{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:23:10Z","timestamp":1778084590597,"version":"3.51.4"},"reference-count":47,"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\/iccv51701.2025.02504","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26977-26986","source":"Crossref","is-referenced-by-count":1,"title":["RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation"],"prefix":"10.1109","author":[{"given":"Yuwen","family":"Du","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anning","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zichen","family":"Chao","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Ge","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Genjia","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weitao","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3543072"},{"key":"ref2","article-title":"Omnire: Omni urban scene reconstruction","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"Blender - a 3D modelling and rendering package.","year":"2018"},{"key":"ref4","first-page":"1","article-title":"Carla: An open urban driving simulator","volume-title":"Conference on robot learning","author":"Dosovitskiy","year":"2017"},{"key":"ref5","article-title":"Magicdrive: Street view generation with diverse 3d geometry control","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Magicdrive3d: Controllable 3d generation for any-view rendering in street scenes","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02109"},{"key":"ref9","article-title":"Gaia-1: A generative world model for autonomous driving","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0352"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32376"},{"key":"ref13","article-title":"Adriver-i: A general world model for autonomous driving","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Drivingdiffusion: Layout-guided multi-view driving scene video generation with latent diffusion model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3560327"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_10"},{"key":"ref21","article-title":"An extensible framework for open heterogeneous collaborative perception","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3439557"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3368234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01411"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01394"},{"key":"ref30","article-title":"Drivedreamer: Towards real-worlddriven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"180","article-title":"Detr3d: 3d object detection from multi-view images via 3d-to-2d queries","volume-title":"Conference on Robot Learning","author":"Wang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01397"},{"key":"ref33","article-title":"Asynchrony-robust collaborative perception via bird\u2019s eye view flow","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wei","year":"2024"},{"key":"ref34","first-page":"1507715087","article-title":"Editable scene simulation for autonomous driving via collaborative 11 m-agents","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341681"},{"key":"ref37","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":"ref38","article-title":"S-nerf: Neural radiance fields for street views","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Bevcontrol: Accurately controlling streetview elements with multi-perspective consistency via bev sketch layout","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02070"},{"key":"ref41","article-title":"Depth anything v2","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3412759"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00140"},{"key":"ref44","article-title":"Mobilesamv2: Faster segment anything to everything","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02139"}],"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\/11445339.pdf?arnumber=11445339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:45Z","timestamp":1777612065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02504","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}