{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:19:59Z","timestamp":1770229199884,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Zhejiang Elite Program","award":["2022C01222"],"award-info":[{"award-number":["2022C01222"]}]},{"name":"National Program of China","award":["2020YFC1523201, 62172365,19ZDA197"],"award-info":[{"award-number":["2020YFC1523201, 62172365,19ZDA197"]}]},{"name":"Key Technologies and Product Research and Development Projects for Cultural Relics Protection and Trading Circulation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611866","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:12Z","timestamp":1698391632000},"page":"7981-7992","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Self-Reference Image Super-Resolution via Pre-trained Diffusion Large Model and Window Adjustable Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2938-527X","authenticated-orcid":false,"given":"Guangyuan","family":"Li","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7994-6725","authenticated-orcid":false,"given":"Wei","family":"Xing","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4791-454X","authenticated-orcid":false,"given":"Lei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7486-2103","authenticated-orcid":false,"given":"Zehua","family":"Lan","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2894-9456","authenticated-orcid":false,"given":"Jiakai","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8966-1328","authenticated-orcid":false,"given":"Zhanjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2121-2159","authenticated-orcid":false,"given":"Quanwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-5349","authenticated-orcid":false,"given":"Huaizhong","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2377-7608","authenticated-orcid":false,"given":"Zhijie","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University of Science and Technology, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Marco Bevilacqua Aline Roumy Christine Guillemot and Marie Line Alberi-Morel. 2012. Low-complexity single-image super-resolution based on nonnegative neighbor embedding. (2012).","DOI":"10.5244\/C.26.135"},{"key":"e_1_3_2_2_2_1","volume-title":"Tel Aviv","author":"Cao Jiezhang","year":"2022","unstructured":"Jiezhang Cao, Jingyun Liang, Kai Zhang, Yawei Li, Yulun Zhang, Wenguan Wang, and Luc Van Gool. 2022. Reference-Based Image Super-Resolution with Deformable Attention Transformer. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XVIII. Springer, 325--342."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"e_1_3_2_2_5_1","first-page":"25478","article-title":"Cross Aggregation Transformer for Image Restoration","volume":"35","author":"Chen Zheng","year":"2022","unstructured":"Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xin Yuan, et al. 2022. Cross Aggregation Transformer for Image Restoration. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25478--25490.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_6_1","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, Vol. 34 (2021), 8780--8794.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_7_1","volume-title":"Kaiming He, and Xiaoou Tang.","author":"Dong Chao","year":"2015","unstructured":"Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. 2015. Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 2 (2015), 295--307."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.891788"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00966"},{"key":"e_1_3_2_2_10_1","volume-title":"Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Guo Yong","year":"2020","unstructured":"Yong Guo, Jian Chen, Jingdong Wang, Qi Chen, Jiezhang Cao, Zeshuai Deng, Yanwu Xu, and Mingkui Tan. 2020. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence Vol. 45 1 (2022) 87--110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_2_2_12_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, Vol. 33 (2020), 6840--6851.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299156"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00584"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00213"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00214"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00214"},{"key":"e_1_3_2_2_18_1","volume-title":"Practical Single-Image Super-Resolution Using Look-Up Table. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Jo Younghyun","year":"2021","unstructured":"Younghyun Jo and Seon Joo Kim. 2021. Practical Single-Image Super-Resolution Using Look-Up Table. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_19_1","volume-title":"Denoising diffusion restoration models. arXiv preprint arXiv:2201.11793","author":"Kawar Bahjat","year":"2022","unstructured":"Bahjat Kawar, Michael Elad, Stefano Ermon, and Jiaming Song. 2022. Denoising diffusion restoration models. arXiv preprint arXiv:2201.11793 (2022)."},{"key":"e_1_3_2_2_20_1","volume-title":"Neural Side-By-Side: Predicting Human Preferences for No-Reference Super-Resolution Evaluation. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Khrulkov Valentin","year":"2021","unstructured":"Valentin Khrulkov and Artem Babenko. 2021. Neural Side-By-Side: Predicting Human Preferences for No-Reference Super-Resolution Evaluation. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_21_1","volume-title":"Variational diffusion models. Advances in neural information processing systems","author":"Kingma Diederik","year":"2021","unstructured":"Diederik Kingma, Tim Salimans, Ben Poole, and Jonathan Ho. 2021. Variational diffusion models. Advances in neural information processing systems, Vol. 34 (2021), 21696--21707."