skip to main content
10.1145/3587716.3587786acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicmlcConference Proceedingsconference-collections
research-article

Single Image De-Rain Algorithm Based on Multi-Scale Attention Residual Structure

Published: 07 September 2023 Publication History

Abstract

Rain in nature is affected by wind, gravity, atmospheric refraction, and temperature as it falls. As a result of these factors, rain trails in images often appear to have multiple angles, streaks, and lengths. Currently, available methods are often based on specific assumptions, but this hardly covers all cases in reality. In this paper, we consider rain streaks in images as a kind of noise with a specific pattern and based on this idea we follow the idea of image denoising. In this paper, we propose a new efficient module for rain trace extraction and design a multi-scale fusion attention network that is more suitable for the image de-noising task, obtaining significant improvements in the extraction of rain traces and greatly enhancing the robustness of the model.

References

[1]
Wang H, Xie Q, Zhao Q, A model-driven deep neural network for single image rain removal[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 3103-3112.
[2]
Ye Y, Chang Y, Zhou H, Closing the loop: Joint rain generation and removal via disentangled image translation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 2053-2062.
[3]
Yang W, Tan R T, Feng J, Deep joint rain detection and removal from a single image[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1357-1366.
[4]
Ren D, Zuo W, Hu Q, Progressive image deraining networks: A better and simpler baseline[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 3937-3946.
[5]
K. Jiang, Z. Wang, Y. Peng, C. Chen, B. Huang, Y. Luo, J. Ma, and J. Jiang. Multi-scale progressive fusion network for single image deraining. In IEEE Conference on Computer Vision and Pattern Recognition, pages 8346–8355, 2020.
[6]
Chen C, Li H. Robust representation learning with feedback for single image deraining[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 7742-7751.
[7]
Shao M, Li L, Wang H, Selective generative adversarial network for raindrop removal from a single image[J]. Neurocomputing, 2021, 426: 265-273.
[8]
Fu X, Liang B, Huang Y, Lightweight pyramid networks for image deraining[J]. IEEE transactions on neural networks and learning systems, 2019, 31(6): 1794-1807.
[9]
Woo S, Park J, Lee J Y, Cbam: Convolutional block attention module[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 3-19.
[10]
Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.
[11]
Zhang H, Patel V M. Density-aware single image de-raining using a multi-stream dense network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 695-704.
[12]
He K, Zhang X, Ren S, Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[13]
Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv:1511.07122, 2015.
[14]
Howard A, Sandler M, Chu G, Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314-1324.
[15]
Chen D, He M, Fan Q, Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE winter conference on applications of computer vision (WACV). IEEE, 2019: 1375-1383.
[16]
Wu H, Zheng S, Zhang J, Fast end-to-end trainable guided filter[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 1838-1847.
[17]
T. Wang, X. Yang, K. Xu, S. Chen, Q. Zhang, and R. W. H. Lau. Spatial attentive single-image deraining with a highquality real rain dataset. In IEEE Conference on Computer Vision and Pattern Recognition, pages 12262–12271, 2019.
[18]
Marco Forte and Franc¸ois Piti´e. F, b, alpha matting. CoRR,abs/2003.07711, 2020.
[19]
Qiqi Hou and Feng Liu. Context-aware image matting for simultaneous foreground and alpha estimation, 2019.
[20]
Liu L, Jiang H, He P, On the variance of the adaptive learning rate and beyond[J]. arXiv preprint arXiv:1908.03265, 2019.
[21]
Zhang, He, and Vishal M. Patel. "Density-aware single image de-raining using a multi-stream dense network." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
[22]
X. Fu, J. Huang, D. Zeng, Y. Huang, X. Ding, and J. Paisley. Removing rain from single images via a deep detail network. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1715–1723, 2017.
[23]
Y. Li, R. T. Tan, X. Guo, J. Lu, and M. S. Brown. Rain streak removal using layer priors. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2736–2744, 2016.
[24]
Y. Luo, Y. Xu, and H. Ji. Removing rain from a single image via discriminative sparse coding. In IEEE International Conference on Computer Vision, pages 3397–3405, 2015.

Index Terms

  1. Single Image De-Rain Algorithm Based on Multi-Scale Attention Residual Structure

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICMLC '23: Proceedings of the 2023 15th International Conference on Machine Learning and Computing
    February 2023
    619 pages
    ISBN:9781450398411
    DOI:10.1145/3587716
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 07 September 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Attention mechanisms
    2. Deep residual self-attention network
    3. Image goes to rain
    4. Multi-scale feature extraction

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICMLC 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 22
      Total Downloads
    • Downloads (Last 12 months)10
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 20 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media