Four-path unsupervised learning-based image defogging network

Wei LIU; Cheng CHEN; Rui JIANG; Tao LU

doi:10.11959/j.issn.1000-436x.2022201

您当前的位置：

首页 >

文章列表页 >

Four-path unsupervised learning-based image defogging network

Correspondences | 更新时间：2024-06-05

- Four-path unsupervised learning-based image defogging network
- Journal on Communications Vol. 43, Issue 10, Pages: 210-222(2022)
- 作者机构：
  
  1. 武汉工程大学计算机科学与工程学院，湖北武汉 430205
  2. 武汉工程大学智能机器人湖北省重点实验室，湖北武汉 430205
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(62001334);The National Natural Science Foundation of China(62072350);Technology Innovation and Development Project of Supports Enterprise of Hubei Province(2021BLB172)
- DOI：10.11959/j.issn.1000-436x.2022201
  CLC： TP391.41
- Online First：2022-10，
  
  Published：25 October 2022
- 稿件说明：
移动端阅览
Wei LIU, Cheng CHEN, Rui JIANG, et al. Four-path unsupervised learning-based image defogging network[J]. Journal on Communications, 2022, 43(10): 210-222.
DOI：

Wei LIU, Cheng CHEN, Rui JIANG, et al. Four-path unsupervised learning-based image defogging network[J]. Journal on Communications, 2022, 43(10): 210-222. DOI： 10.11959/j.issn.1000-436x.2022201.

摘要

摘要：为了解决单幅图像去雾领域有监督网络和无监督网络分别存在的问题，基于循环生成对抗网络（CycleGAN），提出了一种四通道无监督学习图像去雾网络。所提模型主要包括3个子网络，即去雾网络、合成雾网络和注意力特征融合网络；并由此3个子网络顺序组合构建了4条学习通道，即去雾通道、去雾结果颜色-纹理恢复通道、合成雾通道以及合成雾结果颜色-纹理恢复通道。特别地，在合成雾网络中，为了更好地约束去雾网络生成更高质量的无雾图像，引入了大气散射模型（ASM）以加强网络从有雾图像域到无雾图像域的映射转换；同时，为了进一步提高去雾网络和合成雾网络的图像生成质量，提出了一种注意力特征融合网络，该网络基于雾相关派生图，采用多路映射结构和注意力机制，加强对生成图像颜色、纹理细节等信息的恢复。在合成雾和真实雾图数据集上的大量实验结果表明，所提方法能更好地恢复各类场景中雾图的颜色和纹理细节等信息。

Abstract

To solve the problems of supervised network and unsupervised network in the field of single image defogging

a four-path unsupervised learning-based image defogging network based on cycle generative adversarial network (CycleGAN) was proposed

which mainly included three sub-networks: defogging network

synthetic fog network and attention feature fusion network.The three sub-networks were sequentially combined to construct four learning paths

which were the defogging path

the color-texture recovery path for defogged result

the synthetic fog path

and the color-texture recovery path for synthetic fog result.Specifically

in the synthetic fog network

to better constrain the defogging network to generate higher quality fogfree images

the atmospheric scattering model (ASM)was introduced to enhance the mapping transformation of the network from the foggy image domain to the fogfree image domain.Furthermore

to further improve the image generation quality of the defogging network and the synthetic fog network

an attention feature fusion network was proposed.The proposed network was based on several fog-derived images

which adopts a multi-channel mapping structure and an attention mechanism to enhance the recovery of color and texture details.Extensive experiments on both synthetic and real-world datasets show that the proposed method can better restore the color and texture details information of foggy images in various scenes.

关键词

Keywords

references

LAND E H . The Retinex [J ] . American Scientist , 1964 , 52 ( 2 ): 247 - 264 .

黄黎红 . 一种基于单尺度 Retinex 的雾天降质图像增强新算法 [J ] . 应用光学 , 2010 , 31 ( 5 ): 728 - 733 .

HUANG L H . Fog-degraded image enhancement based on single-scale Retinex [J ] . Journal of Applied Optics , 2010 , 31 ( 5 ): 728 - 733 .

YU T H , MENG X , ZHU M , et al . An improved multi-scale Retinex fog and haze image enhancement method [C ] // Proceedings of 2016 International Conference on Information System and Artificial Intelligence . Piscataway:IEEE Press , 2016 : 557 - 560 .

JOBSON D J , RAHMAN Z , WOODELL G A . A multiscale Retinex for bridging the gap between color images and the human observation of scenes [J ] . IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society , 1997 , 6 ( 7 ): 965 - 976 .

李竹林 , 车雯雯 , 钱梦杭 , 等 . 一种改进的直方图均衡化图像去雾算法 [J ] . 河南科学 , 2021 , 39 ( 1 ): 1 - 6 .

LI Z L , CHE W W , QIAN M H , et al . An improved image defogging algorithm based on histogram equalization [J ] . Henan Science , 2021 , 39 ( 1 ): 1 - 6 .

XU Z Y , LIU X M , CHEN X N . Fog removal from video sequences using contrast limited adaptive histogram equalization [C ] // Proceedings of International Conference on Computational Intelligence and Software Engineering . Piscataway:IEEE Press , 2009 : 1 - 4 .

MCCARTNEY E J . Optics of the atmosphere:scattering by molecules and particles [M ] . New York : Wiley , 1976 .

TAREL J P , HAUTIÈRE N ,, . Fast visibility restoration from a single color or gray level image [C ] // Proceedings of IEEE 12th International Conference on Computer Vision . Piscataway:IEEE Press , 2009 : 2201 - 2208 .

