{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:06:32Z","timestamp":1784268392174,"version":"3.55.0"},"reference-count":80,"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\/iccv51701.2025.02532","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27272-27283","source":"Crossref","is-referenced-by-count":4,"title":["InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Lu","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanchi","family":"Ren","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Southern California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianchang","family":"Shen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangjie","family":"Wu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanja","family":"Fidler","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"https:\/\/blackforestlabs.ai\/announcing-black-forest-labs\/","year":"2024"},{"key":"ref2","article-title":"STORM: Spatio-temporal reconstruction model for large-scale outdoor scenes","volume-title":"Submitted to The Thirteenth International Conference on Learning Representations","year":"2024"},{"key":"ref3","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","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","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref10","article-title":"Omnire: Omni urban scene reconstruction","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2558"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2308"},{"key":"ref16","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Cat3d: Create anything in 3d with multi-view diffusion models","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Dome: Taming diffusion model into high-fidelity controllable occupancy world model","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Streetsurf: Extending multi-view implicit surface reconstruction to street views","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref23","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"CoRR"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"issue":"4","key":"ref29","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3592433","article-title":"Thomas Leimk\u00fchler, and George Drettakis. 3d gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"ref31","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Collaborative video diffusion: Consistent multi-video generation with camera control","author":"Kuang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_13"},{"key":"ref34","article-title":"Hydra-mdp: End-to-end multimodal planning with multitarget hydra-distillation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02085"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref41","volume-title":"Viser: A library for interactive 3d visualization in python","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00355"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00403"},{"key":"ref44","article-title":"Scube: Instant large-scale scene reconstruction using voxsplats","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657497"},{"key":"ref49","article-title":"Mvdream: Multi-view diffusion for 3d generation","author":"Shi","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01411"},{"key":"ref53","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00275"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01956"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3658226"},{"key":"ref61","first-page":"315","article-title":"Mars: An instance-aware, modular and realistic simulator for autonomous driving","volume-title":"CAAI International Conference on Artificial Intelligence","author":"Wu","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_18"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref65","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Street gaussians for modeling dynamic urban scenes","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Emernerf: Emergent spatial-temporal scene decomposition via self-supervision","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Drivearena: A closed-loop generative simulation platform for autonomous driving","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref72","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"4diffusion: Multi-view video diffusion model for 4 d generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Urban scene diffusion through semantic occupancy map","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref80","article-title":"Lidardm: Generative lidar simulation in a generated world","author":"Zyrianov","year":"2024","journal-title":"arXiv preprint"}],"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\/11445755.pdf?arnumber=11445755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:55Z","timestamp":1777529755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02532","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}