{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T20:48:53Z","timestamp":1782334133091,"version":"3.54.5"},"reference-count":107,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC Project","award":["62521004"],"award-info":[{"award-number":["62521004"]}]},{"name":"Shanghai Municipal Science Technology Major Project","award":["2025SHZDZX025G02"],"award-info":[{"award-number":["2025SHZDZX025G02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tvcg.2026.3688720","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:47:34Z","timestamp":1777578454000},"page":"6842-6856","source":"Crossref","is-referenced-by-count":0,"title":["VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8324-1528","authenticated-orcid":false,"given":"Sixiao","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zimian","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanpeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9533-9546","authenticated-orcid":false,"given":"Xiangru","family":"Huang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, 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":"School of Data Science and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","first-page":"34630","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Guo","year":"2024"},{"key":"ref3","article-title":"VideoCrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref6","first-page":"100433","article-title":"CameraCtrl: Enabling camera control for video diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"He","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"ref9","first-page":"84807","article-title":"Training-free camera control for video generation","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Hou","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555384"},{"key":"ref13","first-page":"1","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Zhang","year":"2025"},{"key":"ref14","article-title":"RelightVid: Temporal-consistent diffusion model for video relighting","author":"Fang","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref18","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref21","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref22","first-page":"52208","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. 12th Int. Conf. Learn. Representations","volume":"2024","author":"Chen","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"ref25","article-title":"DragNUWA: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023"},{"key":"ref26","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref27","article-title":"Open-Sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref28","article-title":"Seedance 1.0: Exploring the boundaries of video generation models","author":"Gao","year":"2025"},{"key":"ref29","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025"},{"key":"ref30","first-page":"83048","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Yang","year":"2022"},{"key":"ref31","article-title":"Step-video-TI2V technical report: A state-of-the-art text-driven image-to-video generation model","author":"Huang","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0518"},{"key":"ref33","article-title":"CamCo: Camera-controllable 3d-consistent image-to-video generation","author":"Xu","year":"2024"},{"key":"ref34","first-page":"66712","article-title":"VD3D: Taming large video diffusion transformers for 3D camera control","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Bahmani","year":"2025"},{"key":"ref35","article-title":"CamI2V: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01246"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00083"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01271"},{"key":"ref40","first-page":"102934","article-title":"Trajectory attention for fine-grained video motion control","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Xiao","year":"2025"},{"key":"ref41","article-title":"EPiC: Efficient video camera control learning with precise anchor-video guidance","author":"Wang","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01241"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02673"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763842"},{"key":"ref49","article-title":"I2VControl-Camera: Precise video camera control with adjustable motion strength","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Feng","year":"2025"},{"key":"ref50","article-title":"MotionMaster: Training-free camera motion transfer for video generation","author":"Hu","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1082"},{"key":"ref52","article-title":"MotionClone: Training-free motion cloning for controllable video generation","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"2025","author":"Ling","year":"2025"},{"key":"ref53","article-title":"LightMotion: A light and tuning-free method for simulating camera motion in video generation","author":"Song","year":"2025"},{"key":"ref54","article-title":"MotionBridge: Dynamic video inbetweening with flexible controls","author":"Tanveer","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref56","article-title":"Motion dreamer: Realizing physically coherent video generation through scene-aware motion reasoning","author":"Xu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32533"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0586"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"ref62","article-title":"FreeTraj: Tuning-free trajectory control in video diffusion models","author":"Qiu","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687652"},{"key":"ref64","first-page":"38483","article-title":"SG-I2V: Self-guided trajectory control in image-to-video generation","volume-title":"Proc. 13th Int. Conf. Learn. Representations","volume":"2025","author":"Namekata","year":"2025"},{"key":"ref65","article-title":"Boximator: Generating rich and controllable motions for video synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wang","year":"2024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01126"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00198"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01165"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681567"},{"key":"ref71","article-title":"Mojito: Motion trajectory and intensity control for video generation","author":"He","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00195"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02810-6"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01334"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01304"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01052"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730755"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323008"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00729"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657470"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00517"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02371"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00659"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3095816"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687644"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02070"},{"key":"ref91","article-title":"LumiSculpt: A consistency lighting control network for video generation","author":"Zhang","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763970"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15147"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00088"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02007-9"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00595"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00084"},{"key":"ref98","article-title":"A new dimension in testimony: Relighting video with reflectance field exemplars","author":"Huynh","year":"2021"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01237"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref102","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01804"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00568"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02428"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11575570\/11502017.pdf?arnumber=11502017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T19:50:00Z","timestamp":1782330600000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11502017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":107,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2026.3688720","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}