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

但志平; 方帅领; 孙航; 李晶; 万俊

doi:10.12263/DZXB.20211337

您当前的位置：

首页 >

文章列表页 >

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

学术论文 | 更新时间：2025-12-08

- 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
- Outdoor Image Dehazing Based on Multi-Order Channel Attention Calibration Using a Dual-Discriminator Heterogeneous CycleGAN Framework
- 电子学报 2023年51卷第9期页码：2558-2571
- 作者机构：
  
  1.三峡大学计算机与信息学院,湖北宜昌 443000
  2.三峡大学湖北省水电工程智能视觉监测重点实验室,湖北宜昌 443000
  3.武汉大学计算机学院,湖北武汉 430072
  4.中南财经政法大学信息与安全工程学院,湖北武汉430073
- 作者简介：
  
  但志平男， 1976年3月出生于湖北省咸宁市.现为三峡大学教授，硕士生导师.主要研究方向为计算机视觉、模式识别. E-mail: zp_dan@ctgu.edu.cn
  方帅领　男，1996年1月出生于河南省商丘市.现为三峡大学硕士研究生.主要研究方向为计算机视觉、图像去雾.E-mail: fslcv_110@163.com
  孙航（通讯作者）男， 1986年4月出生于湖北省武汉市.现为三峡大学校聘副教授，硕士生导师.主要研究方向为水下图像修复. E-mail: sunhang0418@whu.edu.cn
- 基金信息：
  
  国家自然科学基金(62002233);湖北省自然科学基金(2021CFB004)
- DOI：10.12263/DZXB.20211337
  中图分类号： TP391.4
- 收稿：2021-09-29，
  
  修回：2022-07-22，
  
  纸质出版：2023-09-25
- 稿件说明：
移动端阅览
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(09):2558-2571.

DAN Zhi-ping,FANG Shuai-ling,SUN Hang,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(09):2558-2571.
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(09):2558-2571. DOI： 10.12263/DZXB.20211337.

DAN Zhi-ping,FANG Shuai-ling,SUN Hang,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(09):2558-2571. DOI： 10.12263/DZXB.20211337.

摘要

图像去雾是计算机视觉领域中一个经典并具有挑战性的研究方向.近年来，基于深度学习的方法在图像去雾领域取得了显著的成绩.然而，大多数去雾算法依赖于合成配对数据训练网络，由于合成数据与真实有雾数据在分布上存在一定的差距，从而限制了这类去雾方法的实际应用.目前基于CycleGAN网络框架的去雾算法将图像去雾视为一般性图像转换问题，忽视了生成器学习的有效性；此外，在恢复图像时缺乏对于局部区域的探索，构建的网络结构中仅采用一阶通道注意力，忽略了深层次通道相关信息的有效利用.为此，本文提出一种基于双判别器异构CycleGAN框架下多阶通道注意力校准的室外图像去雾算法，该方法主要包含双判别器异构循环框架和多阶通道注意力模块.具体来说，双判别器异构CycleGAN框架通过异构批归一化的生成器和约束生成器局部视野的方式，提升算法的收敛效果和增加局部区域关注.为了进一步挖掘对于图像去雾至关重要的特征通道信息，本文通过引入一阶、二阶特征统计量提出了多阶通道注意力模块，从而提升去雾图像的视觉质量.实验结果表明，在公开合成和真实室外数据集上，本文提出的去雾方法相比现有的8种优秀的去雾算法，取得了最好的客观评价指标和视觉效果.

Abstract

Image dehazing is a classic and challenging research direction in the field of computer vision. In recent years

methods based on deep learning have achieved remarkable achievements in image dehazing. However

most existing dehazing algorithms rely on synthetic paired data training network

which limits the practical application of the dehazing methods

due to the discrepancy in the distribution between the synthetic and real-world foggy images. At present

image dehazing algorithms based on the CycleGAN network framework regard image dehazing as general image transformation

ignoring the effectiveness of generator learning. In addition

these algorithms lacks the exploration of local areas in image restoration

and uses only first-order channel attention in the constructed network

ignoring the effective utilization of deep-level channel-related information. Therefore

this paper proposes a dehazing algorithm for outdoor images based on multi-order channel attention calibration using a dual-discriminator heterogeneous CycleGAN framework

which mainly consists of a dual-discriminator heterogeneous cycle framework and multi-order channel attention module. Specifically

the dual-discriminator heterogeneous CycleGAN framework improves the convergence effect of the algorithm and increases the focus of the local area through the batch normalization generator of the heterogeneous CycleGAN and constraining the generator's local field of view. To further explore the feature channel information that is essential for image dehazing

this study employs a multi-order channel attention module by introducing first-order and second-order feature statistics to improve the visual quality of dehazing images. The results of the experiment show that our proposed method outperforms eight state-of-the-art dehazing algorithms on both synthetic and real-world data sets

regarding the extent of objective evaluation and visual quality.

