{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:25Z","timestamp":1784268685937,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,15]]},"DOI":"10.1145\/3757377.3763842","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:30:41Z","timestamp":1765211441000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3916-2843","authenticated-orcid":false,"given":"Chenjie","family":"Cao","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China and Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4629-0659","authenticated-orcid":false,"given":"Jingkai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9674-2556","authenticated-orcid":false,"given":"Shikai","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9841-8584","authenticated-orcid":false,"given":"Jingyun","family":"Liang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7852-4491","authenticated-orcid":false,"given":"Chaohui","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7320-1119","authenticated-orcid":false,"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4897-9209","authenticated-orcid":false,"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-6893","authenticated-orcid":false,"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China and Shanghai Innovation Institute, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,14]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"e_1_3_3_3_4_1","volume-title":"International Conference on Learning Representations","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 International Conference on Learning Representations."},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"e_1_3_3_3_7_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et\u00a0al. 2023. 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_3_8_1","unstructured":"Aleksei Bochkovskii Ama\u00ebl Delaunoy Hugo Germain Marcel Santos Yichao Zhou Stephan\u00a0R. Richter and Vladlen Koltun. 2024. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second. arXiv (2024). https:\/\/arxiv.org\/abs\/2410.02073"},{"key":"e_1_3_3_3_9_1","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman Clarence Ng Ricky Wang and Aditya Ramesh. 2024. Video generation models as world simulators. (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"e_1_3_3_3_10_1","volume-title":"International Conference on Learning Representations","author":"Cao Chenjie","year":"2024","unstructured":"Chenjie Cao, Xinlin Ren, and Yanwei Fu. 2024. MVSFormer++: Revealing the Devil in Transformer\u2019s Details for Multi-View Stereo. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00567"},{"key":"e_1_3_3_3_12_1","unstructured":"Yingjie Chen Yifang Men Yuan Yao Miaomiao Cui and Liefeng Bo. 2025. Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.05020 (2025)."},{"key":"e_1_3_3_3_13_1","unstructured":"Hyung\u00a0Won Chung Noah Constant Xavier Garcia Adam Roberts Yi Tay Sharan Narang and Orhan Firat. 2023. Unimax: Fairer and more effective language sampling for large-scale multilingual pretraining. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.09151 (2023)."},{"key":"e_1_3_3_3_14_1","volume-title":"International Conference on Learning Representations","author":"Feng Wanquan","year":"2025","unstructured":"Wanquan Feng, Jiawei Liu, Pengqi Tu, Tianhao Qi, Mingzhen Sun, Tianxiang Ma, Songtao Zhao, Siyu Zhou, and Qian He. 2025. I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"e_1_3_3_3_16_1","unstructured":"Zekai Gu Rui Yan Jiahao Lu Peng Li Zhiyang Dou Chenyang Si Zhen Dong Qifeng Liu Cheng Lin Ziwei Liu et\u00a0al. 2025. Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03847 (2025)."},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"e_1_3_3_3_19_1","volume-title":"International Conference on Learning Representations","author":"He Hao","year":"2025","unstructured":"Hao He, Yinghao Xu, Yuwei Guo, Gordon Wetzstein, Bo Dai, Hongsheng Li, and Ceyuan Yang. 2025a. Cameractrl: Enabling camera control for text-to-video generation. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_20_1","unstructured":"Hao He Ceyuan Yang Shanchuan Lin Yinghao Xu Meng Wei Liangke Gui Qi Zhao Gordon Wetzstein Lu Jiang and Hongsheng Li. 2025b. CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10592 (2025)."},{"key":"e_1_3_3_3_21_1","volume-title":"International Conference on Learning Representations","author":"Hou Chen","year":"2025","unstructured":"Chen Hou, Guoqiang Wei, Yan Zeng, and Zhibo Chen. 2025. Training-free camera control for video generation. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_22_1","volume-title":"International Conference on Learning Representations","author":"Hu Edward\u00a0J","year":"2022","unstructured":"Edward\u00a0J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_23_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_3_24_1","unstructured":"Li Hu Guangyuan Wang Zhen Shen Xin Gao Dechao Meng Lian Zhuo Peng Zhang Bang Zhang and Liefeng Bo. 2025. Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06145 (2025)."},{"key":"e_1_3_3_3_25_1","unstructured":"Ziqi Huang Fan Zhang Xiaojie Xu Yinan He Jiashuo Yu Ziyue Dong Qianli Ma Nattapol Chanpaisit Chenyang Si Yuming Jiang et\u00a0al. 2024. Vbench++: Comprehensive and versatile benchmark suite for video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.13503 (2024)."},{"key":"e_1_3_3_3_26_1","unstructured":"Biao Jiang Xin Chen Wen Liu Jingyi Yu Gang Yu and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2023) 20067\u201320079."},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00642"},{"key":"e_1_3_3_3_28_1","doi-asserted-by":"crossref","unstructured":"Arno Knapitsch Jaesik Park Qian-Yi Zhou and Vladlen Koltun. 2017. Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Transactions on Graphics (ToG) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00103"},{"key":"e_1_3_3_3_30_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_3_31_1","unstructured":"Kuaishou. 2024. Kling. https:\/\/klingai.kuaishou.com (2024)."},{"key":"e_1_3_3_3_32_1","unstructured":"Teng Li Guangcong Zheng Rui Jiang Tao Wu Yehao Lu Yining Lin Xi Li et\u00a0al. 2025b. RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.10059 (2025)."},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"crossref","unstructured":"Hanwen Liang Junli Cao Vidit Goel Guocheng Qian Sergei Korolev Demetri Terzopoulos Konstantinos\u00a0N Plataniotis Sergey Tulyakov and Jian Ren. 2024. Wonderland: Navigating 3D Scenes from a Single Image. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.12091 (2024).","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"e_1_3_3_3_35_1","unstructured":"Jing Lin Ailing Zeng Shunlin Lu Yuanhao Cai Ruimao Zhang Haoqian Wang and Lei Zhang. 2023. Motion-x: A large-scale 3d expressive whole-body human motion dataset. Advances in Neural Information Processing Systems 36 (2023) 25268\u201325280."},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"e_1_3_3_3_37_1","unstructured":"Yaron Lipman Ricky\u00a0TQ Chen Heli Ben-Hamu Maximilian Nickel and Matt Le. 2022. Flow matching for generative modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.02747 (2022)."},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"e_1_3_3_3_39_1","unstructured":"Xingchen Liu Piyush Tayal Jianyuan Wang Jesus Zarzar Tom Monnier Konstantinos Tertikas Jiali Duan Antoine Toisoul Jason\u00a0Y Zhang Natalia Neverova et\u00a0al. 2025. UnCommon Objects in 3D. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.07574 (2025)."},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"crossref","unstructured":"Matthias Plappert Christian Mandery and Tamim Asfour. 2016. The kit motion-language dataset. Big data 4 4 (2016) 236\u2013252.","DOI":"10.1089\/big.2016.0028"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"crossref","unstructured":"Stefan Popov Amit Raj Michael Krainin Yuanzhen Li William\u00a0T Freeman and Michael Rubinstein. 2025. CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.06006 (2025).","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"e_1_3_3_3_46_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."},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_50_1","unstructured":"RunwayML. 2024. Gen-3 Alpha. https:\/\/runwayml.com\/research\/ introducing-gen-3-alpha (2024)."},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687565"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00473"},{"key":"e_1_3_3_3_54_1","unstructured":"Wenqiang Sun Shuo Chen Fangfu Liu Zilong Chen Yueqi Duan Jun Zhang and Yikai Wang. 2024. Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.04928 (2024)."},{"key":"e_1_3_3_3_55_1","volume-title":"International Conference on Learning Representations","author":"Tan Shuai","year":"2025","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. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_56_1","first-page":"197","volume-title":"European conference on computer vision","author":"Tung Joseph","year":"2024","unstructured":"Joseph Tung, Gene Chou, Ruojin Cai, Guandao Yang, Kai Zhang, Gordon Wetzstein, Bharath Hariharan, and Noah Snavely. 2024. Megascenes: Scene-level view synthesis at scale. In European conference on computer vision. Springer, 197\u2013214."},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"crossref","unstructured":"Shinji Umeyama. 1991. Least-squares estimation of transformation parameters between two point patterns. IEEE Transactions on Pattern Analysis & Machine Intelligence 13 04 (1991) 376\u2013380.","DOI":"10.1109\/34.88573"},{"key":"e_1_3_3_3_58_1","first-page":"1","volume-title":"European Conference on Computer Vision","author":"Veicht Alexander","year":"2024","unstructured":"Alexander Veicht, Paul-Edouard Sarlin, Philipp Lindenberger, and Marc Pollefeys. 