{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:06:26Z","timestamp":1784228786562,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811224","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1116-4148","authenticated-orcid":false,"given":"Omar","family":"El Khalifi","sequence":"first","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9650-4783","authenticated-orcid":false,"given":"Thomas","family":"Rossi","sequence":"additional","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7426-8604","authenticated-orcid":false,"given":"Oscar","family":"Fossey","sequence":"additional","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5296-9366","authenticated-orcid":false,"given":"Thibault","family":"Fouque","sequence":"additional","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2795-2321","authenticated-orcid":false,"given":"Ulysse","family":"Mizrahi","sequence":"additional","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7072-3325","authenticated-orcid":false,"given":"Ivan","family":"Laptev","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5649","authenticated-orcid":false,"given":"Fabio","family":"Pizzati","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7062-6783","authenticated-orcid":false,"given":"Baptiste","family":"Bellot-Gurlet","sequence":"additional","affiliation":[{"name":"Kinetix, Paris, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"e_1_3_3_2_3_1","volume-title":"ICLR","author":"Bahmani Sherwin","year":"2025","unstructured":"Sherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace, Guocheng Qian, Michael Vasilkovsky, Hsin-Ying Lee, Chaoyang Wang, Jiaxu Zou, Andrea Tagliasacchi, et\u00a0al. 2025b. Vd3d: Taming large video diffusion transformers for 3d camera control. In ICLR."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"e_1_3_3_2_5_1","unstructured":"Chenjie Cao Jingkai Zhou Shikai Li Jingyun Liang Chaohui Yu Fan Wang Yanwei Fu and Xiangyang Xue. 2025. Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation. arXiv (2025)."},{"key":"e_1_3_3_2_6_1","volume-title":"IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen Handi","year":"2025","unstructured":"Handi Chen, Hongming Zhang, Tianyu Pang, Chao Du, and Min Lin. 2025. WorldScore: A Unified Evaluation Benchmark for World Generation. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_3_2_7_1","unstructured":"Gang Cheng Xin Gao Li Hu Siqi Hu Mingyang Huang Chaonan Ji Ju Li Dechao Meng Jinwei Qi Penchong Qiao Zhen Shen Yafei Song Ke Sun Linrui Tian Feng Wang Guangyuan Wang Qi Wang Zhongjian Wang Jiayu Xiao Sheng Xu Bang Zhang Peng Zhang et\u00a0al. 2025. Wan-Animate: Unified Character Animation and Replacement with Holistic Replication. arXiv (2025)."},{"key":"e_1_3_3_2_8_1","volume-title":"SIGGRAPH Asia","author":"Chu Honglin","year":"2024","unstructured":"Honglin Chu et\u00a0al. 2024. GVHMR: Human Motion Recovery via Gravity-View Coordinates. In SIGGRAPH Asia."},{"key":"e_1_3_3_2_9_1","volume-title":"International Conference on Learning Representations (ICLR)","author":"Courant Robin","year":"2026","unstructured":"Robin Courant, David Loiseaux, Xi Wang, Marc Christie, and Vicky Kalogeiton. 2026. Pulp Motion: Framing-aware multimodal camera and human motion generation. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_10_1","unstructured":"Qijun Gan Yi Ren Chen Zhang Zhenhui Ye Pan Xie Xiang Yin Zehuan Yuan Bingyue Peng and Jianke Zhu. 2025. Humandit: Pose-guided diffusion transformer for long-form human motion video generation. arXiv (2025)."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"e_1_3_3_2_13_1","volume-title":"ICLR","author":"Guo Yuwei","year":"2023","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2023. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In ICLR."},{"key":"e_1_3_3_2_14_1","volume-title":"ICLR","author":"He Hao","year":"2025","unstructured":"Hao He, Yinghao Xu, Yuwei Guo, Gordon Wetzstein, Bo Dai, Hongsheng Li, and Ceyuan Yang. 2025. Cameractrl: Enabling camera control for text-to-video generation. In ICLR."