{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T18:11:43Z","timestamp":1791051103555,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":88,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62132001"],"award-info":[{"award-number":["62132001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763885","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1883-0777","authenticated-orcid":false,"given":"Zehuan","family":"Huang","sequence":"first","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0770-361X","authenticated-orcid":false,"given":"Haoran","family":"Feng","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6370-1603","authenticated-orcid":false,"given":"Yang-Tian","family":"Sun","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6164-8343","authenticated-orcid":false,"given":"Yuan-Chen","family":"Guo","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-4374","authenticated-orcid":false,"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"VAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-9163","authenticated-orcid":false,"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"crossref","unstructured":"Andreas Aristidou and Joan Lasenby. 2011. FABRIK: A fast iterative solver for the Inverse Kinematics problem. Graphical Models 73 5 (2011) 243\u2013260.","DOI":"10.1016\/j.gmod.2011.05.003"},{"key":"e_1_3_3_2_4_1","volume-title":"k-means++: The advantages of careful seeding","author":"Arthur David","year":"2006","unstructured":"David Arthur and Sergei Vassilvitskii. 2006. k-means++: The advantages of careful seeding. Technical Report. Stanford."},{"key":"e_1_3_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01381"},{"key":"e_1_3_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_4"},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"e_1_3_3_2_8_1","unstructured":"Jianhong Bai Menghan Xia Xintao Wang Ziyang Yuan Xiao Fu Zuozhu Liu Haoji Hu Pengfei Wan and Di Zhang. 2024. SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.07760 (2024)."},{"key":"e_1_3_3_2_9_1","unstructured":"Fan Bao Chendong Xiang Gang Yue Guande He Hongzhou Zhu Kaiwen Zheng Min Zhao Shilong Liu Yaole Wang and Jun Zhu. 2024. Vidu: a highly consistent dynamic and skilled text-to-video generator with diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.04233 (2024)."},{"key":"e_1_3_3_2_10_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023a. 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_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"e_1_3_3_2_13_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_14_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et\u00a0al. 2023b. 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_15_1","doi-asserted-by":"publisher","unstructured":"Jianqi Chen Biao Zhang Xiangjun Tang and Peter Wonka. 2025. V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video. CoRR abs\/2503.09631 (2025). 10.48550\/ARXIV.2503.09631 arXiv:https:\/\/arXiv.org\/abs\/2503.09631","DOI":"10.48550\/ARXIV.2503.09631"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"crossref","unstructured":"Matt Deitke Ruoshi Liu Matthew Wallingford Huong Ngo Oscar Michel Aditya Kusupati Alan Fan Christian Laforte Vikram Voleti Samir\u00a0Yitzhak Gadre et\u00a0al. 2023a. Objaverse-xl: A universe of 10m+ 3d objects. Advances in Neural Information Processing Systems 36 (2023) 35799\u201335813.","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_3_2_20_1","unstructured":"Adobe Family. 2022. Mixamo. https:\/\/www.mixamo.com\/ (2022)."},{"key":"e_1_3_3_2_21_1","unstructured":"Ruiqi Gao Aleksander Holynski Philipp Henzler Arthur Brussee Ricardo Martin-Brualla Pratul Srinivasan Jonathan\u00a0T Barron and Ben Poole. 2024. Cat3d: Create anything in 3d with multi-view diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.10314 (2024)."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Inbar Gat Sigal Raab Guy Tevet Yuval Reshef Amit\u00a0H Bermano and Daniel Cohen-Or. 2025. AnyTop: Character Animation Diffusion with Any Topology. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.17327 (2025).","DOI":"10.1145\/3721238.3730621"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_3_2_24_1","volume-title":"ICLR","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In ICLR."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/861369"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"crossref","unstructured":"Richard\u00a0I Hartley and Peter Sturm. 