{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:57:34Z","timestamp":1774022254379,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"name":"The National Natural Science Foundation of China","award":["62372480"],"award-info":[{"award-number":["62372480"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2514050003495"],"award-info":[{"award-number":["2514050003495"]}]},{"name":"NSFC Science Fund Program for Young Scientists Fund","award":["62406089"],"award-info":[{"award-number":["62406089"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2025A1515011361"],"award-info":[{"award-number":["2025A1515011361"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,10]]},"DOI":"10.1145\/3721238.3730699","type":"proceedings-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T08:40:47Z","timestamp":1753260047000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1078-3806","authenticated-orcid":false,"given":"Zhe","family":"Kong","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Shenzhen, China; Meituan, Shenzhen, China and The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8548-013X","authenticated-orcid":false,"given":"Le","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-3448","authenticated-orcid":false,"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7822-4317","authenticated-orcid":false,"given":"Feng","family":"Gao","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0799-9232","authenticated-orcid":false,"given":"Shaoshu","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0202-0174","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4317-660X","authenticated-orcid":false,"given":"Kaihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3119-503X","authenticated-orcid":false,"given":"Zhuoliang","family":"Kang","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7471-8344","authenticated-orcid":false,"given":"Xiaoming","family":"Wei","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1273-4752","authenticated-orcid":false,"given":"Guanying","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5697-4168","authenticated-orcid":false,"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"Omer Bar-Tal Lior Yariv Yaron Lipman and Tali Dekel. 2023. Multidiffusion: Fusing diffusion paths for controlled image generation. (2023)."},{"key":"e_1_3_3_2_3_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.15127 (2023)."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00846"},{"key":"e_1_3_3_2_5_1","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman et\u00a0al. 2024. Video generation models as world simulators. 2024. URL https:\/\/openai. com\/research\/video-generation-models-as-world-simulators 3 (2024)."},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"e_1_3_3_2_9_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et\u00a0al. 2023. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19512 (2023)."},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Xiaoxu Chen Jingfan Tan Tao Wang Kaihao Zhang Wenhan Luo and Xiaochun Cao. 2024a. Towards real-world blind face restoration with generative diffusion prior. TCSVT (2024).","DOI":"10.1109\/TCSVT.2024.3383659"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00589"},{"key":"e_1_3_3_2_13_1","volume-title":"ICML","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et\u00a0al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In ICML."},{"key":"e_1_3_3_2_14_1","unstructured":"Jingwen He Tianfan Xue Dongyang Liu Xinqi Lin Peng Gao Dahua Lin Yu Qiao Wanli Ouyang and Ziwei Liu. 2024. Venhancer: Generative space-time enhancement for video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.07667 (2024)."},{"key":"e_1_3_3_2_15_1","volume-title":"ICLR","author":"He Yingqing","year":"2023","unstructured":"Yingqing He, Shaoshu Yang, Haoxin Chen, Xiaodong Cun, Menghan Xia, Yong Zhang, Xintao Wang, Ran He, Qifeng Chen, and Ying Shan. 2023. Scalecrafter: Tuning-free higher-resolution visual generation with diffusion models. In ICLR."},{"key":"e_1_3_3_2_16_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. NIPS 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022. Video diffusion models. NIPS 35 (2022) 8633\u20138646.","DOI":"10.52202\/068431-0628"},{"key":"e_1_3_3_2_18_1","first-page":"8153","volume-title":"CVPR","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In CVPR. 8153\u20138163."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_38"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_3_2_21_1","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. HunyuanVideo: A Systematic Framework For Large Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"e_1_3_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00825"},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Jingyun Liang Jiezhang Cao Yuchen Fan Kai Zhang Rakesh Ranjan Yawei Li Radu Timofte and Luc Van\u00a0Gool. 2024. Vrt: A video restoration transformer. TIP (2024).","DOI":"10.1109\/TIP.2024.3372454"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Jingyun Liang Yuchen Fan Xiaoyu Xiang Rakesh Ranjan Eddy Ilg Simon Green Jiezhang Cao Kai Zhang Radu Timofte and Luc\u00a0V Gool. 2022. Recurrent video restoration transformer with guided deformable attention. NIPS 35 (2022) 378\u2013393.","DOI":"10.52202\/068431-0028"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Gongye Liu Menghan Xia Yong Zhang Haoxin Chen Jinbo Xing Yibo Wang Xintao Wang Ying Shan and Yujiu Yang. 2024. StyleCrafter: Taming Artistic Video Diffusion with Reference-Augmented Adapter Learning. TOG 43 6 (2024) 1\u201310.","DOI":"10.1145\/3687975"},{"key":"e_1_3_3_2_29_1","unstructured":"Xin Ma Yaohui Wang Gengyun Jia Xinyuan Chen Ziwei Liu Yuan-Fang Li Cunjian Chen and Yu Qiao. 2024. Latte: Latent diffusion transformer for video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.03048 (2024)."