关键词

Keywords

references

XIONG Y Y , LIU H X , GUPTA S , et al . MobileDets: searching for object detection architectures for mobile accelerators [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 3824 - 3833 .

GUO J Z , ZHU X Y , YANG Y , et al . Towards fast, accurate and stable 3D dense face alignment [C]// Computer Vision-ECCV 2020 . Cham : Springer International Publishing , 2020 : 152 - 168 .

LI C S , LIU C , DUAN L X , et al . Reconstruction regularized deep metric learning for multi-label image classification [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 7 ): 2294 - 2303 .

孙航 , 李晶 , 杜博 , 等 . 基于多阶段学习的相关滤波目标跟踪 [J]. 电子学报 , 2017 , 45 ( 10 ): 2337 - 2342 .

SUN H , LI J , DU B , et al . Correlation filtering target tracking based on online multi-lifespan learning [J]. Acta Electronica Sinica , 2017 , 45 ( 10 ): 2337 - 2342 . (in Chinese)

CANTOR A . Optics of the atmosphere: Scattering by molecules and particles [J]. IEEE Journal of Quantum Electronics , 1978 , 14 ( 9 ): 698 - 699 .

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 (CVPR) . Piscataway : IEEE , 2016 : 1674 - 1682 .

ZHU Q S , MAI J M , SHAO L . Single image dehazing using color attenuation prior [C]// 2014 British Machine Vision Conference . Nottingham : BMVA Press , 2014 : 2179 - 2183 .

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 .

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 .

TANG K T , YANG J C , WANG J . Investigating haze-relevant features in a learning framework for image dehazing [C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2014 : 2995 - 3002 .

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 (ICCV) . Piscataway : IEEE , 2017 : 4780 - 4788 .

DONG Y , LIU Y H , ZHANG H , et al . FD-GAN: Generative adversarial networks with fusion-discriminator for single image dehazing [J]. Proceedings of the AAAI Conference on Artificial Intelligence , 2020 , 34 ( 7 ): 10729 - 10736 .

LI R D , PAN J S , HE M , et al . Task-oriented network for image dehazing [J]. IEEE Transactions on Image Processing , 2020 , 29 : 6523 - 6534 .

QU Y Y , CHEN Y Z , HUANG J Y , et al . Enhanced Pix2pix dehazing network [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 8152 - 8160 .

ENGIN D , GENC A , EKENEL H K . Cycle-dehaze: Enhanced cyclegan for single image dehazing [C]// 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshop . Salt Lake City : IEEE , 2018 : 825 - 833 .

SHAO Y J , LI L , REN W Q , et al . Domain adaptation for image dehazing [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 2805 - 2814 .

LIU W , HOU X X , DUAN J , et al . End-to-end single image fog removal using enhanced cycle consistent adversarial networks [J]. IEEE Transactions on Image Processing , 2020 , 29 : 7819 - 7833 .

GOODFELLOW I , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial networks [J]. Communications of the ACM , 2020 , 63 ( 11 ): 139 - 144 .

WANG X , YU K , WU S , et al . ESRGAN: Enhanced super-resolution generative adversarial networks [C]// 2018 European Conference on Computer Vision Workshops . Munich : Springer , 2018 : 63 - 79 .

NI Z K , YANG W H , WANG S Q , et al . Towards unsupervised deep image enhancement with generative adversarial network [J]. IEEE Transactions on Image Processing , 2020 , 29 : 9140 - 9151 .

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 (ICCV) . Piscataway : IEEE , 2017 : 2242 - 2251 .

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

HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 .

LI P H , XIE J T , WANG Q L , et al . Is second-order information helpful for large-scale visual recognition? [C]// 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2017 : 2089 - 2097 .

LI P H , XIE J T , WANG Q L , et al . Towards faster training of global covariance pooling networks by iterative matrix square root normalization [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 947 - 955 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL]. ( 2014-09-04 )[ 2021-09-01 ]. https://arxiv.org/abs/1409.1556 https://arxiv.org/abs/1409.1556 .

LI B Y , REN W Q , FU D P , et al . Benchmarking single-image dehazing and beyond [J]. IEEE Transactions on Image Processing , 2019 , 28 ( 1 ): 492 - 505 .

ZHANG Y F , DING L , SHARMA G . HazeRD: An outdoor scene dataset and benchmark for single image dehazing [C]// 2017 IEEE International Conference on Image Processing (ICIP) . Piscataway : IEEE , 2018 : 3205 - 3209 .

ANCUTI C O , ANCUTI C , TIMOFTE R , et al . O-HAZE: A dehazing benchmark with real hazy and haze-free outdoor images [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway : IEEE , 2018 : 754 - 762 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

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

基于梯度引导偏振度估算的图像去雾

双注意力引导的细节和结构信息融合图像去雾网络

基于超像素图像分割的暗通道先验去雾改进算法