1997. Triangulation. Computer vision and image understanding 68 2 (1997) 146\u2013157.","DOI":"10.1006\/cviu.1997.0547"},{"key":"e_1_3_3_2_27_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_28_1","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022. Video diffusion models. Advances in Neural Information Processing Systems 35 (2022) 8633\u20138646."},{"key":"e_1_3_3_2_29_1","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685 (2021)."},{"key":"e_1_3_3_2_30_1","unstructured":"Zehuan Huang Yuan-Chen Guo Haoran Wang Ran Yi Lizhuang Ma Yan-Pei Cao and Lu Sheng. 2024a. Mv-adapter: Multi-view consistent image generation made easy. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03632 (2024)."},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00934"},{"key":"e_1_3_3_2_33_1","unstructured":"VRoid Hub. 2022. VRoid. https:\/\/vroid.com\/ (2022)."},{"key":"e_1_3_3_2_34_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023","author":"Jiang Biao","year":"2023","unstructured":"Biao Jiang, Xin Chen, Wen Liu, Jingyi Yu, Gang Yu, and Tao Chen. 2023. MotionGPT: Human Motion as a Foreign Language. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/3fbf0c1ea0716c03dea93bb6be78dd6f-Abstract-Conference.html"},{"key":"e_1_3_3_2_35_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","author":"Jiang Yanqin","year":"2024","unstructured":"Yanqin Jiang, Chaohui Yu, Chenjie Cao, Fan Wang, Weiming Hu, and Jin Gao. 2024a. Animate3D: Animating Any 3D Model with Multi-view Video Diffusion. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub\u00a0M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/e3b53f89136b1bc69a5714ea465f01b6-Abstract-Conference.html"},{"key":"e_1_3_3_2_36_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Jiang Yanqin","year":"2024","unstructured":"Yanqin Jiang, Li Zhang, Jin Gao, Weiming Hu, and Yao Yao. 2024b. Consistent4D: Consistent 360\u00b0 Dynamic Object Generation from Monocular Video. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=sPUrdFGepF"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00192"},{"key":"e_1_3_3_2_38_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_39_1","unstructured":"Black\u00a0Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_3_2_40_1","unstructured":"Jiaman Li C\u00a0Karen Liu and Jiajun Wu. 2024. Lifting Motion to the 3D World via 2D Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.18808 (2024)."},{"key":"e_1_3_3_2_41_1","unstructured":"Xuan Li Qianli Ma Tsung-Yi Lin Yongxin Chen Chenfanfu Jiang Ming-Yu Liu and Donglai Xiang. 2025. Articulated Kinematics Distillation from Video Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.01204 (2025)."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3519"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","unstructured":"Tianqi Liu Zihao Huang Zhaoxi Chen Guangcong Wang Shoukang Hu Liao Shen Huiqiang Sun Zhiguo Cao Wei Li and Ziwei Liu. 2025. Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency. CoRR abs\/2503.20785 (2025). 10.48550\/ARXIV.2503.20785 arXiv:https:\/\/arXiv.org\/abs\/2503.20785","DOI":"10.48550\/ARXIV.2503.20785"},{"key":"e_1_3_3_2_46_1","unstructured":"Yuan Liu Cheng Lin Zijiao Zeng Xiaoxiao Long Lingjie Liu Taku Komura and Wenping Wang. 2023. Syncdreamer: Generating multiview-consistent images from a single-view image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.03453 (2023)."},{"key":"e_1_3_3_2_47_1","doi-asserted-by":"publisher","unstructured":"Matthew Loper Naureen Mahmood Javier Romero Gerard Pons-Moll and Michael\u00a0J. Black. 2015. SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34 6 (2015) 248:1\u2013248:16. 10.1145\/2816795.2818013","DOI":"10.1145\/2816795.2818013"},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Giulia Martinelli Nicola Garau Niccol\u00f3 Bisagno and Nicola Conci. 2024. MoMa: Skinned motion retargeting using masked pose modeling. Computer Vision and Image Understanding 249 (2024) 104141.","DOI":"10.1016\/j.cviu.2024.104141"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","unstructured":"Marc Bened\u00ed\u00a0San Mill\u00e1n Angela Dai and Matthias Nie\u00dfner. 2025. Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models. CoRR abs\/2503.15996 (2025). 10.48550\/ARXIV.2503.15996 arXiv:https:\/\/arXiv.org\/abs\/2503.15996","DOI":"10.48550\/ARXIV.2503.15996"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","unstructured":"Huaijin Pi Ruoxi Guo Zehong Shen Qing Shuai Zechen Hu Zhumei Wang Yajiao Dong Ruizhen Hu Taku Komura Sida Peng and Xiaowei Zhou. 2024. Motion-2-to-3: Leveraging 2D Motion Data to Boost 3D Motion Generation. CoRR abs\/2412.13111 (2024). 