},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"Anish Mittal Anush\u00a0Krishna Moorthy and Alan\u00a0Conrad Bovik. 2012. No-reference image quality assessment in the spatial domain. TIP 21 12 (2012) 4695\u20134708.","DOI":"10.1109\/TIP.2012.2214050"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Claudio Rota Marco Buzzelli and Joost van\u00a0de Weijer. 2025. Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models. ECCV (2025).","DOI":"10.1007\/978-3-031-73254-6_3"},{"key":"e_1_3_3_2_34_1","unstructured":"Jingfan Tan Xiaoxu Chen Tao Wang Kaihao Zhang Wenhan Luo and Xiaocun Cao. 2023. Blind face restoration for under-display camera via dictionary guided transformer. TCSVT (2023)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680917"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Qi Tang Yao Zhao Meiqin Liu and Chao Yao. 2024. SeeClear: Semantic distillation enhances pixel condensation for video super-resolution. Advances in Neural Information Processing Systems 37 (2024) 134902\u2013134926.","DOI":"10.52202\/079017-4287"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.479"},{"key":"e_1_3_3_2_38_1","unstructured":"Haofan Wang Matteo Spinelli Qixun Wang Xu Bai Zekui Qin and Anthony Chen. 2024a. Instantstyle: Free lunch towards style-preserving in text-to-image generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02733 (2024)."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"crossref","unstructured":"Jianyi Wang Zhijie Lin Meng Wei Yang Zhao Ceyuan Yang Chen\u00a0Change Loy and Lu Jiang. 2025. SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.01320 (2025).","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"e_1_3_3_2_41_1","unstructured":"Jiuniu Wang Hangjie Yuan Dayou Chen Yingya Zhang Xiang Wang and Shiwei Zhang. 2023b. Modelscope text-to-video technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.06571 (2023)."},{"key":"e_1_3_3_2_42_1","unstructured":"Tao Wang Kaihao Zhang Ziqian Shao Wenhan Luo Bjorn Stenger Tong Lu Tae-Kyun Kim Wei Liu and Hongdong Li. 2024b. Gridformer: Residual dense transformer with grid structure for image restoration in adverse weather conditions. IJCV (2024) 1\u201323."},{"key":"e_1_3_3_2_43_1","unstructured":"Xiaojuan Wang Boyang Zhou Brian Curless Ira Kemelmacher-Shlizerman Aleksander Holynski and Steven\u00a0M Seitz. 2024c. Generative inbetweening: Adapting image-to-video models for keyframe interpolation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.15239 (2024)."},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25398"},{"key":"e_1_3_3_2_46_1","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:https:\/\/arXiv.org\/abs\/2501.02976 (2025)."},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"e_1_3_3_2_48_1","unstructured":"Yiran Xu Taesung Park Richard Zhang Yang Zhou Eli Shechtman Feng Liu Jia-Bin Huang and Difan Liu. 2024. VideoGigaGAN: Towards detail-rich video super-resolution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.12388 (2024)."},{"key":"e_1_3_3_2_49_1","unstructured":"Jingyun Xue Hongfa Wang Qi Tian Yue Ma Andong Wang Zhiyuan Zhao Shaobo Min Wenzhe Zhao Kaihao Zhang Heung-Yeung Shum et\u00a0al. 2024. Follow-Your-Pose v2: Multiple-Condition Guided Character Image Animation for Stable Pose Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.03035 (2024)."},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"crossref","unstructured":"Tianfan Xue Baian Chen Jiajun Wu Donglai Wei and William\u00a0T Freeman. 2019. Video enhancement with task-oriented flow. IJCV 127 (2019) 1106\u20131125.","DOI":"10.1007\/s11263-018-01144-2"},{"key":"e_1_3_3_2_51_1","unstructured":"Shaoshu Yang Yong Zhang Xiaodong Cun Ying Shan and Ran He. 2024b. ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.00908 (2024)."},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"e_1_3_3_2_53_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024a. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_2_54_1","unstructured":"Zixuan Ye Huijuan Huang Xintao Wang Pengfei Wan Di Zhang and Wenhan Luo. 2024. StyleMaster: Stylize Your Video with Artistic Generation and Translation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.07744 (2024)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"e_1_3_3_2_56_1","unstructured":"Zongsheng Yue Kang Liao and Chen\u00a0Change Loy. 2024a. Arbitrary-steps Image Super-resolution via Diffusion InversionScaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.09013 (2024)."},{"key":"e_1_3_3_2_57_1","unstructured":"Zongsheng Yue Jianyi Wang and Chen\u00a0Change Loy. 2024b. Resshift: Efficient diffusion model for image super-resolution by residual shifting. NIPS 36 (2024)."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_60_1","unstructured":"Sijie Zhao Wenbo Hu Xiaodong Cun Yong Zhang Xiaoyu Li Zhe Kong Xiangjun Gao Muyao Niu and Ying Shan. 2024. Stereocrafter: Diffusion-based generation of long and high-fidelity stereoscopic 3d from monocular videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.07447 (2024)."},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00245"}],"event":{"name":"SIGGRAPH Conference Papers '25: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Vancouver BC Canada","acronym":"SIGGRAPH Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721238.3730699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T14:58:18Z","timestamp":1774018698000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721238.3730699"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":60,"alternative-id":["10.1145\/3721238.3730699","10.1145\/3721238"],"URL":"https:\/\/doi.org\/10.1145\/3721238.3730699","relation":{},"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}