1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 基於強化學習的影像除雨技術
Reinforcement-learning-based Image Deraining
作者 廖禾豪
Liao, He-Hao
貢獻者 彭彥璁
Peng, Yan-Tsung
廖禾豪
Liao, He-Hao
關鍵詞 自監督式學習
強化學習
影像除雨
Self-Supervised Learning
Reinforcement Learning
Image deraining
日期 2024
上傳時間 1-Mar-2024 13:41:42 (UTC+8)
摘要 戶外拍攝的影像品質經常受到天氣的影響。影響視覺的其中一個因素是影像中的雨紋，它可能阻礙觀察者以及依賴這些影像的電腦視覺應用的視線。本研究旨在通過自監督強化學習（RL）進行影像去雨任務（SRL-Derain）來還原雨天影像。我們通過字典學習從輸入的雨天影像中找到雨紋像素，並使用像素級的強化學習代理進行多次修補(inpainting)操作，逐步去除雨紋。據我們所知，這是首次將自監督強化學習應用於影像去雨的嘗試。來自各種基準影像去雨數據集的實驗結果表明，所提出的方法 SRL-Derain 在與最先進的自監督影像降噪、少量樣本和自監督影像去雨方法相比表現更優。
The quality of images captured outdoors is often affected by the weather. One factor that interferes with sight is rain, which can obstruct the view of observers and computer vision applications that rely on those images. The work aims to recover rain images by removing rain streaks via Self-supervised Reinforcement Learning (RL) for image deraining (SRL-Derain). We locate rain streak pixels from the input rain image via dictionary learning and use pixel-wise RL agents to take multiple inpainting actions to remove rain progressively. To our best knowledge, this work is the first attempt where self-supervised RL is applied to image draining. Experimental results from various benchmark image-deraining datasets demonstrate that the proposed SRL-Derain exhibits superior performance compared to state-of-the-art self-supervised image denoising, few-shot and self-supervised image deraining methods.
參考文獻 [1] Pablo Arbelaez, Michael Maire, Charless Fowlkes, and Jitendra Malik. Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence, 33(5):898–916, 2010. [2] 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 European Conference on Computer Vision, pages 723–740. Springer, 2022. [3] Joshua Batson and Loic Royer. Noise2self: Blind denoising by self-supervision. In Proc. Int’l Conf. Machine Learning, 2019. [4] NavneetDalalandBillTriggs.Histogramsoforientedgradientsforhumandetection. In Proc. Conf. Computer Vision and Pattern Recognition, 2005. [5] Liang-Jian Deng, Ting-Zhu Huang, Xi-Le Zhao, and Tai-Xiang Jiang. A directional global sparse model for single image rain removal. Applied Mathematical Modelling, 2018. [6] Sen Deng, Mingqiang Wei, Jun Wang, Yidan Feng, Luming Liang, Haoran Xie, Fu Lee Wang, and Meng Wang. Detail-recovery image deraining via context aggregation networks. In Proc. Conf. Computer Vision and Pattern Recognition, 2020. [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] Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, and John Paisley. Clearing the skies: A deep network architecture for single-image rain removal. IEEE Transactions on Image Processing, 26(6):2944–2956, 2017. [9] RyosukeFuruta,NaotoInoue,andToshihikoYamasaki.Fully convolutional network with multi-step reinforcement learning for image processing. In Proc. Nat’l Conf. Artificial Intelligence, 2019. [10] Kshitiz Garg and Shree K Nayar. Photorealistic rendering of rain streaks. ACM Transactions on Graphics (TOG), 25(3):996–1002, 2006. [11] Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Christopher Burgess, Alexan- der Pritzel, Matthew Botvinick, Charles Blundell, and Alexander Lerchner. Darla: Improving zero-shot transfer in reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2017. [12] Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, and Jianzhuang Liu. Neigh- bor2neighbor: Self-supervised denoising from single noisy images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14781–14790, 2021. [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. [14] Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, and Wei Zhou. Unsupervised single image deraining with self-supervised constraints. In Proc. Int’l Conf. Image Processing, 2019. [15] Li-WeiKang,Chia-WenLin,andYu-HsiangFu.Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans. on Image Processing, 2011. [16] Alexander Krull, Tim-Oliver Buchholz, and Florian Jug. Noise2void-learning de-noising from single noisy images. In Proc. Conf. Computer Vision and Pattern Recognition, 2019. [17] Michael Laskin, Aravind Srinivas, and Pieter Abbeel. CURL: Contrastive unsupervised representations for reinforcement learning. In Proc. Int’l Conf. Machine Learning, pages 5639–5650, 2020. [18] Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee, John Canny, and Sergio Guadarrama. Predictive information accelerates learning in RL. Proc. Neural Information Processing Systems, 2020. [19] WooseokLee, SanghyunSon,andKyoungMuLee.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. [20] Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Mi- ika Aittala, and Timo Aila. Noise2noise: Learning image restoration without clean data. arXiv preprint arXiv:1803.04189, 2018. [21] Debang Li, Huikai Wu, Junge Zhang, and Kaiqi Huang. A2-rl: Aesthetics aware reinforcement learning for image cropping. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8193–8201, 2018. [22] JunyiLi,ZhiluZhang,XiaoyuLiu,ChaoyuFeng,XiaotaoWang,LeiLei,andWang- meng 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. [23] Xiang Li, Jinghuan Shang, Srijan Das, and Michael Ryoo. Does self-supervised learning really improve reinforcement learning from pixels? Proc. Neural Information Processing Systems, 2022. [24] 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. [25] 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. [26] Julien Mairal, Francis Bach, Jean Ponce, and Guillermo Sapiro. Online learning for matrix factorization and sparse coding. Journal of Machine Learning Research, 2010. [27] 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 Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, volume 2, pages 416–423. IEEE, 2001. [28] AnishMittal,AnushKrishnaMoorthy,andAlanConradBovik.No-reference image quality assessment in the spatial domain. IEEE Trans. on Image Processing, 2012. [29] Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. Making a “completely blind” image quality analyzer. Signal Processing Letters, 2012. [30] Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2016. [31] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013. [32] Ofir Nachum, Mohammad Norouzi, Kelvin Xu, and Dale Schuurmans. Bridging the gap between value and policy based reinforcement learning. Proc. Neural Information Processing Systems, 2017. [33] Ashvin V Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, and Sergey Levine. Visual reinforcement learning with imagined goals. Proc. Neural Information Processing Systems, 2018. [34] Jongchan Park, Joon-Young Lee, Donggeun Yoo, and In So Kweon. Distort-and-recover: Color enhancement using deep reinforcement learning. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018. [35] Yan-Tsung Peng and Wei-Hua Li. Rain2avoid: Self-supervised single image derain- ing. In Proc. Int’l Conf. Acoustics, Speech, and Signal Processing, 2023. [36] Shyam Nandan Rai, Rohit Saluja, Chetan Arora, Vineeth N Balasubramanian, An- bumani 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. [37] Gerald Schaefer and Michal Stich. Ucid: An uncompressed color image database. In Storage and retrieval methods and applications for multimedia 2004, volume 5307, pages 472–480. SPIE, 2003. [38] John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. Trust region policy optimization. In Proc. Int’l Conf. Machine Learning, 2015. [39] Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, and Philip Bachman. Data-efficient reinforcement learning with self-predictive representations. In Proc. Int’l Conf. Learning Representations, 2021. [40] RamananSekar,OlehRybkin,KostasDaniilidis,PieterAbbeel,DanijarHafner,and Deepak Pathak. Planning to explore via self-supervised world models. In Proc. Int’l Conf. Machine