10.48550\/ARXIV.2412.13111 arXiv:https:\/\/arXiv.org\/abs\/2412.13111","DOI":"10.48550\/ARXIV.2412.13111"},{"key":"e_1_3_3_2_54_1","unstructured":"Dustin Podell Zion English Kyle Lacey Andreas Blattmann Tim Dockhorn Jonas M\u00fcller Joe Penna and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.01952 (2023)."},{"key":"e_1_3_3_2_55_1","unstructured":"Ben Poole Ajay Jain Jonathan\u00a0T Barron and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.14988 (2022)."},{"key":"e_1_3_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"e_1_3_3_2_57_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"publisher","unstructured":"Jiawei Ren Liang Pan Jiaxiang Tang Chi Zhang Ang Cao Gang Zeng and Ziwei Liu. 2023. DreamGaussian4D: Generative 4D Gaussian Splatting. CoRR abs\/2312.17142 (2023). 10.48550\/ARXIV.2312.17142 arXiv:https:\/\/arXiv.org\/abs\/2312.17142","DOI":"10.48550\/ARXIV.2312.17142"},{"key":"e_1_3_3_2_59_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","author":"Ren Jiawei","year":"2024","unstructured":"Jiawei Ren, Cheng Xie, Ashkan Mirzaei, Hanxue Liang, Xiaohui Zeng, Karsten Kreis, Ziwei Liu, Antonio Torralba, Sanja Fidler, Seung\u00a0Wook Kim, and Huan Ling. 2024. L4GM: Large 4D Gaussian Reconstruction Model. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub\u00a0M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/6808f2c57d9564a2639a4710e3bbd9b9-Abstract-Conference.html"},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_61_1","unstructured":"Yahao Shi Yang Liu Yanmin Wu Xing Liu Chen Zhao Jie Luo and Bin Zhou. 2025. Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.07489 (2025)."},{"key":"e_1_3_3_2_62_1","unstructured":"Yichun Shi Peng Wang Jianglong Ye Mai Long Kejie Li and Xiao Yang. 2023. Mvdream: Multi-view diffusion for 3d generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.16512 (2023)."},{"key":"e_1_3_3_2_63_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Singer Uriel","year":"2022","unstructured":"Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, et\u00a0al. 2022. Make-A-Video: Text-to-Video Generation without Text-Video Data. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_64_1","unstructured":"Vincent Sitzmann Semon Rezchikov Bill Freeman Josh Tenenbaum and Fredo Durand. 2021. Light field networks: Neural scene representations with single-evaluation rendering. Advances in Neural Information Processing Systems 34 (2021) 19313\u201319325."},{"key":"e_1_3_3_2_65_1","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.","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_3_2_66_1","doi-asserted-by":"publisher","unstructured":"Qi Sun Zhiyang Guo Ziyu Wan Jing\u00a0Nathan Yan Shengming Yin Wengang Zhou Jing Liao and Houqiang Li. 2024. EG4D: Explicit Generation of 4D Object without Score Distillation. CoRR abs\/2405.18132 (2024). 10.48550\/ARXIV.2405.18132 arXiv:https:\/\/arXiv.org\/abs\/2405.18132","DOI":"10.48550\/ARXIV.2405.18132"},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"e_1_3_3_2_68_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit\u00a0Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"e_1_3_3_2_69_1","doi-asserted-by":"publisher","unstructured":"Lukas Uzolas Elmar Eisemann and Petr Kellnhofer. 2024. MotionDreamer: Zero-Shot 3D Mesh Animation from Video Diffusion Models. CoRR abs\/2405.20155 (2024). 10.48550\/ARXIV.2405.20155 arXiv:https:\/\/arXiv.org\/abs\/2405.20155","DOI":"10.48550\/ARXIV.2405.20155"},{"key":"e_1_3_3_2_70_1","unstructured":"Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng et\u00a0al. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_2_71_1","doi-asserted-by":"crossref","unstructured":"Hao Wen Zehuan Huang Yaohui Wang Xinyuan Chen Yu Qiao and Lu Sheng. 2024. Ouroboros3d: Image-to-3d generation via 3d-aware recursive diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.03184 (2024).","DOI":"10.1109\/CVPR52734.2025.02015"},{"key":"e_1_3_3_2_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"e_1_3_3_2_73_1","unstructured":"Zijie Wu Chaohui Yu Fan Wang and Xiang Bai. 2025. AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09982 (2025)."},{"key":"e_1_3_3_2_74_1","doi-asserted-by":"publisher","unstructured":"Yiming Xie Chun-Han Yao Vikram Voleti Huaizu Jiang and Varun Jampani. 