从全局到局部:双注意力融合去雾网络

杨瑷玮; 王华珂; 侯兴松

doi:10.7652/xjtuxb202307018

您当前的位置：

首页 >

文章列表页 >

从全局到局部:双注意力融合去雾网络

—————————————————————— | 更新时间：2025-07-09

- 从全局到局部:双注意力融合去雾网络
- From Global to Local: A Dual-Attention Fusion Dehazing Network
- 西安交通大学学报 2023年57卷第7期页码：191-200
- 作者机构：
  
  西安交通大学电子与信息学部,西安,710049
- 作者简介：
  
  : 2022-10-28。作者简介: 杨瑷玮(1996—),男,硕士生
  侯兴松(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(62272376,61872286)
- 基金信息：
  
  : 2022-10-28。作者简介: 杨瑷玮(1996—),男,硕士生;侯兴松(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(62272376,61872286);陕西省重点研发计划资助项目(2020ZDLGY04-05)。
- DOI：10.7652/xjtuxb202307018
  中图分类号： TP391
- 网络首发：2023-07-10，
  
  纸质出版：2023
- 稿件说明：
移动端阅览
杨瑷玮, 王华珂, 侯兴松. 从全局到局部:双注意力融合去雾网络[J]. 西安交通大学学报, 2023,57(7):191-200.

YANG Aiwei, WANG Huake, HOU Xingsong. From Global to Local: A Dual-Attention Fusion Dehazing Network[J]. 2023, 57(7): 191-200.
杨瑷玮, 王华珂, 侯兴松. 从全局到局部:双注意力融合去雾网络[J]. 西安交通大学学报, 2023,57(7):191-200. DOI： 10.7652/xjtuxb202307018.

YANG Aiwei, WANG Huake, HOU Xingsong. From Global to Local: A Dual-Attention Fusion Dehazing Network[J]. 2023, 57(7): 191-200. DOI： 10.7652/xjtuxb202307018.

摘要

为了处理现有的基于卷积神经网络去雾方法只使用单一的注意力、很难生成细节生动的清晰图像

且容易导致色彩失真的问题

提出了一个全局与局部注意力融合的图像去雾方法

以获得正常清晰度和无色彩失真的去雾图像。首先利用通道注意力将输入的有雾图像在通道维度切分为两部分

一部分送入通道像素注意力通道抽取局部特征

另一部分送入Transformer通道学习全局特征

然后利用像素注意力对两个通道学习的特征进行融合

将上述模块作为基本单元组合为一个多级U型去雾网络

增加残差连接缓解上下采样导致的细节信息丢失

最后在网络底层加入一个Transformer模块学习全局信息。在多个公开可用的去雾图像数据集RESIDE SOTS Indoor、RESIDE SOTS Outdoor上测试所提方法的有效性

结果表明:对比经典的去雾方法

所提网络生成的图像细节更丰富并且色彩失真最少; 在RESIDE SOTS Outdoor数据集上

相比经典的FFA-Net

峰值信噪比提高1.16 dB

相比GridDehazeNet

峰值信噪比提高3.68 dB。提出的全局与局部注意力融合方法能有效地去除雾霾

提升图像的对比度与清晰度

设计的多级U型去雾网络和残差连接结构能够缓解细节丢失

提升去雾效果

获得清晰的图像。

Abstract

In terms of the problem that the existing dehazing methods based on the convolution neural network employs attention only from a single perspective

causing difficulties in generating a clear image with vivid details and the propensity to give rise to color distortion

this paper proposes a global and local attention fusion image dehazing network is proposed

in order to obtain a dehazing image with normal definition and no color distortion. The input haze image is first divided into two parts in the channel dimension by using the channel attention. One part is sent into the channel pixel attention channel to extract local features

and the other part is sent into the Transformer channel to learn global features. Then

the pixel attention is used to fuse the features learned by the two channels

and the above modules are combined as basic units into a multi-level U-shaped dehazing network

residual connection is added to alleviate the loss of detail information caused by upper and lower sampling

and finally

a Transformer module is added at the bottom of the network to learn global information. The effectiveness of the method proposed is tested on several publicly available dehazing image data sets including RESIDE SOTS Indoor and RESIDE SOTS Outdoor. The results show that compared with the classical dehazing method

the image generated by the method proposed is more detailed and has the least color distortion. On the RESIDE SOTS Outdoor data set

the PSNR is 1.16dB higher than that of the classical FFA-Net

and 3.68dB higher than that of the GridDehazeNet. The global and local attention fusion method proposed in this paper can effectively remove haze and improve the contrast and clarity of the image; the designed multi-level U-shaped dehazing network and residual connection structure can alleviate the loss of details and improve the dehazing effect

so that clear images are obtained.

