{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:43Z","timestamp":1777889143985,"version":"3.51.4"},"reference-count":60,"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\/iccv51701.2025.00722","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7698-7708","source":"Crossref","is-referenced-by-count":0,"title":["Voyaging into Perpetual Dynamic Scenes from a Single View"],"prefix":"10.1109","author":[{"given":"Fengrui","family":"Tian","sequence":"first","affiliation":[{"name":"University of Pennsylvania,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinqi","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hancheng","family":"Min","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ren\u00e9","family":"Vidal","sequence":"additional","affiliation":[{"name":"University of Pennsylvania,USA"}],"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","article-title":"Gaudi: A neural architect for immersive 3D scene generation","author":"Bautista","year":"2022","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392485"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2766945"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01404"},{"key":"ref7","article-title":"ThreeDWorld: A platform for interactive multi-modal physical simulation","author":"Gan","year":"2021","journal-title":"NeurIPS"},{"key":"ref8","article-title":"CAT3D: Create anything in 3D with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"NeurIPS"},{"key":"ref9","article-title":"ManiSkill2: A unified benchmark for generalizable manipulation skills","volume-title":"ICLR","author":"Gu","year":"2023"},{"key":"ref10","article-title":"AnimateDiff: Animate your personalized text-toimage diffusion models without specific tuning","volume-title":"ICLR","author":"Guo","year":"2024"},{"key":"ref11","article-title":"CameraCtrl: Enabling camera control for text-to-video generation","volume-title":"ICLR","author":"He","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref14","article-title":"CogVideo: Large-scale pretraining for text-tovideo generation via transformers","volume-title":"ICLR","author":"Hong","year":"2022"},{"key":"ref15","article-title":"Training-free camera control for video generation","volume-title":"ICLR","author":"Hou","year":"2025"},{"key":"ref16","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01230"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_19"},{"key":"ref22","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","volume-title":"Flux","year":"2024"},{"key":"ref24","author":"Batifol","year":"2025","journal-title":"Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00814"},{"key":"ref26","article-title":"4K4DGen: Panoramic 4D generation at 4 K resolution","volume-title":"ICLR","author":"Li","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_30"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"ref31","article-title":"SyncDreamer: Generating multiview-consistent images from a single-view image","volume-title":"ICLR","author":"Liu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref33","article-title":"Openvid-1M: A large-scale high-quality dataset for text-tovideo generation","volume-title":"ICLR","author":"Nan","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02615-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00065"},{"key":"ref36","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3019967"},{"key":"ref38","article-title":"DreamGaussian4D: Generative 4D gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"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"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01641"},{"key":"ref44","article-title":"Semantic Flow: Learning semantic fields of dynamic scenes from monocular videos","volume-title":"ICLR","author":"Tian","year":"2024"},{"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\/CVPR52733.2024.01956"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref50","article-title":"SV4D: Dynamic 3D content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00994"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref54","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","volume-title":"ICLR","author":"Yang","year":"2024"},{"key":"ref55","article-title":"4DGen: Grounded 4D content generation with spatial-temporal consistency","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"4Real: Towards photorealistic 4D scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00555"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","article-title":"GenXD: Generating any 3D and 4D scenes","volume-title":"ICLR","author":"Zhao","year":"2025"}],"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\/11444612.pdf?arnumber=11444612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:54Z","timestamp":1777612014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00722","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}