{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:10:15Z","timestamp":1784268615431,"version":"3.55.0"},"reference-count":100,"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\/501100014219","name":"National Science Foundation for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62225605"],"award-info":[{"award-number":["62225605"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["12326608"],"award-info":[{"award-number":["12326608"]}],"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\/iccv51701.2025.02673","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"28785-28796","source":"Crossref","is-referenced-by-count":4,"title":["RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control"],"prefix":"10.1109","author":[{"given":"Teng","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangcong","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuigen","family":"Zhan","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehao","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yining","family":"Lin","sequence":"additional","affiliation":[{"name":"Supremind"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanyun","family":"Deng","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,2012 Lab,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yepan","family":"Xiong","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,2012 Lab,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,2012 Lab,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Cheng","sequence":"additional","affiliation":[{"name":"Central Media Technology Institute,2012 Lab,Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science & Technology, Zhejiang University"}],"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"},{"key":"ref3","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3687945"},{"key":"ref8","article-title":"Motion-zero: Zero-shot moving object control framework for diffusion-based video generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02190"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref13","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2023"},{"key":"ref14","article-title":"Vchitect-2.0: Parallel transformer for scaling up video diffusion models","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","author":"Feng","year":"2024","journal-title":"I2vcontrol-camera: Precise video camera control with adjustable motion strength"},{"key":"ref16","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"key":"ref18","article-title":"Emu video: Factorizing text-to-video generation by explicit image conditioning","author":"Girdhar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Atomovideo: High fidelity image-to-video generation","author":"Gong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref22","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00220"},{"key":"ref24","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Training-free camera control for video generation","author":"Hou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref29","article-title":"Motionmaster: Training-free camera motion transfer for video generation","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Vbench++: Comprehensive and versatile benchmark suite for video generative models","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00772"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3814-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00639"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1551"},{"key":"ref35","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Collaborative video diffusion: Consistent multivideo generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Personalvideo: High id-fidelity video customization without dynamic and semantic degradation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Image conductor: Precision control for interactive video synthesis","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref40","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref44","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arXiv preprint","author":"Meng","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref46","article-title":"Lindell. Sg-i2v: Selfguided trajectory control in image-to-video generation","author":"Namekata","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Openvid-1m: A large-scale high-quality dataset for text-tovideo generation","author":"Nan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Global Structure-from-Motion Revisited","volume-title":"European Conference on Computer Vision (ECCV)","author":"Pan","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref50","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref52","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref55","article-title":"Repvideo: Rethinking crosslayer representation for video generation","author":"Si","year":"2025","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0707"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"ref61","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00789"},{"key":"ref64","first-page":"arXiv-2307","article-title":"Disco: Disentangled control for referring human dance generation in real world","author":"Wang","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2026.3668653"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref70","article-title":"Fleet. Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Motionbooth: Motion-aware customized text-tovideo generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28429"},{"key":"ref73","article-title":"Videomaker: Zero-shot customized video generation with the inherent force of video diffusion models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"ref75","article-title":"Ifadapter: Instance feature con-trol for grounded text-to-image generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Dynamicrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Cavia: Camera-controllable multi-view video diffusion with view-integrated attention","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","article-title":"Camco: Camera-controllable 3d-consistent image-to-video generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref80","author":"Yang","year":"2024","journal-title":"Depth anything v2"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref82","article-title":"Cogvideox: Text-tovideo diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref84","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref85","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Efficient video diffusion models via content-frame motion-latent decomposition","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref88","article-title":"Moonshot: Towards controllable video generation and editing with multi-modal conditions","author":"Junhao Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref89","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref91","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","volume-title":"arXiv preprint","author":"Zhang","year":"2023"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref93","article-title":"3d object manipulation in a single image using generative models","author":"Zhao","year":"2025","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_43"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref96","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref97","article-title":"Realcam-vid: High-resolution video dataset with dynamic scenes and metric-scale camera movements","author":"Zheng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref98","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref99","author":"Zhou","year":"2018","journal-title":"Open3D: A modern library for 3D data processing"},{"key":"ref100","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\/11444614.pdf?arnumber=11444614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:05Z","timestamp":1777612025000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02673","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}