{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:27:02Z","timestamp":1776277622170,"version":"3.50.1"},"reference-count":58,"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\/icra55743.2025.11127609","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"6063-6070","source":"Crossref","is-referenced-by-count":2,"title":["Renderworld: World Model with Self-Supervised 3D Label"],"prefix":"10.1109","author":[{"given":"Ziyang","family":"Yan","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}]},{"given":"Wenzhen","family":"Dong","sequence":"additional","affiliation":[{"name":"The Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China"}]},{"given":"Yihua","family":"Shao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Yuhang","family":"Lu","sequence":"additional","affiliation":[{"name":"The ShanghaiTech University,Shanghai,China"}]},{"given":"Haiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Science and Technology Beijing,Beijing,China"}]},{"given":"Jingwen","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Science and Technology Beijing,Beijing,China"}]},{"given":"Haozhe","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Hong Kong,China"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"The Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Institute for AI Industry Research (AIR), Tsinghua University,Beijing,China"}]},{"given":"Fabio","family":"Remondino","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler,Trento,Italy"}]},{"given":"Yuexin","family":"Ma","sequence":"additional","affiliation":[{"name":"The ShanghaiTech University,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref3","article-title":"Bevdet: Highperformance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iv64158.2025.11097578"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161552"},{"key":"ref6","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3327715"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561904"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016120"},{"key":"ref15","article-title":"Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25297"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref19","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref21","article-title":"Occnerf: Self-supervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs15143585"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLVIII-1-W3-2023-219-2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3416798"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01885"},{"key":"ref30","article-title":"Occflownet: Towards selfsupervised occupancy estimation via differentiable rendering and occupancy flow","author":"Boeder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Let occ flow: Self-supervised 3d occupancy flow prediction","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"3dsceneeditor: Controllable 3d scene editing with gaussian splatting","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"ref34","article-title":"Gaussianocc: Fully self-supervised and efficient 3d occupancy estimation with gaussian splatting","author":"Gan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599254"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref39","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"issue":"1988","key":"ref40","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00361"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref46","article-title":"Bevdet4d: Exploit temporal cues in multicamera 3d object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref50","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume":"36","author":"Tian","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00886"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01254"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_21"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref57","article-title":"Fb-occ: 3d occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Octreeocc: Efficient and multigranularity occupancy prediction using octree queries","author":"Lu","year":"2023","journal-title":"arXiv preprint"}],"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\/11127609.pdf?arnumber=11127609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:35:42Z","timestamp":1764959742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127609","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}