{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:07Z","timestamp":1776931147869,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763952","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:27:29Z","timestamp":1765211249000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-572X","authenticated-orcid":false,"given":"Guoxian","family":"Song","sequence":"first","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4455-5632","authenticated-orcid":false,"given":"Hongyi","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8976-7723","authenticated-orcid":false,"given":"Xiaochen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-6518","authenticated-orcid":false,"given":"You","family":"Xie","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3173-8895","authenticated-orcid":false,"given":"Tianpei","family":"Gu","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7794-5358","authenticated-orcid":false,"given":"Zenan","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1971-1975","authenticated-orcid":false,"given":"Chenxu","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6322-1175","authenticated-orcid":false,"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"ByteDance, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_2_2_1","volume-title":"Forty-first International Conference on Machine Learning","author":"Chang Di","year":"2023","unstructured":"Di Chang, Yichun Shi, Quankai Gao, Hongyi Xu, Jessica Fu, Guoxian Song, Qing Yan, Yizhe Zhu, Xiao Yang, and Mohammad Soleymani. 2023. MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_2_3_1","unstructured":"MMPose Contributors. 2020. OpenMMLab Pose Estimation Toolbox and Benchmark. https:\/\/github.com\/open-mmlab\/mmpose."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_3_2_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et\u00a0al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_2_6_1","volume-title":"Forty-first international conference on machine learning","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 Forty-first international conference on machine learning."},{"key":"e_1_3_3_2_7_1","first-page":"8153","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu Li","year":"2024","unstructured":"Li Hu. 2024. Animate anyone: Consistent and controllable image-to-video synthesis for character animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8153\u20138163."},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"crossref","unstructured":"Rawal Khirodkar Timur Bagautdinov Julieta Martinez Su Zhaoen Austin James Peter Selednik Stuart Anderson and Shunsuke Saito. 2024. Sapiens: Foundation for Human Vision Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.12569 (2024).","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"e_1_3_3_2_10_1","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang Kathrina Wu Qin Lin Aladdin Wang Andong Wang Changlin Li Duojun Huang Fang Yang Hao Tan Hongmei Wang Jacob Song Jiawang Bai Jianbing Wu Jinbao Xue Joey Wang Junkun Yuan Kai Wang Mengyang Liu Pengyu Li Shuai Li Weiyan Wang Wenqing Yu Xinchi Deng Yang Li Yanxin Long Yi Chen Yutao Cui Yuanbo Peng Zhentao Yu Zhiyu He Zhiyong Xu Zixiang Zhou Zunnan Xu Yangyu Tao Qinglin Lu Songtao Liu Dax Zhou Hongfa Wang Yong Yang Di Wang Yuhong Liu Jie Jiang and Caesar Zhong. 2024. HunyuanVideo: A Systematic Framework For Large Video Generative Models. https:\/\/arxiv.org\/abs\/2412.03603"},{"key":"e_1_3_3_2_11_1","unstructured":"Kuaishou. 2024. Kling ai. https:\/\/klingai.kuaishou.com\/. Accessed: 2025-05-19."},{"key":"e_1_3_3_2_12_1","unstructured":"Gaojie Lin Jianwen Jiang Jiaqi Yang Zerong Zheng and Chao Liang. 2025a. OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.01061 (2025)."},{"key":"e_1_3_3_2_13_1","unstructured":"Shanchuan Lin Ceyuan Yang Hao He Jianwen Jiang Yuxi Ren Xin Xia Yang Zhao Xuefeng Xiao and Lu Jiang. 2025b. Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09350 (2025)."},{"key":"e_1_3_3_2_14_1","unstructured":"Yuxuan Luo Zhengkun Rong Lizhen Wang Longhao Zhang Tianshu Hu and Yongming Zhu. 2025. DreamActor-M1: Holistic Expressive and Robust Human Image Animation with Hybrid Guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.01724 (2025)."},{"key":"e_1_3_3_2_15_1","unstructured":"Midjourney. 2024. midjourney. https:\/\/www.midjourney.com (2024)."},{"key":"e_1_3_3_2_16_1","unstructured":"mixamo. 2024. mixamo. https:\/\/www.mixamo.com\/\/ (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"Alex Nichol Prafulla Dhariwal Aditya Ramesh Pranav Shyam Pamela Mishkin Bob McGrew Ilya Sutskever and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.10741 (2021)."},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_2_19_1","unstructured":"William Peebles and Saining Xie. 2023. Scalable Diffusion Models with Transformers. arxiv:https:\/\/arXiv.org\/abs\/2212.09748\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2212.09748"},{"key":"e_1_3_3_2_20_1","unstructured":"Pexels. 2024. pexels. https:\/\/www.pexels.com\/ (2024)."