},{"key":"e_1_3_3_2_15_1","unstructured":"Chen Hou and Zhibo Chen. 2024. Training-free camera control for video generation. arXiv (2024)."},{"key":"e_1_3_3_2_16_1","volume-title":"CVPR","author":"Hu Li","year":"2024","unstructured":"Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, Liefeng Bo, et\u00a0al. 2024. Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation. In CVPR."},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02120"},{"key":"e_1_3_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_19_1","unstructured":"Ziqi Huang Fan Zhang Xiaojie Xu Yinan He Jiashuo Yu Ziyue Dong Qianli Ma Nattapol Chanpaisit Chenyang Si Yuming Jiang Yaohui Wang Xinyuan Chen Ying-Cong Chen Limin Wang Dahua Lin Yu Qiao and Ziwei Liu. 2024b. VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models. arXiv (2024)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Zeyinzi Jiang Zhen Han Chaojie Mao Jingfeng Zhang Yulin Pan Yu Liu et\u00a0al. 2025. VACE: All-in-One Video Creation and Editing. arXiv (2025).","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"e_1_3_3_2_21_1","volume-title":"\u201cOnly Gets Better Here\u201d: Elon Musk Reacts to AI-Generated Short Film Harry Potter Set in Vietnam War Going Viral","author":"Marzia Juhi","year":"2025","unstructured":"Juhi Marzia. 2025. \u201cOnly Gets Better Here\u201d: Elon Musk Reacts to AI-Generated Short Film Harry Potter Set in Vietnam War Going Viral. Sportskeeda. https:\/\/www.sportskeeda.com\/pop-culture\/news-only-gets-better-here-elon-musk-reacts-ai-generated-short-film-harry-potter-set-vietnam-war-goes-viral Accessed: 2026-01-22."},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Zhengfei Kuang Shengqu Cai Hao He Yinghao Xu Hongsheng Li Leonidas\u00a0J Guibas and Gordon Wetzstein. 2024. Collaborative video diffusion: Consistent multi-video generation with camera control. NeurIPS (2024).","DOI":"10.52202\/079017-0518"},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01639"},{"key":"e_1_3_3_2_24_1","unstructured":"Jingyun Liang Jingkai Zhou Shikai Li Chenjie Cao Lei Sun Yichen Qian Weihua Chen and Fan Wang. 2025. Realismotion: Decomposed human motion control and video generation in the world space. arXiv (2025)."},{"key":"e_1_3_3_2_25_1","unstructured":"Han Lin Jaemin Cho Abhay Zala and Mohit Bansal. 2024. Ctrl-adapter: An efficient and versatile framework for adapting diverse controls to any diffusion model. arXiv (2024)."},{"key":"e_1_3_3_2_26_1","unstructured":"Pengyang Ling Jiazi Bu Pan Zhang Xiaoyi Dong Yuhang Zang Tong Wu Huaian Chen Jiaqi Wang and Yi Jin. 2024. Motionclone: Training-free motion cloning for controllable video generation. arXiv (2024)."},{"key":"e_1_3_3_2_27_1","volume-title":"ECCV","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et\u00a0al. 2024. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In ECCV."},{"key":"e_1_3_3_2_28_1","volume-title":"ICLR","author":"Meng YOU","year":"2025","unstructured":"YOU Meng, Zhiyu Zhu, LIU Hui, and Junhui Hou. 2025. NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer. In ICLR."},{"key":"e_1_3_3_2_29_1","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. NeurIPS (2024).","DOI":"10.52202\/079017-0586"},{"key":"e_1_3_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01389"},{"key":"e_1_3_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02133"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Paul\u00a0D Sampson. 1982. Fitting conic sections to \u201cvery scattered\u201d data: An iterative refinement of the Bookstein algorithm. Computer graphics and image processing (1982).","DOI":"10.1016\/0146-664X(82)90101-0"},{"key":"e_1_3_3_2_34_1","volume-title":"ICLR","author":"Tan Shuai","year":"2024","unstructured":"Shuai Tan, Biao Gong, Xiang Wang, Shiwei Zhang, Dandan Zheng, Ruobing Zheng, Kecheng Zheng, Jingdong Chen, Ming Yang, et\u00a0al. 2024. Animate-X: Universal Character Image Animation with Enhanced Motion Representation. In ICLR."