政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/147030
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 113325/144300 (79%)
造訪人次 : 51163863      線上人數 : 911
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋
    政大機構典藏 > 資訊學院 > 資訊科學系 > 學位論文 >  Item 140.119/147030


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/147030


    題名: 自監督式學習的單張影像除雨技術
    Self-supervised Single Image Deraining
    作者: 李偉華
    Li, Wei-Hua
    貢獻者: 彭彥璁
    Peng, Yan-Tsung
    李偉華
    Li, Wei-Hua
    關鍵詞: 影像處理
    影像除雨
    自監督式學習
    Image processing
    Image deraining
    Self-supervised learning
    日期: 2023
    上傳時間: 2023-09-01 15:23:59 (UTC+8)
    摘要: 單一影像除雨 (Single Image Deraining) 的任務目標在於去除單一影 像中的雨紋，該領域近年來引起了許多關注。近期在這個主題的研 究，主要集中在深度學習中的監督式學習方法上，該方法使用下雨場 景影像與其相對應的乾淨影像來訓練模型。然而，收集成對影像的工 作相當花費時間與人力成本。因此，我們提出了 Rain2Avoid (R2A)， 一個只需要一張下雨場景影像就可以除雨的自監督式學習模型。
    我們也提出一個參考局部影像梯度來預測潛在雨紋的模組，在自監 督的訓練過程中我們會略過雨紋像素，參考區域相似的像素來產生較 乾淨的背景影像，並直接對輸入下雨影像進行自監督式訓練。可以預 期的是自監督式的 R2A 表現可能不如有使用乾淨影像作為參考的監 督式學習模型。但是當訓練的成對影像是無法取得時，R2A 就會有優 勢，R2A 可以只使用一張下雨場景影像進行自監督學習。實驗結果顯 示，我們所提出的方法表現得比最先進的小樣本除雨和自監督降噪方 法還要良好。
    It is common to take pictures outside; however, the weather may not be good. If we shoot the picture on a rainy day, we might capture rain streaks in the image. Image deraining is one of the image processing tasks, trying to remove the rain streaks on the image. Most works in these years apply a supervised image-deraining method, which relies on rainy-clean image pairs to train. However, collecting such pairwise images is strenuous and time- consuming. Therefore, some works generated synthetic rainy images, making it easier to get lots of pairwise images. However, using synthetic images to train a deraining model may not work well on real rainy images.
    We present a novel self-supervised method based on locally dominant gra- dient prior (LDGP) and non-local self-similarity stochastic sampling (NSSS) which can respectively extract the potential rain streak and generate the stochas- tic derain reference. With the help of LDGP and NSSS, we can self-supervise only one single image for image deraining. Extensive experiments on syn- thetic and real image datasets validate the potential of our self-supervised image-deraining method.
    參考文獻: [1] Yunhao Ba, Howard Zhang, Ethan Yang, Akira Suzuki, Arnold Pfahnl, Chethan Chinder Chandrappa, Celso M de Melo, Suya You, Stefano Soatto, Alex Wong, et al. Not just streaks: Towards ground truth for single image deraining. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VII, pages 723–740. Springer, 2022.
    [2] Joshua Batson and Loic Royer. Noise2self: Blind denoising by self-supervision. In Proc. Int’l Conf. Machine Learning. PMLR, 2019.
    [3] Xiang Chen, Hao Li, Mingqiang Li, and Jinshan Pan. Learning a sparse transformer network for effective image deraining. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5896–5905, 2023.
    [4] Xiang Chen, Jinshan Pan, Kui Jiang, Yufeng Li, Yufeng Huang, Caihua Kong, Longgang Dai, and Zhentao Fan. Unpaired deep image deraining using dual contrastive learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2017–2026, 2022.
    [5] Yi-Lei Chen and Chiou-Ting Hsu. A generalized low-rank appearance model for spatio-temporally correlated rain streaks. In Proc. Conf. Computer Vision and Pattern Recognition, 2013.
    [6] Liang-Jian Deng, Ting-Zhu Huang, Xi-Le Zhao, and Tai-Xiang Jiang. A directional 53 global sparse model for single image rain removal. Applied Mathematical Modelling, 2018.
    [7] David Eigen, Dilip Krishnan, and Rob Fergus. Restoring an image taken through a window covered with dirt or rain. In Proc. Int’l Conf. Computer Vision, 2013.
    [8] Kshitiz Garg and Shree K Nayar. Photorealistic rendering of rain streaks. ACM Transactions on Graphics (TOG), 2006.
    [9] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proc. Conf. Computer Vision and Pattern Recognition, 2016.
    [10] Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017.
    [11] Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, and Jianzhuang Liu. Neighbor2neighbor: Self-supervised denoising from single noisy images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14781–14790, 2021.
    [12] Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, and Junjun Jiang. Multi-scale progressive fusion network for single image deraining. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8346–8355, 2020.
    [13] Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, and Yao Wang. Fastderain: A novel video rain streak removal method using directional gradient priors. IEEE Trans. on Image Processing, 2018. 54
    [14] Alexander Krull, Tim-Oliver Buchholz, and Florian Jug. Noise2void-learning denoising from single noisy images. In Proc. Conf. Computer Vision and Pattern Recognition, 2019.
