{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:34:57Z","timestamp":1770752097802,"version":"3.50.0"},"reference-count":72,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61902151 and 62172190"],"award-info":[{"award-number":["61902151 and 62172190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Jiangsu Province, China","award":["BK20170197"],"award-info":[{"award-number":["BK20170197"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:p>\n                    Since raining weather always degrades image quality and poses significant challenges to most computer vision-based intelligent systems, image de-raining has been a hot research topic in computer vision community. Fortunately, in a rainy Light Field (LF) image, background obscured by rain streaks in one sub-view may be visible in the other sub-views, and implicit depth information and recorded 4D structural information may benefit rain streak detection and removal. However, existing LF image rain removal methods either do not fully exploit the global correlations of 4D LF data or only utilize partial sub-views (i.e., under-utilization of the rich angular information), resulting in sub-optimal rain removal performance and no-equally good quality for all de-rained sub-views. In this article, we propose an efficient neural network, called\n                    <jats:italic toggle=\"yes\">MDeRainNet<\/jats:italic>\n                    , for rain streak removal from LF images. The proposed network adopts a multi-scale encoder\u2013decoder architecture, which directly works on Macro-pixel Images (MPIs) for improving the rain removal performance. To fully model the global correlation between the spatial information and the angular information, we propose an\n                    <jats:italic toggle=\"yes\">Extended Spatial-angular Interaction (ESAI)<\/jats:italic>\n                    module to merge the two types of information, in which a simple and effective Transformer-based\n                    <jats:italic toggle=\"yes\">Spatial-angular Interaction Attention (SAIA)<\/jats:italic>\n                    block is also proposed for modeling long-range geometric correlations and making full use of the angular information. Furthermore, to improve the generalization performance of our network on real-world rainy scenes, we propose a novel semi-supervised learning framework for our\n                    <jats:italic toggle=\"yes\">MDeRainNet<\/jats:italic>\n                    , which utilizes multi-level KL loss to bridge the domain gap between features of synthetic and that of real-world rain streaks and introduces colored-residue image-guided contrastive regularization to reconstruct rain-free images. Extensive experiments conducted on both synthetic and real-world Light Field Images (LFIs) demonstrate that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.\n                  <\/jats:p>","DOI":"10.1145\/3775059","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T14:43:16Z","timestamp":1763044996000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MDeRainNet: An Efficient Macro-pixel Image Rain Removal Network"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9162-8551","authenticated-orcid":false,"given":"Tao","family":"Yan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0974-9766","authenticated-orcid":false,"given":"Weilong","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9713-6008","authenticated-orcid":false,"given":"Weijiang","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0746-8427","authenticated-orcid":false,"given":"Chenglong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8662-2657","authenticated-orcid":false,"given":"Cihang","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9311-8645","authenticated-orcid":false,"given":"Yiwei","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9847-6882","authenticated-orcid":false,"given":"Xiangjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8157-7326","authenticated-orcid":false,"given":"Yinghui","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8957-8129","authenticated-orcid":false,"given":"Rynson W. H.","family":"Lau","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,10]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Jimmy Lei Ba Jamie Ryan Kiros and Geoffrey E. Hinton. 