{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T07:31:02Z","timestamp":1776238262902,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2009XJTU0016"],"award-info":[{"award-number":["2009XJTU0016"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2049"],"award-info":[{"award-number":["U22B2049"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755117","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"7785-7794","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7661-1364","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-9507","authenticated-orcid":false,"given":"Jinshan","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-5130","authenticated-orcid":false,"given":"Yinchuan","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1366-9843","authenticated-orcid":false,"given":"Qingji","family":"Dong","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9138-9987","authenticated-orcid":false,"given":"Chao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5489-8288","authenticated-orcid":false,"given":"Yu","family":"Guo","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3462-8472","authenticated-orcid":false,"given":"Fei","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681637"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657423"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"e_1_3_2_1_9_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","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."},{"key":"e_1_3_2_1_10_1","volume-title":"One step diffusion via shortcut models. arXiv preprint arXiv:2410.12557","author":"Frans Kevin","year":"2024","unstructured":"Kevin Frans, Danijar Hafner, Sergey Levine, and Pieter Abbeel. 2024. One step diffusion via shortcut models. arXiv preprint arXiv:2410.12557 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00431"},{"key":"e_1_3_2_1_12_1","volume-title":"Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373","author":"Geyer Michal","year":"2023","unstructured":"Michal Geyer, Omer Bar-Tal, Shai Bagon, and Tali Dekel. 2023. Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"NTIRE 2022 challenge on perceptual image quality assessment. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 951-967","author":"Gu Jinjin","year":"2022","unstructured":"Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S Ren, Radu Timofte, Yuan Gong, Shanshan Lao, Shuwei Shi, Jiahao Wang, Sidi Yang, et al., 2022. NTIRE 2022 challenge on perceptual image quality assessment. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 951-967."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475320"},{"key":"e_1_3_2_1_15_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","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."},{"key":"e_1_3_2_1_16_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611908"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_37"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547994"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9822-9832","author":"Wang Xiaogang","year":"2023","unstructured":"Dasong Li, Xiaoyu Shi, Yi Zhang, Ka Chun Cheung, Simon See, Xiaogang Wang, Hongwei Qin, and Hongsheng Li. 2023. A simple baseline for video restoration with grouped spatial-temporal shift. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 9822-9832."},{"key":"e_1_3_2_1_25_1","volume-title":"Kaiwen Zhou, Jiqian Dong, Kaiyang Guo, Xiu Li, Zhitang Chen, et al.","author":"Li Yinchuan","year":"2025","unstructured":"Yinchuan Li, Xinyu Shao, Jianping Zhang, Haozhi Wang, Leo Maxime Brunswic, Kaiwen Zhou, Jiqian Dong, Kaiyang Guo, Xiu Li, Zhitang Chen, et al., 2025. Generative models in decision making: A survey. arXiv preprint arXiv:2502.17100 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Vrt: A video restoration transformer","author":"Liang Jingyun","year":"2024","unstructured":"Jingyun Liang, Jiezhang Cao, Yuchen Fan, Kai Zhang, Rakesh Ranjan, Yawei Li, Radu Timofte, and Luc Van Gool. 2024. Vrt: A video restoration transformer. IEEE Transactions on Image Processing (2024)."},{"key":"e_1_3_2_1_27_1","first-page":"378","article-title":"Recurrent video restoration transformer with guided deformable attention","volume":"35","author":"Liang Jingyun","year":"2022","unstructured":"Jingyun Liang, Yuchen Fan, Xiaoyu Xiang, Rakesh Ranjan, Eddy Ilg, Simon Green, Jiezhang Cao, Kai Zhang, Radu Timofte, and Luc V Gool. 2022. Recurrent video restoration transformer with guided deformable attention. Advances in Neural Information Processing Systems, Vol. 35 (2022), 378-393.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00322"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00251"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00746"},{"key":"e_1_3_2_1_32_1","volume-title":"Suraj Patil and Thomas Wolf","author":"Pedro Cuenca Nathan Lambert Anton Lozhkov","year":"2022","unstructured":"Anton Lozhkov Pedro Cuenca Nathan Lambert Kashif Rasul Mishig Davaadorj Patrick von Platen, Suraj Patil and Thomas Wolf. 2022. Diffusers: State-of-the-art Diffusion Models."},{"key":"e_1_3_2_1_33_1","volume-title":"Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_35_1","volume-title":"ACM SIGGRAPH 2024 Conference Papers. 