{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:32:21Z","timestamp":1765254741522,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763917","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-2220","authenticated-orcid":false,"given":"Dvir","family":"Samuel","sequence":"first","affiliation":[{"name":"Bar-Ilan University, Ramat-Gan, Israel and OriginAI, Ramat-Gan, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2915-1618","authenticated-orcid":false,"given":"Matan","family":"Levy","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem, Jerusalem, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0652-9519","authenticated-orcid":false,"given":"Nir","family":"Darshan","sequence":"additional","affiliation":[{"name":"OriginAI, Tel-Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9164-5303","authenticated-orcid":false,"given":"Gal","family":"Chechik","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Tel-Aviv, Israel and Bar-Ilan University, Tel-Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7162-7351","authenticated-orcid":false,"given":"Rami","family":"Ben-Ari","sequence":"additional","affiliation":[{"name":"OriginAI, Tel-Aviv, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Omer Bar-Tal Hila Chefer Omer Tov Charles Herrmann Roni Paiss Shiran Zada Ariel Ephrat Junhwa Hur Guanghui Liu Amit Raj Yuanzhen Li Michael Rubinstein Tomer Michaeli Oliver Wang Deqing Sun Tali Dekel and Inbar Mosseri. 2024. Lumiere: A Space-Time Diffusion Model for Video Generation.","DOI":"10.1145\/3680528.3687614"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Yuxuan Bian Zhaoyang Zhang Xuan Ju Mingdeng Cao Liangbin Xie Ying Shan and Qiang Xu. 2025. VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control. SIGGRAPH (2025).","DOI":"10.1145\/3721238.3730673"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00916"},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566572"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"crossref","unstructured":"A. Criminisi P. Perez and K. Toyama. 2004. Region filling and object removal by exemplar-based image inpainting. IEEE Transactions on Image Processing (2004).","DOI":"10.1109\/TIP.2004.833105"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00923"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_42"},{"key":"e_1_3_3_2_10_1","unstructured":"Zeqi Gu Wenqi Xian Noah Snavely and Abe Davis. 2023. FactorMatte: Redefining Video Matting for Re-Composition Tasks. ACM Transactions on Graphics (TOG) (2023)."},{"key":"e_1_3_3_2_11_1","unstructured":"Yoav HaCohen Nisan Chiprut Benny Brazowski Daniel Shalem David-Pur Moshe Eitan Richardson E.\u00a0I. Levin Guy Shiran Nir Zabari Ori Gordon Poriya Panet Sapir Weissbuch Victor Kulikov Yaki Bitterman Zeev Melumian and Ofir Bibi. 2024. LTX-Video: Realtime Video Latent Diffusion. ArXiv (2024)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_3"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Yoni Kasten Dolev Ofri Oliver Wang and Tali Dekel. 2021. Layered neural atlases for consistent video editing. ACM Transactions on Graphics (TOG) 40 6 (2021) 1\u201312.","DOI":"10.1145\/3478513.3480546"},{"key":"e_1_3_3_2_14_1","volume-title":"Gestalt psychology: The definitive statement of the Gestalt theory","author":"K\u00f6hler Wolfgang","year":"1992","unstructured":"Wolfgang K\u00f6hler. 1992. Gestalt psychology: The definitive statement of the Gestalt theory. H. Liveright."},{"key":"e_1_3_3_2_15_1","unstructured":"Weijie Kong. 2024. HunyuanVideo: A Systematic Framework For Large Video Generative Models."},{"key":"e_1_3_3_2_16_1","unstructured":"Yao-Chih Lee Erika Lu Sarah Rumbley Michal Geyer Jia-Bin Huang Tali Dekel and Forrester Cole. 2024. Generative Omnimatte: Learning to Decompose Video into Layers. CVPR (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"Xiaowen Li Haolan Xue Peiran Ren and Liefeng Bo. 2025. DiffuEraser: A Diffusion Model for Video Inpainting."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02145"},{"key":"e_1_3_3_2_19_1","volume-title":"NeurIPS","author":"Lu Erika","year":"2022","unstructured":"Erika Lu, Forrester Cole, Tali Dekel, Weidi Xie, Andrew Zisserman, William\u00a0T Freeman, and Michael Rubinstein. 2022. Associating Objects and Their Effects in Video Through Coordination Games. In NeurIPS."},{"key":"e_1_3_3_2_20_1","unstructured":"Erika Lu Forrester Cole Tali Dekel Weidi Xie Andrew Zisserman David Salesin William\u00a0T Freeman and Michael Rubinstein. 2020. Layered neural rendering for retiming people in video. arXiv:https:\/\/arXiv.org\/abs\/2009.07833 (2020)."},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00448"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_3_2_23_1","unstructured":"Yang Luo Xuanlei Zhao Mengzhao Chen Kaipeng Zhang Wenqi Shao Kai Wang Zhangyang Wang and Yang You. 2025. Enhance-A-Video: Better Generated Video for Free. ArXiv (2025)."},{"key":"e_1_3_3_2_24_1","volume-title":"ICLR","author":"Meng Chenlin","year":"2022","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, and Stefano Ermon. 2022. SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations. In ICLR."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"crossref","unstructured":"Nobuyuki Otsu. 1979. A Threshold Selection Method from Gray-Level Histograms. IEEE Trans. Syst. Man Cybern. (1979).","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00068"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Wan video. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. https:\/\/github.com\/Wan-Video\/Wan2.1.","DOI":"10.1109\/ICASSP49660.2025.10888491"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015232"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"crossref","unstructured":"J.Y.A. Wang and E.H. Adelson. 1994. Representing moving images with layers. IEEE Transactions on Image Processing (1994).","DOI":"10.1109\/83.334981"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315022"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Daniel Winter Matan Cohen Shlomi Fruchter Yael Pritch Alex Rav-Acha and Yedid Hoshen. 2024. ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion.","DOI":"10.1007\/978-3-031-72980-5_7"},{"key":"e_1_3_3_2_33_1","unstructured":"Tianhao Wu Fangcheng Zhong Andrea Tagliasacchi Forrester Cole and Cengiz Oztireli. 2024. D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video."},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_5"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00589"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00961"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25"},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:31:32Z","timestamp":1765251092000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":35,"alternative-id":["10.1145\/3757377.3763917","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763917","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]},"assertion":[{"value":"2025-12-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}