{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:30Z","timestamp":1777865310019,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFB2505105"],"award-info":[{"award-number":["2024YFB2505105"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.02528","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27231-27241","source":"Crossref","is-referenced-by-count":0,"title":["DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation"],"prefix":"10.1109","author":[{"given":"Jiazhe","family":"Guo","sequence":"first","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yikang","family":"Ding","sequence":"additional","affiliation":[{"name":"MEGVII"}]},{"given":"Xiwu","family":"Chen","sequence":"additional","affiliation":[{"name":"Mach Drive"}]},{"given":"Shuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Bohan","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}]},{"given":"Yingshuang","family":"Zou","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Xiaoyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}]},{"given":"Feiyang","family":"Tan","sequence":"additional","affiliation":[{"name":"Mach Drive"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}]},{"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02740-3"},{"key":"ref4","article-title":"Omnire: Omni urban scene reconstruction","author":"Chen","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00839"},{"key":"ref6","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref8","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref9","article-title":"Magicdrivedit: High-resolution long video generation for autonomous driving with adaptive control","author":"Gao","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref10","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2024","journal-title":"ICLR"},{"key":"ref11","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","author":"Gao","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref12","first-page":"91560","article-title":"Vista: A generalizable driving world model with high fidelity and versatile controllability","volume":"37","author":"Gao","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32376"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276407"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref20","article-title":"Bridging stereo geometry and bev representation with reliable mutual interaction for semantic scene completion","author":"Li","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01118"},{"key":"ref23","article-title":"Feed-forward bullet-time reconstruction of dynamic scenes from monocular videos","author":"Liang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref24","article-title":"Depthlab: From partial to complete","author":"Liu","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127463"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"ref28","volume-title":"pytorch-fid: FID Score for PyTorch","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32793"},{"key":"ref32","article-title":"Stag-1: Towards realistic 4d driving simulation with video generation model","author":"Wang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref33","article-title":"Occsora: 4d occupancy generation models as world simulators for autonomous driving","author":"Wang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref34","article-title":"Freevs: Generative view synthesis on free driving trajectory","author":"Wang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00926"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref40","article-title":"Occllama: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref41","first-page":"539","article-title":"Surrounddepth: Entangling surrounding views for self-supervised multi-camera depth estimation","volume-title":"Conference on robot learning","author":"Wei"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00659"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_10"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00085"},{"key":"ref45","article-title":"Emernerf: Emergent spatial-temporal scene decomposition via self-supervision","author":"Yang","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref46","article-title":"Storm: Spatio-temporal reconstruction model for large-scale outdoor scenes","author":"Yang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref47","article-title":"Bevcontrol: Accurately controlling street-view elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprintarXiv"},{"key":"ref48","article-title":"Drivearena: A closed-loop generative simulation platform for autonomous driving","author":"Yang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref50","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_20"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01122"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref56","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprintarXiv"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.20"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_16"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128001"}],"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\/11445308.pdf?arnumber=11445308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:30Z","timestamp":1777529670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02528","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}