{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:27:03Z","timestamp":1765254423219,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3764008","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DynVFX: Augmenting Real Videos with Dynamic Content"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4504-8192","authenticated-orcid":false,"given":"Danah","family":"Yatim","sequence":"first","affiliation":[{"name":"Weizmann Institute of Science, Rehovot, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1990-2948","authenticated-orcid":false,"given":"Rafail","family":"Fridman","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science, Rehovot, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1622-3674","authenticated-orcid":false,"given":"Omer","family":"Bar-Tal","sequence":"additional","affiliation":[{"name":"Runway ML, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3703-0783","authenticated-orcid":false,"given":"Tali","family":"Dekel","sequence":"additional","affiliation":[{"name":"Weizmann Institute of Science, Rehovot, Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023).","key":"e_1_3_3_2_2_1"},{"unstructured":"Adobe. 2024. After Effects. https:\/\/www.adobe.com\/products\/aftereffects.","key":"e_1_3_3_2_3_1"},{"unstructured":"Autodesk. 2024. Maya. https:\/\/autodesk.com\/maya.","key":"e_1_3_3_2_4_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_5_1","DOI":"10.1145\/3680528.3687614"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_6_1","DOI":"10.1007\/978-3-031-19784-0_41"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_7_1","DOI":"10.1145\/3721238.3730673"},{"unstructured":"Blender. 2024. VFX (Visual Effects). https:\/\/www.blender.org\/features\/vfx.","key":"e_1_3_3_2_8_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_9_1","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_2_10_1","first-page":"144","volume-title":"European Conference on Computer Vision","author":"Canberk Alper","year":"2024","unstructured":"Alper Canberk, Maksym Bondarenko, Ege Ozguroglu, Ruoshi Liu, and Carl Vondrick. 2024. EraseDraw: Learning to Insert Objects by Erasing Them from Images. In European Conference on Computer Vision. Springer, 144\u2013160."},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_11_1","DOI":"10.1109\/ICCV51070.2023.02062"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_12_1","DOI":"10.1109\/CVPR52733.2024.01265"},{"unstructured":"Yuren Cong Mengmeng Xu Christian Simon Shoufa Chen Jiawei Ren Yanping Xie Juan-Manuel Perez-Rua Bodo Rosenhahn Tao Xiang and Sen He. 2023. FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.05922 (2023).","key":"e_1_3_3_2_13_1"},{"doi-asserted-by":"crossref","unstructured":"Rinon Gal Or Patashnik Haggai Maron Amit\u00a0H Bermano Gal Chechik and Daniel Cohen-Or. 2022. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. ACM Transactions on Graphics (TOG) 41 4 (2022) 1\u201313.","key":"e_1_3_3_2_14_1","DOI":"10.1145\/3528223.3530164"},{"unstructured":"Michal Geyer Omer Bar-Tal Shai Bagon and Tali Dekel. 2023. TokenFlow: Consistent Diffusion Features for Consistent Video Editing. arXiv preprint arxiv:https:\/\/arXiv.org\/abs\/2307.10373 (2023).","key":"e_1_3_3_2_15_1"},{"unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851.","key":"e_1_3_3_2_16_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_17_1","DOI":"10.1109\/3DV66043.2025.00076"},{"unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. LoRA: Low-Rank Adaptation of Large Language Models. ICLR 1 2 (2022) 3.","key":"e_1_3_3_2_18_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_19_1","DOI":"10.1109\/CVPR52733.2024.02060"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_20_1","DOI":"10.1109\/CVPR52733.2024.00880"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_21_1","DOI":"10.1109\/ICCV51070.2023.01462"},{"unstructured":"KlingAI. 