{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T03:29:19Z","timestamp":1785382159159,"version":"3.55.0"},"reference-count":69,"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":["62441615,62225603,U21B2004,62476241"],"award-info":[{"award-number":["62441615,62225603,U21B2004,62476241"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LZ23F020008"],"award-info":[{"award-number":["LZ23F020008"]}],"id":[{"id":"10.13039\/501100004731","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\/iccv51701.2025.01376","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14834-14844","source":"Crossref","is-referenced-by-count":8,"title":["Recammaster: Camera-Controlled Generative Rendering From a Single Video"],"prefix":"10.1109","author":[{"given":"Jianhong","family":"Bai","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menghan","family":"Xia","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Fu","sequence":"additional","affiliation":[{"name":"CUHK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianrui","family":"Mu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwen","family":"Cao","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuozhu","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoji","family":"Hu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"HUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology,Kling Team"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02130"},{"key":"ref2","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref3","article-title":"Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints","author":"Bai","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref5","article-title":"Gs-dit: Advancing video generation with pseudo 4d gaussian fields through efficient dense 3d point tracking","author":"Bian","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Follow-your-canvas: Higher-resolution video outpainting with extensive content generation","author":"Chen","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"International Conference on Machine Learning (ICML)","author":"Esser"},{"key":"ref10","volume-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref11","article-title":"3dtrajmaster: Mastering 3d trajectory for multi-entity motion in video generation","author":"Fu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref12","volume-title":"Unreal engine 5","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref17","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref18","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref19","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref22","article-title":"Motionmaster: Training-free camera motion transfer for video generation","author":"Hu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.381"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref27","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma"},{"key":"ref28","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00981"},{"key":"ref30","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref31","article-title":"Flow matching for generative modeling","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lipman"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_22"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24894\/sprengglossarium_g09306"},{"key":"ref42","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref43","article-title":"Ominicontrol: Minimal and universal control for diffusion transformer","author":"Tan","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref44","article-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019","journal-title":"Openreview"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2884280"},{"key":"ref48","article-title":"Video-tovideo synthesis","volume-title":"arxiv preprint arxiv","author":"Wang","year":"2018"},{"key":"ref49","article-title":"Few-shot video-to-video synthesis","volume-title":"arxiv preprint arxiv","author":"Wang","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.008"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref54","article-title":"Trajectory attention for fine-grained video motion control","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xiao"},{"key":"ref55","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref57","article-title":"Camco: Cameracontrollable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00205"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3687919"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref62","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref63","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref64","article-title":"Trajectorycrafter: Redirecting camera trajectory for monocular videos via diffusion models","author":"Mark","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00197"},{"key":"ref66","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref67","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref68","article-title":"Vidcraft3: Camera, object, and lighting control for image-to-video generation","author":"Zheng","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00245"}],"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\/11444064.pdf?arnumber=11444064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:41Z","timestamp":1777529981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01376","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}