Learning, 2020. [41] EvanShelhamer,ParsaMahmoudieh,MaxArgus,andTrevorDarrell.Lossisitsown reward: Self-supervision for reinforcement learning. In International Conference on Learning Representations Workshop, 2017. [42] AdamStooke,KiminLee,PieterAbbeel,andMichaelLaskin.Decoupling representation learning from reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2021. [43] Seiya Tokui, Ryosuke Okuta, Takuya Akiba, Yusuke Niitani, Toru Ogawa, Shunta Saito, Shuji Suzuki, Kota Uenishi, Brian Vogel, and Hiroyuki Yamazaki Vincent. Chainer: A deep learning framework for accelerating the research cycle. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019. [44] Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. Deep image prior. In Proc. Conf. Computer Vision and Pattern Recognition, 2018. [45] 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. [46] 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. [47] 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. [48] 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. [49] Wei Wei, Lixuan Yi, Qi Xie, Qian Zhao, Deyu Meng, and Zongben Xu. Should we encode rain streaks in video as deterministic or stochastic? In Proceedings of the IEEE International Conference on Computer Vision, pages 2516–2525, 2017. [50] YanyanWei,ZhaoZhang,YangWang,MingliangXu,YiYang,ShuichengYan,and Meng Wang. Deraincyclegan: Rain attentive cyclegan for single image deraining and rainmaking. IEEE Trans. on Image Processing, 2021. [51] 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 Proc. Conf. Computer Vision and Pattern Recognition, 2017. [52] Denis Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos, Joelle Pineau, and Rob Fergus. Improving sample efficiency in model-free reinforcement learning from images. In Proc. Nat’l Conf. Artificial Intelligence, 2021. [53] KeYu,ChaoDong,LiangLin,andChenChangeLoy.Craftingatoolchainforimage restoration by deep reinforcement learning. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018. [54] Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Shao. Multi-stage progressive image restoration. In Proc. Conf. Computer Vision and Pattern Recognition, 2021. [55] 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. [56] He Zhang, Vishwanath Sindagi, and Vishal M Patel. Image de-raining using a conditional generative adversarial network. IEEE Trans. on Circuits and Systems for Video Technology, 2019. [57] Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018. [58] Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng, Wengang Zhou, Tao Qin, Tie-Yan Liu, and Houqiang Li. Masked contrastive representation learning for reinforcement learning. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2023.
描述 碩士
國立政治大學
資訊科學系
110753115
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110753115
資料類型 thesis
dc.contributor.advisor 彭彥璁zh_TW
dc.contributor.advisor Peng, Yan-Tsungen_US
dc.contributor.author (Authors) 廖禾豪zh_TW
dc.contributor.author (Authors) Liao, He-Haoen_US
dc.creator (作者) 廖禾豪zh_TW
dc.creator (作者) Liao, He-Haoen_US
dc.date (日期) 2024en_US
dc.date.accessioned 1-Mar-2024 13:41:42 (UTC+8)-
dc.date.available 1-Mar-2024 13:41:42 (UTC+8)-
dc.date.issued (上傳時間) 1-Mar-2024 13:41:42 (UTC+8)-
dc.identifier (Other Identifiers) G0110753115en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/150168-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學系zh_TW
dc.description (描述) 110753115zh_TW
dc.description.abstract (摘要) 戶外拍攝的影像品質經常受到天氣的影響。影響視覺的其中一個因素是影像中的雨紋，它可能阻礙觀察者以及依賴這些影像的電腦視覺應用的視線。本研究旨在通過自監督強化學習（RL）進行影像去雨任務（SRL-Derain）來還原雨天影像。我們通過字典學習從輸入的雨天影像中找到雨紋像素，並使用像素級的強化學習代理進行多次修補(inpainting)操作，逐步去除雨紋。據我們所知，這是首次將自監督強化學習應用於影像去雨的嘗試。來自各種基準影像去雨數據集的實驗結果表明，所提出的方法 SRL-Derain 在與最先進的自監督影像降噪、少量樣本和自監督影像去雨方法相比表現更優。zh_TW