2024. KlingAI Platform. https:\/\/www.klingai.com.","key":"e_1_3_3_2_22_1"},{"unstructured":"Max Ku Cong Wei Weiming Ren Harry Yang and Wenhu Chen. 2024. AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14468 (2024).","key":"e_1_3_3_2_23_1"},{"unstructured":"Vladimir Kulikov Matan Kleiner Inbar Huberman-Spiegelglas and Tomer Michaeli. 2024. FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.08629 (2024).","key":"e_1_3_3_2_24_1"},{"key":"e_1_3_3_2_25_1","first-page":"14317","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lee Yao-Chih","year":"2023","unstructured":"Yao-Chih Lee, Ji-Ze Genevieve\u00a0Jang Jang, Yi-Ting Chen, Elizabeth Qiu, and Jia-Bin Huang. 2023. Shape-aware Text-driven Layered Video Editing Demo. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14317\u201314326."},{"unstructured":"Long Lian Baifeng Shi Adam Yala Trevor Darrell and Boyi Li. 2023. LLM-grounded Video Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.17444 (2023).","key":"e_1_3_3_2_26_1"},{"unstructured":"Han Lin Abhay Zala Jaemin Cho and Mohit Bansal. 2023. VideoDirectorGPT: Consistent Multi-Scene Video Generation via LLM-Guided Planning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.15091 (2023).","key":"e_1_3_3_2_27_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_28_1","DOI":"10.1145\/3680528.3687664"},{"key":"e_1_3_3_2_29_1","first-page":"1634","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Materzy\u0144ska Joanna","year":"2024","unstructured":"Joanna Materzy\u0144ska, Josef Sivic, Eli Shechtman, Antonio Torralba, Richard Zhang, and Bryan Russell. 2024. NewMove: Customizing text-to-video models with novel motions. In Proceedings of the Asian Conference on Computer Vision. 1634\u20131651."},{"key":"e_1_3_3_2_30_1","volume-title":"International Conference on Learning Representations","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 International Conference on Learning Representations."},{"doi-asserted-by":"crossref","unstructured":"Chong Mou Mingdeng Cao Xintao Wang Zhaoyang Zhang Ying Shan and Jian Zhang. 2024. ReVideo: Remake a Video with Motion and Content Control. Advances in Neural Information Processing Systems 37 (2024) 18481\u201318505.","key":"e_1_3_3_2_31_1","DOI":"10.52202\/079017-0586"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_32_1","DOI":"10.1145\/3680528.3687656"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_33_1","DOI":"10.1609\/aaai.v39i6.32685"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_34_1","DOI":"10.1109\/ICCV51070.2023.00387"},{"unstructured":"Pika. 2024. Pika AI Art. https:\/\/pika.art.","key":"e_1_3_3_2_35_1"},{"unstructured":"Jordi Pont-Tuset Federico Perazzi Sergi Caelles Pablo Arbel\u00e1ez Alex Sorkine-Hornung and Luc Van\u00a0Gool. 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1704.00675 (2017).","key":"e_1_3_3_2_36_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_37_1","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"e_1_3_3_2_38_1","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. PmLR, 8748\u20138763."},{"unstructured":"Runway. 2024. RunwayML. https:\/\/runwayml.com.","key":"e_1_3_3_2_39_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_40_1","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"e_1_3_3_2_41_1","first-page":"2256","volume-title":"International conference on machine learning","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\u20132265."},{"key":"e_1_3_3_2_42_1","volume-title":"International Conference on Learning Representations","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. In International Conference on Learning Representations."},{"doi-asserted-by":"crossref","unstructured":"Jianlin Su Murtadha Ahmed Yu Lu Shengfeng Pan Wen Bo and Yunfeng Liu. 2024. RoFormer: Enhanced Transformer with Rotary Position Embedding. Neurocomputing 568 (2024) 127063.","key":"e_1_3_3_2_43_1","DOI":"10.1016\/j.neucom.2023.127063"},{"unstructured":"Yoad Tewel Rinon Gal Dvir Samuel Yuval Atzmon Lior Wolf and Gal Chechik. 2024a. Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.07232 (2024).","key":"e_1_3_3_2_44_1"},{"doi-asserted-by":"crossref","unstructured":"Yoad Tewel Omri Kaduri Rinon Gal Yoni Kasten Lior Wolf Gal Chechik and Yuval Atzmon. 2024b. Training-Free Consistent Text-to-Image Generation. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201318.","key":"e_1_3_3_2_45_1","DOI":"10.1145\/3658157"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_46_1","DOI":"10.1145\/3721238.3730647"},{"unstructured":"Unreal Engine. 2024. Unreal Engine. https:\/\/www.unrealengine.com.","key":"e_1_3_3_2_47_1"},{"unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. Advances in neural information processing systems 30 (2017).","key":"e_1_3_3_2_48_1"},{"unstructured":"Xiang Wang Hangjie Yuan Shiwei Zhang Dayou Chen Jiuniu Wang Yingya Zhang Yujun Shen Deli Zhao and Jingren Zhou. 2023. VideoComposer: Compositional Video Synthesis with Motion Controllability. Advances in Neural Information Processing Systems 36 (2023) 7594\u20137611.","key":"e_1_3_3_2_49_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_50_1","DOI":"10.1109\/CVPR52734.2025.01707"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_51_1","DOI":"10.1007\/978-3-031-72980-5_7"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_52_1","DOI":"10.1109\/ICCV51070.2023.00701"},{"unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024. 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_53_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_54_1","DOI":"10.1109\/CVPR52733.2024.00809"},{"doi-asserted-by":"crossref","unstructured":"Emilie Yu Kevin Blackburn-Matzen Cuong Nguyen Oliver Wang Rubaiat Habib\u00a0Kazi and Adrien Bousseau. 2023. VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases. ACM Transactions on Graphics (TOG) 42 4 (2023) 1\u201312.","key":"e_1_3_3_2_55_1","DOI":"10.1145\/3592413"},{"unstructured":"Kai Zhang Lingbo Mo Wenhu Chen Huan Sun and Yu Su. 2023. MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing. Advances in Neural Information Processing Systems 36 (2023) 31428\u201331449.","key":"e_1_3_3_2_56_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_57_1","DOI":"10.1109\/CVPR52733.2024.00862"},{"unstructured":"Yuxuan Zhang Tianheng Cheng Rui Hu Lei Liu Heng Liu Longjin Ran Xiaoxin Chen Wenyu Liu and Xinggang Wang. 2024a. EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.20076 (2024).","key":"e_1_3_3_2_58_1"},{"key":"e_1_3_3_2_59_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang Yabo","year":"2024","unstructured":"Yabo Zhang, Yuxiang Wei, Dongsheng Jiang, XIAOPENG ZHANG, Wangmeng Zuo, and Qi Tian. 2024b. ControlVideo: Training-free Controllable Text-to-video Generation. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=5a79AqFr0c"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_60_1","DOI":"10.1109\/CVPR52733.2024.00684"},{"key":"e_1_3_3_2_61_1","first-page":"273","volume-title":"European Conference on Computer Vision","author":"Zhao Rui","year":"2024","unstructured":"Rui Zhao, Yuchao Gu, Jay\u00a0Zhangjie Wu, David\u00a0Junhao Zhang, Jia-Wei Liu, Weijia Wu, Jussi Keppo, and Mike\u00a0Zheng Shou. 2024. Motiondirector: Motion customization of text-to- video diffusion models. In European Conference on Computer Vision. Springer, 273\u2013290."},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_62_1","DOI":"10.1007\/978-3-030-96530-3"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_63_1","DOI":"10.1609\/aaai.v39i10.33203"}],"event":{"sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"],"acronym":"SA Conference Papers '25","name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong"},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3764008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:24:35Z","timestamp":1765250675000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3764008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":62,"alternative-id":["10.1145\/3757377.3764008","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3764008","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"}}]}}