{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:02:44Z","timestamp":1784268164350,"version":"3.55.0"},"reference-count":46,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01153","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12405-12414","source":"Crossref","is-referenced-by-count":14,"title":["Stable Virtual Camera: Generative View Synthesis with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Jensen","family":"Zhou","sequence":"first","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Gao","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikram","family":"Voleti","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaryaman","family":"Vasishta","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Han","family":"Yao","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Boss","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Rupprecht","sequence":"additional","affiliation":[{"name":"University of Oxford"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[{"name":"Stability AI"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.14988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02036"},{"key":"ref8","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","volume-title":"arXiv","author":"Gao","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref11","volume-title":"Lvsm: A large view synthesis model with minimal 3d inductive bias","author":"Jin","year":"2024"},{"key":"ref12","article-title":"Controlling space and time with diffusion models","author":"Watson","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","article-title":"Zeronvs: Zero-shot 360-degree view synthesis from a single real image","author":"Sargent","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","volume-title":"Virtual camera system","year":"2025"},{"key":"ref15","article-title":"pixelsplat: 3d gaussian splats from image pairs for scalable generalizable 3d reconstruction","volume-title":"arXiv","author":"Charatan","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref17","article-title":"Long-lrm: Longsequence large reconstruction model for wide-coverage gaussian splats","author":"Ziwen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Latent video diffusion models for high-fidelity long video generation","volume-title":"arXiv","author":"He","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","article-title":"MVDream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Accurate, large minibatch sg d: training imagenet in 1 hour","author":"Goyal","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref28","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Simple diffusion: End-to-end diffusion for high resolution images","author":"Hoogeboom","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICLR","author":"Esser","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01534"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"},{"key":"ref40","first-page":"22160","article-title":"D13dv-10k: A large-scale scene dataset for deep learning-based 3d vision","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ling","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref42","article-title":"Motion-conditioned diffusion model for controllable video synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/11449036.pdf?arnumber=11449036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:41Z","timestamp":1777530041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01153","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}