2024. GeoCalib: Learning Single-image Calibration with Geometric Optimization. In European Conference on Computer Vision. Springer, 1\u201320."},{"key":"e_1_3_3_3_59_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. 2025a. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"crossref","unstructured":"Wenshan Wang Delong Zhu Xiangwei Wang Yaoyu Hu Yuheng Qiu Chen Wang Yafei Hu Ashish Kapoor and Sebastian Scherer. 2020. TartanAir: A Dataset to Push the Limits of Visual SLAM. (2020).","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"e_1_3_3_3_62_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. 2024a. 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_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"e_1_3_3_3_65_1","volume-title":"International Conference on Learning Representations","author":"Xu Yinghao","year":"2024","unstructured":"Yinghao Xu, Hao Tan, Fujun Luan, Sai Bi, Peng Wang, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, and Kai Zhang. 2024a. DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"crossref","unstructured":"Yufei Xu Jing Zhang Qiming Zhang and Dacheng Tao. 2023. Vitpose++: Vision transformer for generic body pose estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 2 (2023) 1212\u20131230.","DOI":"10.1109\/TPAMI.2023.3330016"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"e_1_3_3_3_69_1","volume-title":"International Conference on Learning Representations","author":"Yang Zhuoyi","year":"2025","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et\u00a0al. 2025. Cogvideox: Text-to-video diffusion models with an expert transformer. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_70_1","volume-title":"International Conference on Learning Representations","author":"You Meng","year":"2025","unstructured":"Meng You, Zhiyu Zhu, Hui Liu, and Junhui Hou. 2025. Nvs-solver: Video diffusion model as zero-shot novel view synthesizer. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_71_1","unstructured":"Wangbo Yu Jinbo Xing Li Yuan Wenbo Hu Xiaoyu Li Zhipeng Huang Xiangjun Gao Tien-Tsin Wong Ying Shan and Yonghong Tian. 2024. Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02048 (2024)."},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"e_1_3_3_3_74_1","volume-title":"International Conference on Learning Representations","author":"Zheng Guangcong","year":"2025","unstructured":"Guangcong Zheng, Teng Li, Rui Jiang, Yehao Lu, Tao Wu, and Xi Li. 2025a. Cami2v: Camera-controlled image-to-video diffusion model. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_75_1","unstructured":"Sixiao Zheng Zimian Peng Yanpeng Zhou Yi Zhu Hang Xu Xiangru Huang and Yanwei Fu. 2025b. VidCRAFT3: Camera Object and Lighting Control for Image-to-Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.07531 (2025)."},{"key":"e_1_3_3_3_76_1","unstructured":"Jingkai Zhou Benzhi Wang Weihua Chen Jingqi Bai Dongyang Li Aixi Zhang Hao Xu Mingyang Yang and Fan Wang. 2024. RealisDance: Equip controllable character animation with realistic hands. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.06202 (2024)."},{"key":"e_1_3_3_3_77_1","unstructured":"Jingkai Zhou Yifan Wu Shikai Li Min Wei Chao Fan Weihua Chen Wei Jiang and Fan Wang. 2025b. RealisDance-DiT: Simple yet Strong Baseline towards Controllable Character Animation in the Wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.14977 (2025)."},{"key":"e_1_3_3_3_78_1","unstructured":"Jensen\u00a0Jinghao Zhou Hang Gao Vikram Voleti Aaryaman Vasishta Chun-Han Yao Mark Boss Philip Torr Christian Rupprecht and Varun Jampani. 2025a. STABLE VIRTUAL CAMERA: Generative View Synthesis with Diffusion Models. arXiv e-prints (2025) arXiv\u20132503."},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","unstructured":"Tinghui Zhou Richard Tucker John Flynn Graham Fyffe and Noah Snavely. 2018. Stereo magnification: learning view synthesis using multiplane images. ACM Trans. Graph. 37 4 Article 65 (July 2018) 12\u00a0pages. 10.1145\/3197517.3201323","DOI":"10.1145\/3197517.3201323"},{"key":"e_1_3_3_3_80_1","first-page":"145","volume-title":"European Conference on Computer Vision","volume":"15113","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 European Conference on Computer Vision , Vol.\u00a015113. 145\u2013162."}],"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\/3757377.3763842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T03:30:16Z","timestamp":1765251016000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3757377.3763842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":79,"alternative-id":["10.1145\/3757377.3763842","10.1145\/3757377"],"URL":"https:\/\/doi.org\/10.1145\/3757377.3763842","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"}}]}}