},{"key":"e_1_3_3_2_21_1","unstructured":"Adam Polyak Amit Zohar Andrew Brown Andros Tjandra Animesh Sinha Ann Lee Apoorv Vyas Bowen Shi Chih-Yao Ma Ching-Yao Chuang David Yan Dhruv Choudhary Dingkang Wang Geet Sethi Guan Pang Haoyu Ma Ishan Misra Ji Hou Jialiang Wang Kiran Jagadeesh Kunpeng Li Luxin Zhang Mannat Singh Mary Williamson Matt Le Matthew Yu Mitesh\u00a0Kumar Singh Peizhao Zhang Peter Vajda Quentin Duval Rohit Girdhar Roshan Sumbaly Sai\u00a0Saketh Rambhatla Sam Tsai Samaneh Azadi Samyak Datta Sanyuan Chen Sean Bell Sharadh Ramaswamy Shelly Sheynin Siddharth Bhattacharya Simran Motwani Tao Xu Tianhe Li Tingbo Hou Wei-Ning Hsu Xi Yin Xiaoliang Dai Yaniv Taigman Yaqiao Luo Yen-Cheng Liu Yi-Chiao Wu Yue Zhao Yuval Kirstain Zecheng He Zijian He Albert Pumarola Ali Thabet Artsiom Sanakoyeu Arun Mallya Baishan Guo Boris Araya Breena Kerr Carleigh Wood Ce Liu Cen Peng Dimitry Vengertsev Edgar Schonfeld Elliot Blanchard Felix Juefei-Xu Fraylie Nord Jeff Liang John Hoffman Jonas Kohler Kaolin Fire Karthik Sivakumar Lawrence Chen Licheng Yu Luya Gao Markos Georgopoulos Rashel Moritz Sara\u00a0K. Sampson Shikai Li Simone Parmeggiani Steve Fine Tara Fowler Vladan Petrovic and Yuming Du. 2025. Movie Gen: A Cast of Media Foundation Models. arxiv:https:\/\/arXiv.org\/abs\/2410.13720\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2410.13720"},{"key":"e_1_3_3_2_22_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical Text-Conditional Image Generation with CLIP Latents. arxiv:https:\/\/arXiv.org\/abs\/2204.06125\u00a0[cs.CV]"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_24_1","unstructured":"Chitwan Saharia William Chan Saurabh Saxena Lala Li Jay Whang Emily\u00a0L Denton Kamyar Ghasemipour Raphael Gontijo\u00a0Lopes Burcu Karagol\u00a0Ayan Tim Salimans et\u00a0al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems 35 (2022) 36479\u201336494."},{"key":"e_1_3_3_2_25_1","unstructured":"Team Seawead Ceyuan Yang Zhijie Lin Yang Zhao Shanchuan Lin Zhibei Ma Haoyuan Guo Hao Chen Lu Qi Sen Wang et\u00a0al. 2025. Seaweed-7b: Cost-effective training of video generation foundation model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.08685 (2025)."},{"key":"e_1_3_3_2_26_1","unstructured":"Aliaksandr Siarohin St\u00e9phane Lathuili\u00e8re Sergey Tulyakov Elisa Ricci and Nicu Sebe. 2019. First order motion model for image animation. NeurIPS (2019)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"e_1_3_3_2_28_1","unstructured":"Shuai Tan Biao Gong Xiang Wang Shiwei Zhang Dandan Zheng Ruobing Zheng Kecheng Zheng Jingdong Chen and Ming Yang. 2024. Animate-x: Universal character image animation with enhanced motion representation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.10306 (2024)."},{"key":"e_1_3_3_2_29_1","unstructured":"Shuai Tan Biao Gong Xiang Wang Shiwei Zhang Dandan Zheng Ruobing Zheng Kecheng Zheng Jingdong Chen and Ming Yang. 2025. Animate-X: Universal Character Image Animation with Enhanced Motion Representation. ICLR 2025 (2025)."},{"key":"e_1_3_3_2_30_1","unstructured":"Wan Team. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. (2025)."},{"key":"e_1_3_3_2_31_1","unstructured":"Naftali Tishby Fernando\u00a0C Pereira and William Bialek. 2000. The information bottleneck method. arXiv preprint physics\/0004057 (2000)."},{"key":"e_1_3_3_2_32_1","unstructured":"Zhengyan Tong Chao Li Zhaokang Chen Bin Wu and Wenjiang Zhou. 2024. MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation. arxiv (2024)."},{"key":"e_1_3_3_2_33_1","unstructured":"Team Wan Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang 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_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681567"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01724"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_3_2_37_1","unstructured":"Xiang Wang Shiwei Zhang Longxiang Tang Yingya Zhang Changxin Gao Yuehuan Wang and Nong Sang. 2025. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.11289 (2025)."},{"key":"e_1_3_3_2_38_1","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Wang Zhenzhi","year":"2024","unstructured":"Zhenzhi Wang, Yixuan Li, Yanhong Zeng, Youqing Fang, Yuwei Guo, Wenran Liu, Jing Tan, Kai Chen, Tianfan Xue, Bo Dai, et\u00a0al. 2024. Humanvid: Demystifying training data for camera-controllable human image animation. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"e_1_3_3_2_40_1","unstructured":"Zhongcong Xu Chaoyue Song Guoxian Song Jianfeng Zhang Jun\u00a0Hao Liew Hongyi Xu You Xie Linjie Luo Guosheng Lin Jiashi Feng et\u00a0al. 2024a. High Quality Human Image Animation using Regional Supervision and Motion Blur Condition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.19580 (2024)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_2_42_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_43_1","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_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02138"},{"key":"e_1_3_3_2_45_1","unstructured":"Yuang Zhang Jiaxi Gu Li-Wen Wang Han Wang Junqi Cheng Yuefeng Zhu and Fangyuan Zou. 2024. Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.19680 (2024)."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"e_1_3_3_2_47_1","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhao Xiaochen","year":"2025","unstructured":"Xiaochen Zhao, Hongyi Xu, Guoxian Song, You Xie, Chenxu Zhang, Xiu Li, Linjie Luo, Jinli Suo, and Yebin Liu. 2025. X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_3_2_48_1","unstructured":"Shenhao Zhu Junming\u00a0Leo Chen Zuozhuo Dai Yinghui Xu Xun Cao Yao Yao Hao Zhu and Siyu Zhu. 2024. Champ: Controllable and consistent human image animation with 3d parametric guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.14781 (2024)."}],"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\/3757377.3763952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:25:53Z","timestamp":1765250753000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":47,"alternative-id":["10.1145\/3757377.3763952","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763952","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"}}]}}