关键词

Keywords

references

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

高涛, 刘梦尼, 陈婷, 等. 结合暗亮通道先验的远近景融合去雾算法 [J]. 西安交通大学学报, 2021, 55(10): 78-86.

GAO Tao, LIU Mengni, CHEN Ting, et al. A far and nearscene fusion defogging algorithm based on the prior of dark-light channel [J]. Journal of Xi'an Jiaotong University, 2021, 55(10): 78-86.

CAI Bolun, XU Xiangmin, JIA Kui, et al. DehazeNet: an end-to-end system for single image haze removal [J]. IEEE Transactions on Image Processing, 2016, 25(11): 5187-5198.

杨燕, 陆鑫璇. 结合自适应亮度变换不等式估计透射率的图像去雾方法 [J]. 西安交通大学学报, 2021, 55(6): 69-76.

YANG Yan, LU Xinxuan. An image dehazing method combining adaptive brightness transformation inequality to estimate transmittance [J]. Journal of Xi'an Jiaotong University, 2021, 55(6): 69-76.

LI Boyi, PENG Xiulian, WANG Zhangyang, et al. AOD-net: all-in-one dehazing network [C]//2017 IEEE International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2017: 4780-4788.

HU Jie, SHEN Li, SUN Gang. Squeeze-and-Excitation networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7132-7141.

WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module [C]//Computer Vision-ECCV 2018. Cham, Switzerland: Springer International Publishing, 2018: 3-19.

VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA: Curran Associates Inc., 2017: 6000-6010.

QIN Xu, WANG Zhilin, BAI Yuanchao, et al. FFA-net: feature fusion attention network for single image dehazing [C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2020: 11908-11915.

HU Jie, SHEN Li, SUN Gang. Squeeze-and-Excitation networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 7132-7141.

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

HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2016: 770-778.

LOWE D G. Object recognition from local scale-invariant features [C]//Proceedings of the seventh IEEE international conference on computer vision. Piscataway, NJ, USA: IEEE, 1999: 1150-1157.

LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

LIN Zhouhan, FENG Minwei, DOS SANTOS C N, et al. A structured self-attentive sentence embedding [EB/OL].(2017-10-25).https://arXiv.org/abs/1703.03130.

LIN Min, CHEN Qiang, YAN Shuicheng. Network in network [EB/OL].(2017-10-25). https://arXiv.org/abs/1312.4400.

LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: hierarchical vision transformer using shifted windows [C]//2021 IEEE/CVF International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2021: 9992-10002.

LI Boyi, REN Wenqi, FU Dengpan, et al. Benchmarking single-image dehazing and beyond [J]. IEEE Transactions on Image Processing, 2019, 28(1): 492-505.

LOSHCHILOV I, HUTTER F. SGDR: stochastic gradient descent with warm restarts [EB/OL]. [2022-10-10]. https://arxiv.org/abs/1608.03983.

WELSTEAD S T. Fractal and wavelet image compression techniques [M]. Bellingham, WA, USA: SPIE Optical Engineering Press, 1999.

WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

JI Haobo, FENG Xin, PEI Wenjie, et al. U2-Former: a nested U-shaped transformer for image restoration [EB/OL]. [2022-10-10]. https://arXiv.org/abs/2112.02279.

WANG Zhendong, CUN Xiaodong, BAO Jianmin, et al. Uformer: a general U-shaped transformer for image restoration [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2022: 17662-17672.

LIU Xiaohong, MA Yongrui, SHI Zhihao, et al. GridDehazeNet: attention-based multi-scale network for image dehazing [C]//2019 IEEE/CVF International Conference on Computer Vision. Piscataway, NJ, USA: IEEE, 2019: 7313-7322.

LIU Zheng, XIAO Botao, ALRABEIAH M, et al. Generic model-agnostic convolutional neural network for single image dehazing [EB/OL].(2019-11-29). https://arXiv.org/abs/1810.02862.

GOLTS A, FREEDMAN D, ELAD M. Unsupervised single image dehazing using dark channel prior loss [J]. IEEE Transactions on Image Processing, 2019, 29: 2692-2701.

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

结合自适应亮度变换不等式估计透射率的图像去雾方法

采用对比学习的多阶段Transformer图像去雾方法

电子级超纯氮深冷空分流程节能优化研究

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究