2016. Layer normalization. arXiv:1607.06450. Retrieved from https:\/\/arxiv.org\/abs\/1607.06450"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"e_1_3_2_5_2","unstructured":"Weidong Chen Xiaofeng Xing Xiangmin Xu and Jichen Yang. 2021. Key-sparse transformer with cascaded cross-attention block for multimodal speech emotion recognition. arXiv:2106.11532. Retrieved from https:\/\/arxiv.org\/abs\/2106.11532"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00571"},{"key":"e_1_3_2_7_2","first-page":"25627","volume-title":"CVPR","author":"Chen Xiang","year":"2024","unstructured":"Xiang Chen, Jinshan Pan, and Jiangxin Dong. 2024. Bidirectional multi-scale implicit neural representations for image deraining. In CVPR, 25627\u201325636."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00206"},{"key":"e_1_3_2_9_2","first-page":"2447","volume-title":"EMNLP","author":"Cheng Junyan","year":"2021","unstructured":"Junyan Cheng, Iordanis Fostiropoulos, Barry Boehm, and Mohammad Soleymani. 2021. Multimodal phased transformer for sentiment analysis. In EMNLP, 2447\u20132458."},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3190516"},{"key":"e_1_3_2_11_2","doi-asserted-by":"crossref","first-page":"3403","DOI":"10.1109\/TIP.2025.3572788","article-title":"Exploring the potential of pooling techniques for universal image restoration","volume":"34","author":"Cui Yuning","year":"2025","unstructured":"Yuning Cui, Wenqi Ren, and Alois Knoll. 2025. Exploring the potential of pooling techniques for universal image restoration. IEEE Transactions on Image Processing 34 (2025), 3403\u20133416.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1016\/j.apm.2018.03.001","article-title":"A directional global sparse model for single image rain removal","volume":"59","author":"Deng Liang-Jian","year":"2018","unstructured":"Liang-Jian Deng, Ting-Zhu Huang, Xi-Le Zhao, and Tai-Xiang Jiang. 2018. A directional global sparse model for single image rain removal. Applied Mathematical Modelling 59 (2018), 662\u2013679.","journal-title":"Applied Mathematical Modelling"},{"issue":"2","key":"e_1_3_2_13_2","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1109\/TCSVT.2021.3063853","article-title":"Rain streak removal from light field images","volume":"32","author":"Ding Yuyang","year":"2021","unstructured":"Yuyang Ding, Mingyue Li, Tao Yan, Fan Zhang, Yuan Liu, and Rynson W. H. Lau. 2021. Rain streak removal from light field images. IEEE Transactions on Circuits and Systems for Video Technology 32, 2 (2021), 467\u2013482.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_14_2","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2691802"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.186"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3241756"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_19_2","first-page":"12097","volume-title":"ICCV","author":"Guo Yun","year":"2023","unstructured":"Yun Guo, Xueyao Xiao, Yi Chang, Shumin Deng, and Luxin Yan. 2023. From sky to the ground: A large-scale benchmark and simple baseline towards real rain removal. In ICCV, 12097\u201312107."},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1109\/LSP.2021.3078074","article-title":"A unimodal reinforced transformer with time squeeze fusion for multimodal sentiment analysis","volume":"28","author":"He Jiaxuan","year":"2021","unstructured":"Jiaxuan He, Sijie Mai, and Haifeng Hu. 2021. A unimodal reinforced transformer with time squeeze fusion for multimodal sentiment analysis. IEEE Signal Processing Letters 28 (2021), 992\u2013996.","journal-title":"IEEE Signal Processing Letters"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00764"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00837"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3102504"},{"key":"e_1_3_2_24_2","unstructured":"Dong Jing Shuo Zhang Song Chang and Youfang Lin. 2022. Light field raindrop removal via 4D re-sampling. arXiv:2205.13165. Retrieved from https:\/\/arxiv.org\/abs\/2205.13165"},{"key":"e_1_3_2_25_2","first-page":"1692","volume-title":"ACM Multimedia","author":"Jing Dong","year":"2021","unstructured":"Dong Jing, Shuo Zhang, Runmin Cong, and Youfang Lin. 2021. Occlusion-aware bi-directional guided network for light field salient object detection. In ACM Multimedia, 1692\u20131701."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2179057"},{"key":"e_1_3_2_27_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00173"},{"key":"e_1_3_2_29_2","first-page":"288","volume-title":"ECCV","author":"Li Ruoteng","year":"2018","unstructured":"Ruoteng Li, Robby T. Tan, and Loong-Fah Cheong. 2018. Robust optical flow in rainy scenes. In ECCV, 288\u2013304."