{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T09:34:11Z","timestamp":1784194451129,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680950","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"3323-3331","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ANFluid: Animate Natural Fluid Photos base on Physics-Aware Simulation and Dual-Flow Texture Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3372-8441","authenticated-orcid":false,"given":"Xiangcheng","family":"Zhai","sequence":"first","affiliation":[{"name":"Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1674-4984","authenticated-orcid":false,"given":"Yingqi","family":"Jie","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1660-5691","authenticated-orcid":false,"given":"Xueguang","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5774-6706","authenticated-orcid":false,"given":"Aimin","family":"Hao","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2239-1121","authenticated-orcid":false,"given":"Na","family":"Jiang","sequence":"additional","affiliation":[{"name":"Capital Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9149-3554","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.388"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1186822.1073273"},{"key":"e_1_3_2_1_5_1","volume-title":"PhyVR: Physics-based Multi-material and Free-hand Interaction in VR. In 2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). 454--462","author":"Deng Hanchen","year":"2023","unstructured":"Hanchen Deng, Jin Li, Yang Gao, Xiaohui Liang, Hongyu Wu, and Aimin Hao. 2023. PhyVR: Physics-based Multi-material and Free-hand Interaction in VR. In 2023 IEEE International Symposium on Mixed and Augmented Reality (ISMAR). 454--462."},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 1174--1183","author":"Denton Emily","year":"2018","unstructured":"Emily Denton and Rob Fergus. 2018. Stochastic video generation with a learned prior. In International conference on machine learning. PMLR, 1174--1183."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tbench.2024.100152"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01459"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3107597"},{"key":"e_1_3_2_1_11_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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00575"},{"key":"e_1_3_2_1_13_1","first-page":"1","article-title":"Taichi: a language for high-performance computation on spatially sparse data structures","volume":"38","author":"Hu Yuanming","year":"2019","unstructured":"Yuanming Hu, Tzu-Mao Li, Luke Anderson, Jonathan Ragan-Kelley, and Fr\u00e9do Durand. 2019. Taichi: a language for high-performance computation on spatially sparse data structures. ACM Transactions on Graphics (TOG), Vol. 38, 6 (2019), 1--16.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_15_1","first-page":"14745","article-title":"Transgan: Two pure transformers can make one strong gan, and that can scale up","volume":"34","author":"Jiang Yifan","year":"2021","unstructured":"Yifan Jiang, Shiyu Chang, and Zhangyang Wang. 2021. Transgan: Two pure transformers can make one strong gan, and that can scale up. Advances in Neural Information Processing Systems, Vol. 34 (2021), 14745--14758.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 1558--1566","author":"Lindbo Larsen Anders Boesen","year":"2016","unstructured":"Anders Boesen Lindbo Larsen, S\u00f8ren Kaae S\u00f8nderby, Hugo Larochelle, and Ole Winther. 2016. Autoencoding beyond pixels using a learned similarity metric. In International conference on machine learning. PMLR, 1558--1566."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Animating still natural images using warping","volume":"19","author":"Le Ngoc-Hanh","year":"2023","unstructured":"Thi-Ngoc-Hanh Le, Chih-Kuo Yeh, Ying-Chi Lin, and Tong-Yee Lee. 2023. Animating still natural images using warping. ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 19, 1 (2023), 1--24.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"key":"e_1_3_2_1_18_1","volume-title":"MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction","author":"Li Jin","year":"2023","unstructured":"Jin Li, Yang Gao, Ju Dai, Shuai Li, Aimin Hao, and Hong Qin. 2023. MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction. IEEE Transactions on Visualization and Computer Graphics (2023), 1--14."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3359810"},{"key":"e_1_3_2_1_21_1","volume-title":"Occinpflow: Occlusion-inpainting optical flow estimation by unsupervised learning. arXiv preprint arXiv:2006.16637","author":"Luo Kunming","year":"2020","unstructured":"Kunming Luo, Chuan Wang, Nianjin Ye, Shuaicheng Liu, and Jue Wang. 2020. Occinpflow: Occlusion-inpainting optical flow estimation by unsupervised learning. arXiv preprint arXiv:2006.16637 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00365"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12276"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"e_1_3_2_1_26_1","volume-title":"Computer Graphics Forum","author":"Okabe Makoto","year":"1973","unstructured":"Makoto Okabe, Ken Anjyor, and Rikio Onai. 2011. Creating fluid animation from a single image using video database. In Computer Graphics Forum, Vol. 30. Wiley Online Library, 1973--1982."},{"key":"e_1_3_2_1_27_1","unstructured":"Runway Research. 2023. Gen-2: Generate novel videos with text images or video clips. https:\/\/runwayml.com\/research\/gen-2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_29_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention--MICCAI 2015: 18th international conference, Munich, Germany, October 5--9, 2015, proceedings, part III 18. Springer, 234--241."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0469(1975)0322.0.CO;2"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 12469--12480","author":"Qin Hongwei","year":"2023","unstructured":"Xiaoyu Shi, Zhaoyang Huang, Weikang Bian, Dasong Li, Manyuan Zhang, Ka Chun Cheung, Simon See, Hongwei Qin, Jifeng Dai, and Hongsheng Li. 2023. VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). 12469--12480."},{"key":"e_1_3_2_1_32_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_33_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3370551"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0338-4"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"e_1_3_2_1_40_1","volume-title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators. arXiv preprint arXiv:2404.05014","author":"Yuan Shenghai","year":"2024","unstructured":"Shenghai Yuan, Jinfa Huang, Yujun Shi, Yongqi Xu, Ruijie Zhu, Bin Lin, Xinhua Cheng, Li Yuan, and Jiebo Luo. 2024. MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators. arXiv preprint arXiv:2404.05014 (2024)."},{"key":"e_1_3_2_1_41_1","first-page":"18367","article-title":"Improved transformer for high-resolution gans","volume":"34","author":"Zhao Long","year":"2021","unstructured":"Long Zhao, Zizhao Zhang, Ting Chen, Dimitris Metaxas, and Han Zhang. 2021. Improved transformer for high-resolution gans. Advances in Neural Information Processing Systems, Vol. 34 (2021), 18367--18380.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073298"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680950","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:34Z","timestamp":1750295854000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":42,"alternative-id":["10.1145\/3664647.3680950","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680950","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}