},{"key":"e_1_3_3_2_35_1","volume-title":"OpenAI Says It\u2019s Making a Full Hollywood Movie Using AI","author":"Tangermann Victor","year":"2025","unstructured":"Victor Tangermann. 2025. OpenAI Says It\u2019s Making a Full Hollywood Movie Using AI. https:\/\/futurism.com\/openai-full-hollywood-movie-using-ai Accessed: 2026-01-22."},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"S. Umeyama. 1991. Least-squares estimation of transformation parameters between two point patterns. IEEE T-PAMI (1991).","DOI":"10.1109\/34.88573"},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01156"},{"key":"e_1_3_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"e_1_3_3_2_39_1","unstructured":"Xiang Wang Shiwei Zhang Longxiang Tang Yingya Zhang Changxin Gao Yuehuan Wang Nong Sang et\u00a0al. 2025c. UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer. arXiv (2025)."},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0635"},{"key":"e_1_3_3_2_41_1","volume-title":"ECCV","author":"Wu Weijia","year":"2024","unstructured":"Weijia Wu, Zhuang Li, Yuchao Gu, Rui Zhao, Yefei He, David\u00a0Junhao Zhang, Mike\u00a0Zheng Shou, Yan Li, Tingting Gao, and Di Zhang. 2024. Draganything: Motion control for anything using entity representation. In ECCV."},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Zeqi Xiao Yifan Zhou Shuai Yang and Xingang Pan. 2024. Video diffusion models are training-free motion interpreter and controller. NeurIPS (2024).","DOI":"10.52202\/079017-2423"},{"key":"e_1_3_3_2_43_1","volume-title":"ICLR","author":"Xu Dejia","year":"2025","unstructured":"Dejia Xu, Weili Nie, Chao Liu, Sifei Liu, Jan Kautz, Zhangyang Wang, and Arash Vahdat. 2025a. Camco: Camera-controllable 3d-consistent image-to-video generation. In ICLR."},{"key":"e_1_3_3_2_44_1","unstructured":"Shuolin Xu Siming Zheng Ziyi Wang H.\u00a0C. Yu Jinwei Chen Huaqi Zhang Bo Li Peng-Tao Jiang et\u00a0al. 2025b. HyperMotion: DiT-Based Pose-Guided Human Image Animation of Complex Motions. arXiv (2025)."},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"e_1_3_3_2_47_1","unstructured":"Shengming Yin Chenfei Wu Jian Liang Jie Shi Houqiang Li Gong Ming and Nan Duan. 2023. Dragnuwa: Fine-grained control in video generation by integrating text image and trajectory. arXiv (2023)."},{"key":"e_1_3_3_2_48_1","unstructured":"Jiaming Zhang Shengming Cao Rui Li Xiaotong Zhao Yutao Cui Xinglin Hou Gangshan Wu Haolan Chen Yu Xu Limin Wang Kai Ma et\u00a0al. 2025a. SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation. arXiv (2025)."},{"key":"e_1_3_3_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_50_1","volume-title":"ICML","author":"Zhang Yuang","year":"2024","unstructured":"Yuang Zhang, Jiaxi Gu, Li-Wen Wang, Han Wang, Junqi Cheng, Yuefeng Zhu, Fangyuan Zou, et\u00a0al. 2024. MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance. In ICML."},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00198"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"},{"key":"e_1_3_3_2_53_1","unstructured":"Jingkai Zhou Yifan Wu Shikai Li Min Wei Chao Fan Weihua Chen Wei Jiang Fan Wang et\u00a0al. 2025b. RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild. arXiv (2025)."},{"key":"e_1_3_3_2_54_1","volume-title":"ECCV","author":"Zhu Shenhao","year":"2024","unstructured":"Shenhao Zhu, Junming\u00a0Leo Chen, Zuozhuo Dai, Zilong Dong, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, and Siyu Zhu. 2024. Champ: Controllable and consistent human image animation with 3d parametric guidance. In ECCV."}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:24:06Z","timestamp":1784226246000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":53,"alternative-id":["10.1145\/3799902.3811224","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811224","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}