{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:24Z","timestamp":1792786944166,"version":"4.5.0"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62302246"],"award-info":[{"award-number":["62302246"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"ZJNSFC","award":["LQ23F010008"],"award-info":[{"award-number":["LQ23F010008"]}]},{"name":"High Performance Computing Center at Eastern Institute of Technology and Ningbo Institute of Digital Twin","id":[{"id":"https:\/\/ror.org\/00ct9cz38","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3696126","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:36:11Z","timestamp":1779478571000},"page":"12384-12400","source":"Crossref","is-referenced-by-count":1,"title":["Scaling up Occupancy-Centric Driving Scene Generation: Dataset and Method"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6959-7517","authenticated-orcid":false,"given":"Bohan","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1820-8358","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3848-0110","authenticated-orcid":false,"given":"Hu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0910-2299","authenticated-orcid":false,"given":"Hongsi","family":"Liu","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7719-0672","authenticated-orcid":false,"given":"Ruikai","family":"Li","sequence":"additional","affiliation":[{"name":"Li Auto","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4724-0804","authenticated-orcid":false,"given":"Jiazhe","family":"Guo","sequence":"additional","affiliation":[{"name":"Li Auto","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Cai","sequence":"additional","affiliation":[{"name":"Li Auto","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-2845","authenticated-orcid":false,"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3877","authenticated-orcid":false,"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-581X","authenticated-orcid":false,"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2531-3137","authenticated-orcid":false,"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology","place":["Ningbo, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0397"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28085"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127463"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02683"},{"key":"ref8","article-title":"History-guided video diffusion","author":"Song","year":"2025"},{"key":"ref9","article-title":"BEVControl: Accurately controlling street-view elements with multi-perspective consistency via BEV sketch layout","author":"Yang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref12","first-page":"1","article-title":"MagicDrive: Street view generation with diverse3D 3D geometry control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gao","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72384-1_58"},{"key":"ref18","article-title":"Gan augmentation: Augmenting training data using generative adversarial networks","author":"Bowles","year":"2018"},{"key":"ref19","article-title":"Integrating geometric control into text-to-image diffusion models for high-quality detection data generation via text prompt","author":"Chen","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref21","article-title":"Is synthetic data from generative models ready for image recognition?","author":"He","year":"2022"},{"key":"ref22","article-title":"Is a prompt and a few samples all you need? Using GPT-4 for data augmentation in low-resource classification tasks","author":"M\u00f8ller","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01122"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0757"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3071647"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01396"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2809"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref38","first-page":"1","article-title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. ADP3 Workshop","author":"Caesar"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00425"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.18"},{"key":"ref42","article-title":"SynthCity: A large scale synthetic point cloud","author":"Griffiths","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/IV47402.2020.9304596","article-title":"SemanticPOSS: A point cloud dataset with large quantity of dynamic instances","author":"Pan","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref46","article-title":"KITTI-360: A novel dataset and benchmarks for urban scene understanding in 2D and 3D","author":"Liao","year":"2022"},{"key":"ref47","article-title":"Openscene: The largest up-to-date 3D occupancy prediction benchmark in autonomous driving","author":"Contributors","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/107"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3687468"},{"key":"ref54","article-title":"FB-OCC: 3D occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02244-y"},{"key":"ref56","article-title":"3D scene generation: A survey","author":"Wen","year":"2025"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3603078"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02677"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72890-7_5"},{"key":"ref60","article-title":"OccLLaMA: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02000"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33010"},{"key":"ref64","article-title":"DynamicCity: Large-scale 4D occupancy generation from dynamic scenes","author":"Bian","year":"2025"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2906"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/107"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2906"},{"key":"ref69","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72989-8_19"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02612"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01588"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00110"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28546"},{"key":"ref76","first-page":"1","article-title":"GS-LiDAR: Generating realistic LiDAR point clouds with panoramic Gaussian splatting","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang","year":"2025"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236571"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref79","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref81","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref82","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02016"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02425"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2977026"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref91","article-title":"NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref94","article-title":"Open3D: A modern library for 3D data processing","author":"Zhou","year":"2018"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0902"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11533871.pdf?arnumber=11533871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:12:52Z","timestamp":1790269972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":96,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3696126","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}