},{"key":"e_1_3_2_30_2","unstructured":"Xuejian Li Shiqiang Ma Jijun Tang and Fei Guo. 2022. TranSiam: Fusing multimodal visual features using transformer for medical image segmentation. arXiv:2204.12185. Retrieved from https:\/\/arxiv.org\/abs\/2204.12185"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.299"},{"key":"e_1_3_2_32_2","first-page":"589","volume-title":"CVPR","author":"Liang Yuanchu","year":"2022","unstructured":"Yuanchu Liang, Saeed Anwar, and Yang Liu. 2022. DRT: A lightweight single image deraining recursive transformer. In CVPR, 589\u2013598."},{"key":"e_1_3_2_33_2","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/LSP.2022.3146798","article-title":"Light field image super-resolution with transformers","volume":"29","author":"Liang Zhengyu","year":"2022","unstructured":"Zhengyu Liang, Yingqian Wang, Longguang Wang, Jungang Yang, and Shilin Zhou. 2022. Light field image super-resolution with transformers. IEEE Signal Processing Letters 29 (2022), 563\u2013567.","journal-title":"IEEE Signal Processing Letters"},{"key":"e_1_3_2_34_2","doi-asserted-by":"crossref","first-page":"7668","DOI":"10.1109\/TIP.2020.3005517","article-title":"Rain o\u2019er me: Synthesizing real rain to derain with data distillation","volume":"29","author":"Lin Huangxing","year":"2020","unstructured":"Huangxing Lin, Yanlong Li, Xueyang Fu, Xinghao Ding, Yue Huang, and John Paisley. 2020. Rain o\u2019er me: Synthesizing real rain to derain with data distillation. IEEE Transactions on Image Processing 29 (2020), 7668\u20137680.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","first-page":"102183","DOI":"10.1016\/j.inffus.2023.102183","article-title":"Adaptive pixel aggregation for joint spatial and angular super-resolution of light field images","volume":"104","author":"Liu Gaosheng","year":"2024","unstructured":"Gaosheng Liu, Huanjing Yue, Kun Li, and Jingyu Yang. 2024. Adaptive pixel aggregation for joint spatial and angular super-resolution of light field images. Information Fusion 104 (2024), 102183.","journal-title":"Information Fusion"},{"key":"e_1_3_2_36_2","first-page":"6277","volume-title":"CVPRW","author":"Liu Gaosheng","year":"2024","unstructured":"Gaosheng Liu, Huanjing Yue, and Jingyu Yang. 2024. Efficient light field image Super-Resolution via progressive disentangling. In CVPRW, 6277\u20136286."},{"key":"e_1_3_2_37_2","volume-title":"ICCV","author":"Liu Nian","year":"2021","unstructured":"Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, and Junwei Han. 2021. Visual saliency transformer. In ICCV."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3321085"},{"key":"e_1_3_2_39_2","first-page":"13","volume-title":"NeurIPS","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NeurIPS, 13\u201323."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.388"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00903"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2994443"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00406"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"e_1_3_2_45_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Retrieved from https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00239"},{"key":"e_1_3_2_47_2","first-page":"6000","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS, 6000\u20136010."},{"key":"e_1_3_2_48_2","doi-asserted-by":"crossref","first-page":"109244","DOI":"10.1016\/j.knosys.2022.109244","article-title":"Image rain removal and illumination enhancement done in one go","volume":"252","author":"Wan Yecong","year":"2022","unstructured":"Yecong Wan, Yuanshuo Cheng, Mingwen Shao, and Jordi Gonz\u00e0lez. 2022. Image rain removal and illumination enhancement done in one go. Knowledge-Based Systems 252 (2022), 109244.","journal-title":"Knowledge-Based Systems"},{"key":"e_1_3_2_49_2","doi-asserted-by":"crossref","first-page":"111504","DOI":"10.1016\/j.patcog.2025.111504","article-title":"Learning to restore arbitrary hybrid adverse weather conditions in one go","volume":"164","author":"Wan Yecong","year":"2025","unstructured":"Yecong Wan, Mingwen Shao, Yuanshuo Cheng, Yuexian Liu, and Zhiyuan Bao. 2025. Learning to restore arbitrary hybrid adverse weather conditions in one go. Pattern Recognition 164 (2025), 111504.","journal-title":"Pattern Recognition"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3023773"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3064229"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"6","key":"e_1_3_2_53_2","doi-asserted-by":"crossref","first-page":"2590","DOI":"10.1109\/TCSVT.2022.3226227","article-title":"Effective light field De-Occlusion network based on swin transformer","volume":"33","author":"Wang Xingzheng","year":"2022","unstructured":"Xingzheng Wang, Jiehao Liu, Songwei Chen, and Guoyao Wei. 2022. Effective light field De-Occlusion network based on swin transformer. IEEE Transactions on Circuits and Systems for Video Technology 33, 6 (2022), 2590\u20132599.