{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:46:05Z","timestamp":1777567565268,"version":"3.51.4"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127463","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"367-374","source":"Crossref","is-referenced-by-count":4,"title":["DreamDrive: Generative 4D Scene Modeling from Street View Images"],"prefix":"10.1109","author":[{"given":"Jiageng","family":"Mao","sequence":"first","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyi","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ivanovic","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiao","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yurong","family":"You","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaowei","family":"Xiao","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danfei","family":"Xu","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"NVIDIA Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref3","article-title":"Emernerf: Emergent spatialtemporal scene decomposition via self-supervision","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref5","article-title":"Street gaussians for modeling dynamic urban scenes","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"S3 gaussian: Self-supervised street gaussians for autonomous driving","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Periodic vibration gaussian: Dynamic urban scene reconstruction and real-time rendering","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref10","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01389"},{"key":"ref15","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8850-1_1"},{"key":"ref23","article-title":"Sv4d: Dynamic 3d content generation with multi-frame and multi-view consistency","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"L4gm: Large 4d gaussian reconstruction model","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Dreamscene4d: Dynamic multi-object scene generation from monocular videos","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref28","article-title":"Gaussianflow: Splatting gaussian dynamics for 4d content creation","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Comp4d: Llm-guided compositional 4d scene generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"ref31","article-title":"4k4dgen: Panoramic 4d generation at 4k resolution","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Text-to-4d dynamic scene generation","author":"Singer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Luciddreamer: Domain-free generation of 3d gaussian splatting scenes","author":"Chung","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00821"},{"key":"ref36","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00086"},{"key":"ref39","article-title":"One-2\u20133-45: Any single image to 3 d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref41","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"4real: Towards photorealistic 4d scene generation via video diffusion models","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Dreamgaussian4d: Generative 4d gaussian splatting","author":"Ren","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref45","article-title":"Diffusion priors for dynamic view synthesis from monocular videos","volume-title":"arXiv preprint","author":"Wang","year":"2024"},{"key":"ref46","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7572-0_16"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01018"},{"key":"ref51","first-page":"32653","article-title":"D^ 2nerf: Self-supervised decoupling of dynamic and static objects from a monocular video","volume":"35","author":"Wu","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01838"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00853"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01976"},{"key":"ref55","article-title":"Wildgaussians: 3d gaussian splatting in the wild","author":"Kulhanek","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Wild-gs: Real-time novel view synthesis from unconstrained photo collections","volume-title":"arXiv preprint","author":"Xu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3727143"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2644865"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref60","article-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127463.pdf?arnumber=11127463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:28Z","timestamp":1756880248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127463\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127463","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}