},{"key":"e_1_3_2_2_22_1","volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_2_24_1","volume-title":"Deep Image Prior. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Lempitsky Victor","year":"2018","unstructured":"Victor Lempitsky, Andrea Vedaldi, and Dmitry Ulyanov. 2018. Deep Image Prior. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01998"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3099695"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16446-0_44"},{"key":"e_1_3_2_2_28_1","volume-title":"Feedback Network for Image Super-Resolution. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Li Zhen","year":"2020","unstructured":"Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, and Wei Wu. 2020. Feedback Network for Image Super-Resolution. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"e_1_3_2_2_31_1","volume-title":"SGDR: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations.","author":"Loshchilov Ilya","unstructured":"Ilya Loshchilov and Frank Hutter. [n.,d.]. SGDR: Stochastic Gradient Descent with Warm Restarts. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00630"},{"key":"e_1_3_2_2_33_1","volume-title":"2023 a. Multicontrast MRI Super-Resolution via Transformer-Empowered Multiscale Contextual Matching and Aggregation","author":"Lyu Jun","year":"2023","unstructured":"Jun Lyu, Guangyuan Li, Chengyan Wang, Qing Cai, Qi Dou, David Zhang, and Jing Qin. 2023 a. Multicontrast MRI Super-Resolution via Transformer-Empowered Multiscale Contextual Matching and Aggregation. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102760"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4020-z"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00352"},{"key":"e_1_3_2_2_38_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"e_1_3_2_2_40_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"e_1_3_2_2_43_1","first-page":"4713","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi. 2022b. Image super-resolution via iterative refinement. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 45, 4 (2022), 4713--4726.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_2_44_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. arXiv preprint arXiv:2210.08402 (2022)."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00845"},{"key":"e_1_3_2_2_46_1","volume-title":"2012 IEEE International conference on computational photography (ICCP). IEEE, 1--12","author":"Sun Libin","year":"2012","unstructured":"Libin Sun and James Hays. 2012. Super-resolution from internet-scale scene matching. In 2012 IEEE International conference on computational photography (ICCP). IEEE, 1--12."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00342"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"e_1_3_2_2_49_1","volume-title":"Kelvin CK Chan, and Chen Change Loy. 2023 a. Exploiting Diffusion Prior for Real-World Image Super-Resolution. arXiv preprint arXiv:2305.07015","author":"Wang Jianyi","year":"2023","unstructured":"Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin CK Chan, and Chen Change Loy. 2023 a. Exploiting Diffusion Prior for Real-World Image Super-Resolution. arXiv preprint arXiv:2305.07015 (2023)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00488"},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition.","author":"Wang Wenhai","year":"2022","unstructured":"Wenhai Wang, Jifeng Dai, Zhe Chen, Zhenhang Huang, Zhiqi Li, Xizhou Zhu, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, et al. 2022. InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25374"},{"key":"e_1_3_2_2_54_1","volume-title":"Denoising and Super-Resolution. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Xing Wenzhu","year":"2021","unstructured":"Wenzhu Xing and Karen Egiazarian. 2021. End-to-End Learning for Joint Image Demosaicing, Denoising and Super-Resolution. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"e_1_3_2_2_56_1","volume-title":"Accurate Image Restoration with Attention Retractable Transformer. In The Eleventh International Conference on Learning Representations.","author":"Zhang Jiale","year":"2023","unstructured":"Jiale Zhang, Yulun Zhang, Jinjin Gu, Yongbing Zhang, Linghe Kong, and Xin Yuan. 2023. Accurate Image Restoration with Attention Retractable Transformer. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_57_1","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision.","author":"Zhang Kai","year":"2022","unstructured":"Kai Zhang, Jingyun Liang, Luc Van Gool, and Radu Timofte. 2022. Designing a Practical Degradation Model for Deep Blind Image Super-Resolution. In 2021 IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839891"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01322"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00817"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413760"},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_6"},{"key":"e_1_3_2_2_65_1","volume-title":"Cross-scale internal graph neural network for image super-resolution. Advances in neural information processing systems","author":"Zhou Shangchen","year":"2020","unstructured":"Shangchen Zhou, Jiawei Zhang, Wangmeng Zuo, and Chen Change Loy. 2020. Cross-scale internal graph neural network for image super-resolution. Advances in neural information processing systems, Vol. 33 (2020), 3499--3509."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/693"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611866","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:23Z","timestamp":1755820763000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":66,"alternative-id":["10.1145\/3581783.3611866","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611866","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}