HE K M , SUN J , TANG X O . Single image haze removal using dark channel prior [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2011 , 33 ( 12 ): 2341 - 2353 .

JU M Y , DING C , REN W Q , et al . IDE:image dehazing and exposure using an enhanced atmospheric scattering model [J ] . IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society , 2021 , 30 : 2180 - 2192 .

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:a Publication of the IEEE Signal Processing Society , 2016 , 25 ( 11 ): 5187 - 5198 .

REN W Q , LIU S , ZHANG H , et al . Single image dehazing via multi-scale convolutional neural networks [C ] // Proceedings of European Conference on Computer Vision . Berlin:Springer , 2016 : 154 - 169 .

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

ANCUTI C O , ANCUTI C , BEKAERT P . Effective single image dehazing by fusion [C ] // Proceedings of IEEE International Conference on Image Processing . Piscataway:IEEE Press , 2010 : 3541 - 3544 .

ANCUTI C O , ANCUTI C . Single image dehazing by multi-scale fusion [J ] . IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society , 2013 , 22 ( 8 ): 3271 - 3282 .

REN W Q , MA L , ZHANG J W , et al . Gated fusion network for single image dehazing [C ] // Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2018 : 3253 - 3261 .

郭璠 , 唐琎 , 蔡自兴 . 基于融合策略的单幅图像去雾算法 [J ] . 通信学报 , 2014 , 35 ( 7 ): 199 - 207 , 214 .

GUO F , TANG J , CAI Z X . Single image defogging based on fusion strategy [J ] . Journal on Communications , 2014 , 35 ( 7 ): 199 - 207 , 214 .

LI B Y , GOU Y B , LIU J Z , et al . Zero-shot image dehazing [J ] . IEEE Transactions on Image Processing , 2020 , 29 : 8457 - 8466 .

LI B Y , GOU Y B , GU S H , et al . You only look yourself:unsupervised and untrained single image dehazing neural network [J ] . International Journal of Computer Vision , 2021 , 129 ( 5 ): 1754 - 1767 .

ENGIN D , GENC A , EKENEL H K . Cycle-dehaze:enhanced CycleGAN for single image Dehazing [C ] // Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway:IEEE Press , 2018 : 938 - 9388 .

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

YANG Y , WANG C Y , LIU R S , et al . Self-augmented unpaired image dehazing via density and depth decomposition [C ] // Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway:IEEE Press , 2022 : 2027 - 2036 .

GOODFELLOW I , POUGET-ABADIE J ,, MIRZA M , et al . Generative adversarial nets [C ] // Proceedings of Advances in Neural Information Processing Systems . Massachusetts:MIT Press , 2014 :27.

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

LI R D , PAN J S , LI Z C , et al . Single image dehazing via conditional generative adversarial network [C ] // Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2018 : 8202 - 8211 .

肖进胜 , 申梦瑶 , 雷俊锋 , 等 . 基于生成对抗网络的雾霾场景图像转换算法 [J ] . 计算机学报 , 2020 , 43 ( 1 ): 165 - 176 .

XIAO J S , SHEN M Y , LEI J F , et al . Image conversion algorithm for haze scene based on generative adversarial networks [J ] . Chinese Journal of Computers , 2020 , 43 ( 1 ): 165 - 176 .

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

DAI T , CAI J R , ZHANG Y B , et al . Second-order attention network for single image super-resolution [C ] // Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway:IEEE Press , 2019 : 11057 - 11066 .

DENG Z J , ZHU L , HU X W , et al . Deep multi-model fusion for single-image dehazing [C ] // Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway:IEEE Press , 2019 : 2453 - 2462 .

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 .

HUANG G , LIU Z , VAN DER MAATEN L , et al . Densely connected convolutional networks [C ] // Proceedings of IEEE Conference on Computer Vision and Pattern Recognition . Piscataway:IEEE Press , 2017 : 2261 - 2269 .

CHOI L K , YOU J , BOVIK A C . Referenceless prediction of perceptual fog density and perceptual image defogging [J ] . IEEE Transactions on Image Processing:a Publication of the IEEE Signal Processing Society , 2015 , 24 ( 11 ): 3888 - 3901 .

MITTAL A , SOUNDARARAJAN R , BOVIK A C . Making a “com pletely blind” image quality analyzer [J ] . IEEE Signal Processing Letters , 2013 , 20 ( 3 ): 209 - 212 .

CHEN D D , HE M M , FAN Q N , et al . Gated context aggregation network for image dehazing and deraining [C ] // Proceedings of IEEE Winter Conference on Applications of Computer Vision . Piscataway:IEEE Press , 2019 : 1375 - 1383 .

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

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

ZHANG Y F , DING L , SHARMA G . HazeRD:an outdoor scene dataset and benchmark for single image dehazing [C ] // Proceedings of IEEE International Conference on Image Processing . Piscataway:IEEE Press , 2017 : 3205 - 3209 .

Views

1937

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Review of unsupervised anomaly detection techniques for medical imaging

Variational autoencoder-based multipath clustering algorithm for terahertz channels

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction

Review on autoencoder and its application

Image restoration algorithm based on compensated transmission and adaptive haze concentration coefficient

Related Author

Hei Xinhong

You Zhenzhen

Shi Zhenghao

Song Xiaogang

Zhao Yingcheng

LIAO Xi

ZHANG Jie

CHEN Qianbin

Related Institution

School of Computer Science and Engineering, Xi’an University of Technology

Shaanxi Key Laboratory for Network Computing and Security Technology

Human Machine Integration Intelligent Robot Shaanxi Provincial University Engineering Research Center

School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications

PLA Unit

AI问答

⁰