异，其可以有效反映各去雾方法在图像细节还原方面的性能差异.实验结果表明，本文提出的图像去雾方法在确保较低参数量和模型计算复杂度的同时，在客观指标和主观视觉效果上均取得了较好的效果，在SOTS-Indoor、SOTS-Outdoor和Haze4K3个数据上的峰值信噪比（Peak Signal Noise Ratio，PSNR）和结构相似性指数（Structural Similarity Index Measure，SSIM）分别达到了41.46 dB和0.994 3、37.73 dB和0.993 6、34.72 dB和0.993.

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 deterioration substantially impairs the performance of computer vision tasks. Consequently

image dehazing is commonly employed as a preprocessing step for high-level visual tasks to furnish processes with high-quality visual data. U-Net-based image 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 semantic 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 correlation 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 frequency 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 method based on heat maps to visually the dehazing performance of different methods

which uses color gradients to quantitatively 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 ratio (PSNR) and structural similarity index measure (SSIM) values on the SOTS-Indoor

SOTS-Outdoor and Hzae4K datasets 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

Keywords

references

贾童瑶 , 卓力 , 李嘉锋 , 等 . 基于深度学习的单幅图像去雾研究进展 [J ] . 电子学报 , 2023 , 51 ( 1 ): 231 - 245 .

JIA T Y , ZHUO L , LI J F , et al . Research advances on deep learning based single image dehazing [J ] . Acta Electronica Sinica , 2023 , 51 ( 1 ): 231 - 245 . (in Chinese)

CHEN Z X , HE Z W , LU Z M . DEA-net: Single image dehazing based on detail-enhanced convolution and content-guided attention [J ] . IEEE Transactions on Image Processing , 2024 , 33 : 1002 - 1015 .

付文晓 , 张锐 , 林丽丽 , 等 . 雾天室外场景光照参数估计 [J ] . 软件学报 , 2014 , 25 ( 增刊2 ): 268 - 277 .

FU W X , ZHANG R , LIN L L , et al . Illumination estimation of hazing outdoor scene [J ] . Journal of Software , 2014 , 25 ( S2 ): 268 - 277 . (in Chinese)

任东东 , 李金宝 . 低光照环境下的图像恢复与目标识别方法 [J ] . 软件学报 , 2019 , 30 ( 增刊1 ): 94 - 104 .

REN D D , LI J B . Methods of image restoration and object detection in low-light environment [J ] . Journal of Software , 2019 , 30 ( S1 ): 94 - 104 . (in Chinese)

YU H , ZHENG N S , ZHOU M , et al . Frequency and spatial dual guidance for image dehazing [C ] // Computer Vision-ECCV 2022 . Cham : Springer , 2022 : 181 - 198 .

HE K M , SUN J , TANG X O . Single image haze removal using dark channel prior [C ] // 2009 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2009 : 1956 - 1963 .

BERMAN D , TREIBITZ T , AVIDAN S . Non-local image dehazing [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 1674 - 1682 .

ZHU Q S , MAI J M , SHAO L . A fast single image haze removal algorithm using color attenuation prior [J ] . IEEE Transactions on Image Processing , 2015 , 24 ( 11 ): 3522 - 3533 .

LIU R S , FAN X , HOU M J , et al . Learning aggregated transmission propagation networks for haze removal and beyond [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2019 , 30 ( 10 ): 2973 - 2986 .

LIU Y , PAN J S , REN J , et al . Learning deep priors for image dehazing [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2020 : 2492 - 2500 .

ZHAO S Y , ZHANG L , SHEN Y , et al . RefineDNet: A weakly supervised refinement framework for single image dehazing [J ] . IEEE Transactions on Image Processing , 2021 , 30 : 3391 - 3404 .

ZHOU H , CHEN Z K , LIU Y , et al . Physical-priors-guided dehazeformer [J ] . Knowledge-Based Systems , 2023 , 266 : 110410 .

KRICHEN M . Generative adversarial networks [C ] // 2023 14th International Conference on Computing Communication and Networking Technologies . Piscataway : IEEE , 2023 : 1 - 7 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [EB/OL ] . ( 2023-08-02 )[ 2025-06-10 ] . https://arXiv.org/abs/1706.03762 https://arXiv.org/abs/1706.03762 .

RONNEBERGER O , FISCHER P , BROX T . U-Net: Convolutional networks for biomedical image segmentation [C ] // Medical Image Computing and Computer-Assisted Intervention . Cham : Springer , 2015 : 234 - 241 .

CAI B L , XU X M , JIA K , et al . DehazeNet: An end-to-end system for single image haze removal [J ] . IEEE Transactions on Image Processing , 2016 , 25 ( 11 ): 5187 - 5198 .

LI B Y , PENG X L , WANG Z Y , et al . AOD-net: All-in-one dehazing network [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 4780 - 4788 .

ZHANG H , PATEL V M . Densely connected pyramid dehazing network [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3194 - 3203 .

LI Y N , MIAO Q G , OUYANG W L , et al . LAP-net: Level-aware progressive network for image dehazing [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2020 : 3275 - 3284 .

REN W Q , PAN J S , ZHANG H , et al . Single image dehazing via multi-scale convolutional neural networks with holistic edges [J ] . International Journal of Computer Vision , 2020 , 128 ( 1 ): 240 - 259 .

ZHANG L B , WANG S , WANG X H . Single image dehazing based on bright channel prior model and saliency analysis strategy [J ] . IET Image Processing , 2021 , 15 ( 5 ): 1023 - 1031 .