2024. SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency. CoRR abs\/2407.17470 (2024). 10.48550\/ARXIV.2407.17470 arXiv:https:\/\/arXiv.org\/abs\/2407.17470","DOI":"10.48550\/ARXIV.2407.17470"},{"key":"e_1_3_3_2_75_1","first-page":"399","volume-title":"European Conference on Computer Vision","author":"Xing Jinbo","year":"2024","unstructured":"Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2024. Dynamicrafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision. Springer, 399\u2013417."},{"key":"e_1_3_3_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00775"},{"key":"e_1_3_3_2_77_1","doi-asserted-by":"publisher","unstructured":"Zeyu Yang Zijie Pan Chun Gu and Li Zhang. 2024b. Diffusion2: Dynamic 3D Content Generation via Score Composition of Orthogonal Diffusion Models. CoRR abs\/2404.02148 (2024). 10.48550\/ARXIV.2404.02148 arXiv:https:\/\/arXiv.org\/abs\/2404.02148","DOI":"10.48550\/ARXIV.2404.02148"},{"key":"e_1_3_3_2_78_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024c. 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_79_1","unstructured":"Chun-Han Yao Yiming Xie Vikram Voleti Huaizu Jiang and Varun Jampani. 2025. SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.16396 (2025)."},{"key":"e_1_3_3_2_80_1","unstructured":"Jiwen Yu Xiaodong Cun Chenyang Qi Yong Zhang Xintao Wang Ying Shan and Jian Zhang. 2023. Animatezero: Video diffusion models are zero-shot image animators. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.03793 (2023)."},{"key":"e_1_3_3_2_81_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"e_1_3_3_2_82_1","unstructured":"Hao Zhang Di Chang Fang Li Mohammad Soleymani and Narendra Ahuja. 2024b. Magicpose4d: Crafting articulated models with appearance and motion control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.14017 (2024)."},{"key":"e_1_3_3_2_83_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","author":"Zhang Haiyu","year":"2024","unstructured":"Haiyu Zhang, Xinyuan Chen, Yaohui Wang, Xihui Liu, Yunhong Wang, and Yu Qiao. 2024c. 4Diffusion: Multi-view Video Diffusion Model for 4D Generation. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub\u00a0M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/1bbfea488a8968e2d3c6565639b08e5e-Abstract-Conference.html"},{"key":"e_1_3_3_2_84_1","doi-asserted-by":"publisher","unstructured":"Jia-Qi Zhang Xiang Xu Zhi-Meng Shen Zehuan Huang Yang Zhao Yan-Pei Cao Pengfei Wan and Miao Wang. 2021. Write-An-Animation: High-level Text-based Animation Editing with Character-Scene Interaction. Comput. Graph. Forum 40 7 (2021) 217\u2013228. 10.1111\/CGF.14415","DOI":"10.1111\/CGF.14415"},{"key":"e_1_3_3_2_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"e_1_3_3_2_86_1","doi-asserted-by":"publisher","unstructured":"Mingyuan Zhang Zhongang Cai Liang Pan Fangzhou Hong Xinying Guo Lei Yang and Ziwei Liu. 2024a. MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model. IEEE Trans. Pattern Anal. Mach. Intell. 46 6 (2024) 4115\u20134128. 10.1109\/TPAMI.2024.3355414","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"e_1_3_3_2_87_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"e_1_3_3_2_88_1","doi-asserted-by":"publisher","unstructured":"Yuyang Zhao Chung-Ching Lin Kevin Lin Zhiwen Yan Linjie Li Zhengyuan Yang Jianfeng Wang Gim\u00a0Hee Lee and Lijuan Wang. 2024. GenXD: Generating Any 3D and 4D Scenes. CoRR abs\/2411.02319 (2024). 10.48550\/ARXIV.2411.02319 arXiv:https:\/\/arXiv.org\/abs\/2411.02319","DOI":"10.48550\/ARXIV.2411.02319"},{"key":"e_1_3_3_2_89_1","doi-asserted-by":"publisher","unstructured":"Hanxin Zhu Tianyu He Xiqian Yu Junliang Guo Zhibo Chen and Jiang Bian. 2025. AR4D: Autoregressive 4D Generation from Monocular Videos. CoRR abs\/2501.01722 (2025). 10.48550\/ARXIV.2501.01722 arXiv:https:\/\/arXiv.org\/abs\/2501.01722","DOI":"10.48550\/ARXIV.2501.01722"}],"event":{"name":"SA Conference Papers '25: SIGGRAPH Asia 2025 Conference Papers","location":"Hong Kong Hong Kong","acronym":"SA Conference Papers '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the SIGGRAPH Asia 2025 Conference Papers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3757377.3763885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:27:12Z","timestamp":1765250832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":88,"alternative-id":["10.1145\/3757377.3763885","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763885","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"}}]}}