dc.description.abstract (摘要) The quality of images captured outdoors is often affected by the weather. One factor that interferes with sight is rain, which can obstruct the view of observers and computer vision applications that rely on those images. The work aims to recover rain images by removing rain streaks via Self-supervised Reinforcement Learning (RL) for image deraining (SRL-Derain). We locate rain streak pixels from the input rain image via dictionary learning and use pixel-wise RL agents to take multiple inpainting actions to remove rain progressively. To our best knowledge, this work is the first attempt where self-supervised RL is applied to image draining. Experimental results from various benchmark image-deraining datasets demonstrate that the proposed SRL-Derain exhibits superior performance compared to state-of-the-art self-supervised image denoising, few-shot and self-supervised image deraining methods.en_US
dc.description.tableofcontents 第一章 Introduction 1 第一節 Motivation 1 第二節 Contributions 4 第三節 Thesis Structure 5 第二章 Related Work 6 第一節 Traditional Image Deraining 7 第二節 Self-Supervised Image Restoration 7 第一小節 Self-Supervised Learning for Image Denoising 7 第二小節 Self-Supervised Learning for Image Deraining 14 第三節 Reinforcement-Learning-Based Image Restoration 17 第三章 Methodology 20 第一節 Generation of Rain Mask 20 第一小節 Rain Dictionary Prior(RDP) 21 第二小節 Additional Rain Pixel Sampling 22 第二節 Pseudo-Derained Reference Generation 24 第三節 RL-Based Self-Supervised Deraining Scheme 25 第一小節 Reinforcement Learning Algorithm 25 第二小節 Self-Supervised Reward Predictor 26 第三小節 Rewards of RL-agent 29 第四章 Datasets 31 第一節 Rain12 31 第二節 Rain100L 32 第三節 Rain800 32 第四節 DDN-SIRR 33 第五節 GT-Rain 34 第五章 Experiments 35 第一節 Experimental Settings 35 第二節 Quantitative Analysis 36 第三節 Qualitative Analysis 37 第四節 Ablation Study 52 第一小節 Comparison Rain Masks 52 第二小節 Ablation on the Self-Supervised Reward Predictor 53 第三小節 Ablation on Additional Rain Pixel Sampling 55 第四小節 Single vs Multiple Image Training 56 第五節 Analysis and Applications 57 第六章 Conclusions 60 參考文獻 Reference 61zh_TW
dc.format.extent 15628250 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110753115en_US
dc.subject (關鍵詞) 自監督式學習zh_TW
dc.subject (關鍵詞) 強化學習zh_TW
dc.subject (關鍵詞) 影像除雨zh_TW
dc.subject (關鍵詞) Self-Supervised Learningen_US
dc.subject (關鍵詞) Reinforcement Learningen_US
dc.subject (關鍵詞) Image derainingen_US
dc.title (題名) 基於強化學習的影像除雨技術zh_TW
dc.title (題名) Reinforcement-learning-based Image Derainingen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] Pablo Arbelaez, Michael Maire, Charless Fowlkes, and Jitendra Malik. Contour detection and hierarchical image segmentation. IEEE transactions on pattern analysis and machine intelligence, 33(5):898–916, 2010. [2] 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 European Conference on Computer Vision, pages 723–740. Springer, 2022. [3] Joshua Batson and Loic Royer. Noise2self: Blind denoising by self-supervision. In Proc. Int’l Conf. Machine Learning, 2019. [4] NavneetDalalandBillTriggs.Histogramsoforientedgradientsforhumandetection. In Proc. Conf. Computer Vision and Pattern Recognition, 2005. [5] Liang-Jian Deng, Ting-Zhu Huang, Xi-Le Zhao, and Tai-Xiang Jiang. A directional global sparse model for single image rain removal. Applied Mathematical Modelling, 2018. [6] Sen Deng, Mingqiang Wei, Jun Wang, Yidan Feng, Luming Liang, Haoran Xie, Fu Lee Wang, and Meng Wang. Detail-recovery image deraining via context aggregation networks. In Proc. Conf. Computer Vision and Pattern Recognition, 2020. [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] Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, and John Paisley. Clearing the skies: A deep network architecture for single-image rain removal. IEEE Transactions on Image Processing, 26(6):2944–2956, 2017. [9] RyosukeFuruta,NaotoInoue,andToshihikoYamasaki.Fully convolutional network with multi-step reinforcement learning for image processing. In Proc. Nat’l Conf. Artificial Intelligence, 2019. [10] Kshitiz Garg and Shree K Nayar. Photorealistic rendering of rain streaks. ACM Transactions on Graphics (TOG), 25(3):996–1002, 2006. [11] Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Christopher Burgess, Alexan- der Pritzel, Matthew Botvinick, Charles Blundell, and Alexander Lerchner. Darla: Improving zero-shot transfer in reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2017. [12] Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, and Jianzhuang Liu. Neigh- bor2neighbor: Self-supervised denoising from single noisy images. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14781–14790, 2021. [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. [14] Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, and Wei Zhou. Unsupervised single image deraining with self-supervised constraints. In Proc. Int’l Conf. Image Processing, 2019. [15] Li-WeiKang,Chia-WenLin,andYu-HsiangFu.Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans. on Image Processing, 2011. [16] Alexander Krull, Tim-Oliver Buchholz, and Florian Jug. Noise2void-learning de-noising from single noisy images. In Proc. Conf. Computer Vision and Pattern Recognition, 2019. [17] Michael Laskin, Aravind Srinivas, and Pieter Abbeel. CURL: Contrastive unsupervised representations for reinforcement learning. In Proc. Int’l Conf. Machine Learning, pages 5639–5650, 2020. [18] Kuang-Huei Lee, Ian Fischer, Anthony Liu, Yijie Guo, Honglak Lee, John Canny, and Sergio Guadarrama. Predictive information accelerates learning in RL. Proc. Neural Information Processing Systems, 2020. [19] WooseokLee, SanghyunSon,andKyoungMuLee.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. [20] Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Mi- ika Aittala, and Timo Aila. Noise2noise: Learning image restoration without clean data. arXiv preprint arXiv:1803.04189, 2018. [21] Debang Li, Huikai Wu, Junge Zhang, and Kaiqi Huang. A2-rl: Aesthetics aware reinforcement learning for image cropping. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8193–8201, 2018. [22] JunyiLi,ZhiluZhang,XiaoyuLiu,ChaoyuFeng,XiaotaoWang,LeiLei,andWang- meng 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. [23] Xiang Li, Jinghuan Shang, Srijan Das, and Michael Ryoo. Does self-supervised learning really improve reinforcement learning from pixels? Proc. Neural Information Processing Systems, 2022. [24] 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. [25] 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. [26] Julien Mairal, Francis Bach, Jean Ponce, and Guillermo Sapiro. Online learning for matrix factorization and sparse coding. Journal of Machine Learning Research, 2010. [27] 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 Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, volume 2, pages 416–423. IEEE, 2001. [28] AnishMittal,AnushKrishnaMoorthy,andAlanConradBovik.No-reference image quality assessment in the spatial domain. IEEE Trans. on Image Processing, 2012. [29] Anish Mittal, Rajiv Soundararajan, and Alan C Bovik. Making a “completely blind” image quality analyzer. Signal Processing Letters, 2012. [30] Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. Asynchronous methods for deep reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2016. [31] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013. [32] Ofir Nachum, Mohammad Norouzi, Kelvin Xu, and Dale Schuurmans. Bridging the gap between value and policy based reinforcement learning. Proc. Neural Information Processing Systems, 2017. [33] Ashvin V Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, and Sergey Levine. Visual reinforcement learning with imagined goals. Proc. Neural Information Processing Systems, 2018. [34] Jongchan Park, Joon-Young Lee, Donggeun Yoo, and In So Kweon. Distort-and-recover: Color enhancement using deep reinforcement learning. