{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:19Z","timestamp":1777889119175,"version":"3.51.4"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472104,62276067"],"award-info":[{"award-number":["62472104,62276067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01157","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12449-12458","source":"Crossref","is-referenced-by-count":2,"title":["Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation"],"prefix":"10.1109","author":[{"given":"Xincheng","family":"Shuai","sequence":"first","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyuan","family":"Qin","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjun","family":"Ma","sequence":"additional","affiliation":[{"name":"Fudan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VD3D: taming large video diffusion transformers for 3d camera control","volume-title":"ICLR","author":"Bahmani","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref4","article-title":"Motion-Zero: Zero-shot moving object control framework for diffusion-based video generation","author":"Chen","year":"2024","journal-title":"arXiv"},{"key":"ref5","article-title":"InternVL: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"CVPR","author":"Chen","year":"2024"},{"key":"ref6","article-title":"Objaversexl: A universe of $10 \\mathrm{m}+3 \\mathrm{d}$ objects","volume-title":"NeurIPS","author":"Deitke","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00254"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01850"},{"key":"ref10","article-title":"3DTrajMaster: Mastering 3d trajectory for multi-entity motion in video generation","volume-title":"ICLR","author":"Fu","year":"2025"},{"key":"ref11","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref12","article-title":"CameraCtrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv"},{"key":"ref13","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref14","article-title":"Imagen Video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv"},{"key":"ref15","article-title":"Video diffusion models","volume-title":"NeurIPS","author":"Ho","year":"2022"},{"key":"ref16","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arXiv"},{"key":"ref17","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref18","article-title":"MotionMaster: Training-free camera motion transfer for video generation","volume-title":"ACM MM","author":"Hu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"ref20","article-title":"DreamMotion: Space-time self-similarity score distillation for zero-shot video editing","volume-title":"ECCV","author":"Jeong","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00880"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01607","article-title":"AnyI2V: Animating any conditional image with motion control generation","volume-title":"ICCV","author":"Li","year":"2025"},{"key":"ref24","article-title":"MotionClone: Training-free motion cloning for controllable video generation","volume-title":"ICLR","author":"Ling","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687652"},{"key":"ref26","volume-title":"Mixamo","year":"2022"},{"key":"ref27","article-title":"FreeTraj: Tuning-free trajectory control in video diffusion models","author":"Qiu","year":"2024","journal-title":"arXiv"},{"key":"ref28","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref32","article-title":"LAION400 M: open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv"},{"key":"ref33","author":"Seitzer","year":"2020","journal-title":"pytorch-fid: FID Score for PyTorch"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref35","article-title":"A survey of multi-modal-guided image editing with text-to-image diffusion models","author":"Shuai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref37","article-title":"DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras","volume-title":"NeurIPS","author":"Teed","year":"2021"},{"key":"ref38","volume-title":"Bradcatt: Toonyou","year":"2024"},{"key":"ref39","volume-title":"Unreal Engine 5","year":"2022"},{"key":"ref40","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv"},{"key":"ref41","volume-title":"Realistic Vision","year":"2023"},{"key":"ref42","article-title":"Motion inversion for video customization","author":"Wang","year":"2024","journal-title":"arXiv"},{"key":"ref43","article-title":"CharaConsist: Finegrained consistent character generation","author":"Wang","year":"2025","journal-title":"ICCV"},{"key":"ref44","article-title":"VideoComposer: Compositional video synthesis with motion control-lability","volume-title":"NeurIPS","author":"Wang","year":"2023"},{"key":"ref45","article-title":"Score-based generative modeling through backward stochastic differential equations: Inversion and generation","volume-title":"ICLR","author":"Wang","year":"2021"},{"key":"ref46","article-title":"HumanVid: Demystifying training data for camera-controllable human image animation","volume-title":"NeurIPS","author":"Wang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref48","article-title":"MotionBooth: Motion-aware customized text-tovideo generation","volume-title":"NeurIPS","author":"Wu","year":"2024"},{"key":"ref49","article-title":"CamCo: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv"},{"key":"ref50","article-title":"Depth anything V2","volume-title":"NeurIPS","author":"Yang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01855"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref54","article-title":"DragNUWA: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref57","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52729.2023.00883","article-title":"MVImgNet: A largescale dataset of multi-view images","volume-title":"CVPR","author":"Yu","year":"2023"},{"key":"ref58","article-title":"I2VGen-XL: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"ref59","article-title":"Tora: Trajectory-oriented diffusion transformer for video generation","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444744.pdf?arnumber=11444744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:18Z","timestamp":1777612038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01157","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}