ZHU J Y , PARK T , ISOLA P , et al . Unpaired image-to-image translation using cycle-consistent adversarial networks [C ] // 2017 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2017 : 2242 - 2251 .

ENGIN D , GENC A , EKENEL H K . Cycle-dehaze: Enhanced CycleGAN for single image dehazing [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Piscataway : IEEE , 2018 : 938 - 9388 .

但志平 , 方帅领 , 孙航 , 等 . 基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾 [J ] . 电子学报 , 2023 , 51 ( 9 ): 2558 - 2571 .

DAN Z P , FANG S L , SUN H , et al . Outdoor image dehazing based on multi-order channel attention calibration using a dual-discriminator heterogeneous CycleGAN framework [J ] . Acta Electronica Sinica , 2023 , 51 ( 9 ): 2558 - 2571 . (in Chinese)

LIU X H , MA Y R , SHI Z H , et al . GridDehazeNet: Attention-based multi-scale network for image dehazing [C ] // 2019 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2020 : 7313 - 7322 .

QIN X , WANG Z L , BAI Y C , et al . FFA-net: Feature fusion attention network for single image dehazing [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 7 ): 11908 - 11915 .

高继蕊 , 李华锋 , 张亚飞 , 等 . 双注意力引导的细节和结构信息融合图像去雾网络 [J ] . 电子学报 , 2023 , 51 ( 1 ): 160 - 171 .

GAO J R , LI H F , ZHANG Y F , et al . Dual attention-guided detail and structure information fusion network for image dehazing [J ] . Acta Electronica Sinica , 2023 , 51 ( 1 ): 160 - 171 . (in Chinese)

LU L P , XIONG Q , XU B R , et al . MixDehazeNet: Mix structure block for image dehazing network [C ] // 2024 International Joint Conference on Neural Networks . Piscataway : IEEE , 2024 : 1 - 10 .

DONG H , PAN J S , XIANG L , et al . Multi-scale boosted dehazing network with dense feature fusion [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 2154 - 2164 .

LUO P J , XIAO G Q , GAO X B , et al . LKD-net: Large kernel convolution network for single image dehazing [C ] // 2023 IEEE International Conference on Multimedia and Expo . Piscataway : IEEE , 2023 : 1601 - 1606 .

孙航 , 付秋月 , 李勃辉 , 等 . 基于跨层注意力特征交互和多尺度通道注意力的单幅图像去雾网络 [J ] . 电子学报 , 2024 , 52 ( 11 ): 3711 - 3726 .

SUN H , FU Q Y , LI B H , et al . Cross-layer attention feature interaction and multi-scale channel attention network for single image dehazing [J ] . Acta Electronica Sinica , 2024 , 52 ( 11 ): 3711 - 3726 . (in Chinese)

KINGMA D P , BA J L . Adam: A method for stochastic optimization [EB/OL ] . ( 2017-01-30 )[ 2025-06-10 ] . https://arXiv.org/abs/1412.6980 https://arXiv.org/abs/1412.6980 .

LI B Y , REN W Q , FU D P , et al . Benchmarking single image dehazing and beyond [J ] . IEEE Transactions on Image Processing , 2018 , 28 ( 1 ): 492 - 505 .

LIU Y , ZHU L , PEI S D , et al . From synthetic to real: Image dehazing collaborating with unlabeled real data [C ] // Proceedings of the 29th ACM International Conference on Multimedia . New York : ACM , 2021 : 50 - 58 .

BAI H R , PAN J S , XIANG X G , et al . Self-guided image dehazing using progressive feature fusion [J ] . IEEE Transactions on Image Processing , 2022 , 31 : 1217 - 1229 .

SONG Y D , HE Z Q , QIAN H , et al . Vision transformers for single image dehazing [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 1927 - 1941 .

WANG Z Z , ZHAO H T , YAO L J , et al . DFR-net: Density feature refinement network for image dehazing utilizing haze density difference [J ] . IEEE Transactions on Multimedia , 2024 , 26 : 7673 - 7686 .

翟凤文 , 朱玉彤 , 金静 , 等 . 双分支卷积结合细节增强的图像去雾 [J ] . 西北工业大学学报 , 2025 , 43 ( 1 ): 109 - 118 .

ZHAI F W , ZHU Y T , JIN J , et al . Image dehazing based on double branch convolution and detail enhancement [J ] . Journal of Northwestern Polytechnical University , 2025 , 43 ( 1 ): 109 - 118 . (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Dual Attention-Guided Detail and Structure Information Fusion Network for Image Dehazing

Research on Recombination Operator and Multi-Objective Optimization Based on Fitness Guided Mating Restriction Strategy

An RGB-Event Object Tracking Method Based on Geometry Prior Guidance

A Fast Approximate Reasoning Method in Hierarchical DSmT ( B)

Related Author

GAO Ji-rui

LI Hua-feng

ZHANG Ya-fei

XIE Ming-hong

LI Fan

WANG Yu-hong

ZHANG Yi

ZHAO Shaochuan

Related Institution

Yunnan Key Laboratory of Artificial Intelligence

Faculty of Information Engineering and Automation, Kunming University of Science and Technology

School of Mechanical Engineering and Rail Transit , Changzhou University

School of Artificial Intelligence and Computer Science, Jiangnan University

Jiangsu Provincial Industrial Technology Engineering Center for Intelligent Sensing and Emergency IoT in Underground Space

⁰