    [15] Wooseok Lee, Sanghyun Son, and Kyoung Mu Lee. Ap-bsn: Self-supervised denoising for real-world images via asymmetric pd and blind-spot network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17725–17734, 2022.
    [16] Junyi Li, Zhilu Zhang, Xiaoyu Liu, Chaoyu Feng, Xiaotao Wang, Lei Lei, and Wangmeng Zuo. Spatially adaptive self-supervised learning for real-world image denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9914–9924, 2023.
    [17] Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, and Hongbin Zha. Recurrent squeeze-and-excitation context aggregation net for single image deraining. In Proceedings of the European conference on computer vision (ECCV), pages 254–269, 2018.
    [18] Yizhou Li, Yusuke Monno, and Masatoshi Okutomi. Single image deraining network with rain embedding consistency and layered lstm. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 4060–4069, 2022.
    [19] Yu Li, Robby T Tan, Xiaojie Guo, Jiangbo Lu, and Michael S Brown. Rain streak removal using layer priors. In Proc. Conf. Computer Vision and Pattern Recognition, 2016.
    [20] Yu Luo, Yong Xu, and Hui Ji. Removing rain from a single image via discriminative sparse coding. In Proc. Int’l Conf. Computer Vision, 2015. 55
    [21] David Martin, Charless Fowlkes, Doron Tal, and Jitendra Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. Int’l Conf. Computer Vision, 2001.
    [22] Anish Mittal, Anush Krishna Moorthy, and Alan Conrad Bovik. No-reference image quality assessment in the spatial domain. IEEE Trans. on Image Processing, 2012.
    [23] Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. Making a “completely blind”image quality analyzer. IEEE Signal processing letters, 2012.
    [24] Yan-Tsung Peng and Wei-Hua Li. Rain2avoid: Self-supervised single image deraining. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE, 2023.
    [25] Shyam Nandan Rai, Rohit Saluja, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, and CV Jawahar. Fluid: Few-shot self-supervised image deraining. In Proc. of the IEEE/CVF Winter Conf. on Applications of Computer Vision, 2022.
    [26] Dongwei Ren, Wangmeng Zuo, Qinghua Hu, Pengfei Zhu, and Deyu Meng. Progressive image deraining networks: A better and simpler baseline. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3937–3946, 2019.
    [27] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015. 56
    [28] Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. Deep image prior. In CVPR, pages 9446–9454, 2018.
    [29] Hong Wang, Qi Xie, Qian Zhao, Yuexiang Li, Yong Liang, Yefeng Zheng, and Deyu Meng. Rcdnet: An interpretable rain convolutional dictionary network for single image deraining. arXiv preprint arXiv:2107.06808, 2021.
    [30] Yinglong Wang, Shuaicheng Liu, Chen Chen, and Bing Zeng. A hierarchical approach for rain or snow removing in a single color image. IEEE Trans. on Image Processing, 2017.
    [31] Zejin Wang, Jiazheng Liu, Guoqing Li, and Hua Han. Blind2unblind: Self-supervised image denoising with visible blind spots. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2027–2036, 2022.
    [32] Zichun Wang, Ying Fu, Ji Liu, and Yulun Zhang. Lg-bpn: Local and global blind-patch network for self-supervised real-world denoising. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18156–18165, 2023.
    [33] Wei Wei, Deyu Meng, Qian Zhao, Zongben Xu, and Ying Wu. Semi-supervised transfer learning for image rain removal. In Proc. Conf. Computer Vision and Pattern Recognition, 2019.
    [34] Wenhan Yang, Robby T Tan, Jiashi Feng, Jiaying Liu, Zongming Guo, and Shuicheng Yan. Deep joint rain detection and removal from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1357–1366, 2017. 57
    [35] Rajeev Yasarla, Vishwanath A Sindagi, and Vishal M Patel. Syn2real transfer learning for image deraining using gaussian processes. In Proc. Conf. Computer Vision and Pattern Recognition, 2020.
    [36] Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. Restormer: Efficient transformer for high-resolution image restoration. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5728–5739, 2022.
    [37] Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Shao. Multi-stage progressive image restoration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14821–14831, 2021.
    [38] Dan Zhang, Fangfang Zhou, Yuwen Jiang, and Zhengming Fu. Mm-bsn: Self-supervised image denoising for real-world with multi-mask based on blind-spot network. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4188–4197, 2023.
    [39] He Zhang, Vishwanath Sindagi, and Vishal M Patel. Image de-raining using a conditional generative adversarial network. IEEE transactions on circuits and systems for video technology, 2019.
    [40] Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE transactions on image processing, 26(7):3142–3155, 2017.
    [41] Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In Proc. Conf. Computer Vision and Pattern Recognition, 2018
    描述: 碩士
    國立政治大學
    資訊科學系
    110753106
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0110753106
    資料類型: thesis
    顯示於類別:[資訊科學系] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    310601.pdf41740KbAdobe PDF2113檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