1-11","author":"Qin Hongwei","year":"2024","unstructured":"Xiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang, Weikang Bian, Dasong Li, Yi Zhang, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, et al., 2024. Motion-i2v: Consistent and controllable image-to-video generation with explicit motion modeling. In ACM SIGGRAPH 2024 Conference Papers. 1-11."},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256-2265."},{"key":"e_1_3_2_1_37_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. (2023)."},{"key":"e_1_3_2_1_38_1","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume":"36","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, and Bharath Hariharan. 2023. Emergent correspondence from image diffusion. Advances in Neural Information Processing Systems, Vol. 36 (2023), 1363-1389.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.479"},{"key":"e_1_3_2_1_40_1","volume-title":"A connection between score matching and denoising autoencoders. Neural computation","author":"Vincent Pascal","year":"2011","unstructured":"Pascal Vincent. 2011. A connection between score matching and denoising autoencoders. Neural computation, Vol. 23, 7 (2011), 1661-1674."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_2_1_42_1","volume-title":"Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors. arXiv preprint arXiv:2412.07152","author":"Wang Jiangang","year":"2024","unstructured":"Jiangang Wang, Qingnan Fan, Qi Zhang, Haigen Liu, Yuhang Yu, Jinwei Chen, and Wenqi Ren. 2024a. Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors. arXiv preprint arXiv:2412.07152 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Kelvin CK Chan, and Chen Change Loy","author":"Wang Jianyi","year":"2024","unstructured":"Jianyi Wang, Zongsheng Yue, Shangchen Zhou, Kelvin CK Chan, and Chen Change Loy. 2024c. Exploiting diffusion prior for real-world image super-resolution. International Journal of Computer Vision (2024), 1-21."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02437"},{"key":"e_1_3_2_1_46_1","first-page":"8406","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang Zhengyi","year":"2023","unstructured":"Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, and Jun Zhu. 2023b. Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 8406-8441.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_2_1_48_1","first-page":"92529","article-title":"One-step effective diffusion network for real-world image super-resolution","volume":"37","author":"Wu Rongyuan","year":"2024","unstructured":"Rongyuan Wu, Lingchen Sun, Zhiyuan Ma, and Lei Zhang. 2024. One-step effective diffusion network for real-world image super-resolution. Advances in Neural Information Processing Systems, Vol. 37 (2024), 92529-92553.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681357"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413667"},{"key":"e_1_3_2_1_51_1","volume-title":"STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution. arXiv preprint arXiv:2501.02976","author":"Xie Rui","year":"2025","unstructured":"Rui Xie, Yinhong Liu, Penghao Zhou, Chen Zhao, Jun Zhou, Kai Zhang, Zhenyu Zhang, Jian Yang, Zhenheng Yang, and Ying Tai. 2025. STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution. arXiv preprint arXiv:2501.02976 (2025)."},{"key":"e_1_3_2_1_52_1","volume-title":"Addsr: Accelerating diffusion-based blind super-resolution with adversarial diffusion distillation. arXiv preprint arXiv:2404.01717","author":"Xie Rui","year":"2024","unstructured":"Rui Xie, Chen Zhao, Kai Zhang, Zhenyu Zhang, Jun Zhou, Jian Yang, and Ying Tai. 2024. Addsr: Accelerating diffusion-based blind super-resolution with adversarial diffusion distillation. arXiv preprint arXiv:2404.01717 (2024)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"e_1_3_2_1_56_1","volume-title":"Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072","author":"Yang Zhuoyi","year":"2024","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00439"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00320"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"e_1_3_2_1_61_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yue Zongsheng","year":"2024","unstructured":"Zongsheng Yue, Jianyi Wang, and Chen Change Loy. 2024. Resshift: Efficient diffusion model for image super-resolution by residual shifting. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_63_1","volume-title":"European Conference on Computer Vision. Springer, 412-428","author":"Zhang Yuehan","year":"2024","unstructured":"Yuehan Zhang and Angela Yao. 2024. Realviformer: Investigating attention for real-world video super-resolution. In European Conference on Computer Vision. Springer, 412-428."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00245"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:07:16Z","timestamp":1765310836000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":65,"alternative-id":["10.1145\/3746027.3755117","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755117","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}