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018. [35] Yan-Tsung Peng and Wei-Hua Li. Rain2avoid: Self-supervised single image derain- ing. In Proc. Int’l Conf. Acoustics, Speech, and Signal Processing, 2023. [36] Shyam Nandan Rai, Rohit Saluja, Chetan Arora, Vineeth N Balasubramanian, An- bumani 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. [37] Gerald Schaefer and Michal Stich. Ucid: An uncompressed color image database. In Storage and retrieval methods and applications for multimedia 2004, volume 5307, pages 472–480. SPIE, 2003. [38] John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. Trust region policy optimization. In Proc. Int’l Conf. Machine Learning, 2015. [39] Max Schwarzer, Ankesh Anand, Rishab Goel, R Devon Hjelm, Aaron Courville, and Philip Bachman. Data-efficient reinforcement learning with self-predictive representations. In Proc. Int’l Conf. Learning Representations, 2021. [40] RamananSekar,OlehRybkin,KostasDaniilidis,PieterAbbeel,DanijarHafner,and Deepak Pathak. Planning to explore via self-supervised world models. In Proc. Int’l Conf. Machine Learning, 2020. [41] EvanShelhamer,ParsaMahmoudieh,MaxArgus,andTrevorDarrell.Lossisitsown reward: Self-supervision for reinforcement learning. In International Conference on Learning Representations Workshop, 2017. [42] AdamStooke,KiminLee,PieterAbbeel,andMichaelLaskin.Decoupling representation learning from reinforcement learning. In Proc. Int’l Conf. Machine Learning, 2021. [43] Seiya Tokui, Ryosuke Okuta, Takuya Akiba, Yusuke Niitani, Toru Ogawa, Shunta Saito, Shuji Suzuki, Kota Uenishi, Brian Vogel, and Hiroyuki Yamazaki Vincent. Chainer: A deep learning framework for accelerating the research cycle. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019. [44] Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. Deep image prior. In Proc. Conf. Computer Vision and Pattern Recognition, 2018. [45] 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. [46] 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. [47] 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. [48] 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. [49] Wei Wei, Lixuan Yi, Qi Xie, Qian Zhao, Deyu Meng, and Zongben Xu. Should we encode rain streaks in video as deterministic or stochastic? In Proceedings of the IEEE International Conference on Computer Vision, pages 2516–2525, 2017. [50] YanyanWei,ZhaoZhang,YangWang,MingliangXu,YiYang,ShuichengYan,and Meng Wang. Deraincyclegan: Rain attentive cyclegan for single image deraining and rainmaking. IEEE Trans. on Image Processing, 2021. [51] 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 Proc. Conf. Computer Vision and Pattern Recognition, 2017. [52] Denis Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos, Joelle Pineau, and Rob Fergus. Improving sample efficiency in model-free reinforcement learning from images. In Proc. Nat’l Conf. Artificial Intelligence, 2021. [53] KeYu,ChaoDong,LiangLin,andChenChangeLoy.Craftingatoolchainforimage restoration by deep reinforcement learning. In IEEE Trans. on Pattern Analysis and Machine Intelligence, 2018. [54] Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Ming-Hsuan Yang, and Ling Shao. Multi-stage progressive image restoration. In Proc. Conf. Computer Vision and Pattern Recognition, 2021. [55] 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. [56] He Zhang, Vishwanath Sindagi, and Vishal M Patel. Image de-raining using a conditional generative adversarial network. IEEE Trans. on Circuits and Systems for Video Technology, 2019. [57] Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018. [58] Jinhua Zhu, Yingce Xia, Lijun Wu, Jiajun Deng, Wengang Zhou, Tao Qin, Tie-Yan Liu, and Houqiang Li. Masked contrastive representation learning for reinforcement learning. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2023.zh_TW