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"e_1_3_2_54_2","first-page":"19809","volume-title":"CVPR","author":"Wang Yingqian","year":"2022","unstructured":"Yingqian Wang, Longguang Wang, Zhengyu Liang, Jungang Yang, Wei An, and Yulan Guo. 2022. Occlusion-Aware cost constructor for light field depth estimation. In CVPR, 19809\u201319818."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152488"},{"key":"e_1_3_2_56_2","first-page":"290","volume-title":"ECCV","author":"Wang Yingqian","year":"2020","unstructured":"Yingqian Wang, Longguang Wang, Jungang Yang, Wei An, Jingyi Yu, and Yulan Guo. 2020. Spatial-angular interaction for light field image super-resolution. In ECCV, 290\u2013308."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00400"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01041"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183612"},{"key":"e_1_3_2_61_2","doi-asserted-by":"crossref","first-page":"164203","DOI":"10.1109\/ACCESS.2019.2951917","article-title":"Snow removal from light field images","volume":"7","author":"Yan Tao","year":"2019","unstructured":"Tao Yan, Yuyang Ding, Fan Zhang, Ningyu Xie, Wenxi Liu, Zhengtian Wu, and Yuan Liu. 2019. Snow removal from light field images. IEEE Access 7 (2019), 164203\u2013164215.","journal-title":"IEEE Access"},{"key":"e_1_3_2_62_2","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1109\/TIP.2023.3234692","article-title":"Rain removal from light field images with 4D convolution and multi-scale gaussian process","volume":"32","author":"Yan Tao","year":"2023","unstructured":"Tao Yan, Mingyue Li, Bin Li, Yang, Yang, and Rynson W. H. Lau. 2023. Rain removal from light field images with 4D convolution and multi-scale gaussian process. IEEE Transactions on Image Processing 32 (2023), 921\u2013936.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_63_2","first-page":"11966","volume-title":"CVPR","author":"Yan Wending","year":"2021","unstructured":"Wending Yan, Robby T. Tan, Wenhan Yang, and Dengxin Dai. 2021. Self-aligned video deraining with transmission-depth consistency. In CVPR, 11966\u201311976."},{"key":"e_1_3_2_64_2","first-page":"1720","volume-title":"CVPR","author":"Yang Wenhan","year":"2020","unstructured":"Wenhan Yang, Robby T. Tan, Shiqi Wang, and Jiaying Liu. 2020. Self-learning video rain streak removal: When cyclic consistency meets temporal correspondence. In CVPR, 1720\u20131729."},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00860"},{"key":"e_1_3_2_66_2","first-page":"2726","volume-title":"CVPR","author":"Yasarla Rajeev","year":"2020","unstructured":"Rajeev Yasarla, Vishwanath A. Sindagi, and Vishal M. Patel. 2020. Syn2real transfer learning for image deraining using gaussian processes. In CVPR, 2726\u20132736."},{"key":"e_1_3_2_67_2","first-page":"4238","volume-title":"ICCV","author":"Yi Qiaosi","year":"2021","unstructured":"Qiaosi Yi, Juncheng Li, Qinyan Dai, Faming Fang, Guixu Zhang, and Tieyong Zeng. 2021. Structure-preserving deraining with residue channel prior guidance. In ICCV, 4238\u20134247."},{"key":"e_1_3_2_68_2","first-page":"2634","volume-title":"ACM Multimedia","author":"Yu Changfeng","year":"2021","unstructured":"Changfeng Yu, Yi Chang, Yi Li, Xile Zhao, and Luxin Yan. 2021. Unsupervised image deraining: Optimization model driven deep cnn. In ACM Multimedia, 2634\u20132642."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3167175"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920407"},{"key":"e_1_3_2_73_2","first-page":"2526","volume-title":"ICCV","author":"Zhu Lei","year":"2017","unstructured":"Lei Zhu, Chi-Wing Fu, Dani Lischinski, and Pheng-Ann Heng. 2017. Joint bi-layer optimization for single-image rain streak removal. In ICCV, 2526\u20132534."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3775059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T12:15:02Z","timestamp":1770725702000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3775059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,10]]},"references-count":72,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2,28]]}},"alternative-id":["10.1145\/3775059"],"URL":"https:\/\/doi.org\/10.1145\/3775059","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,10]]},"assertion":[{"value":"2025-06-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}