{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T18:50:58Z","timestamp":1778698258936,"version":"3.51.4"},"reference-count":63,"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\/iccv51701.2025.02507","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27010-27020","source":"Crossref","is-referenced-by-count":2,"title":["GaussRender: Learning 3D Occupancy with Gaussian Rendering"],"prefix":"10.1109","author":[{"given":"Lo\u00efck","family":"Chambon","sequence":"first","affiliation":[{"name":"ValeoAI,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eloi","family":"Zablocki","sequence":"additional","affiliation":[{"name":"Sorbonne University,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Boulch","sequence":"additional","affiliation":[{"name":"Sorbonne University,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micka\u00ebl","family":"Chen","sequence":"additional","affiliation":[{"name":"Hcompany.ai,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthieu","family":"Cord","sequence":"additional","affiliation":[{"name":"ValeoAI,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Lara: Latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation","volume-title":"In CoRL","author":"Bartoccioni","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01439"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_7"},{"key":"ref7","author":"Gan","year":"2024","journal-title":"Gaussianocc: Fully self-supervised and efficient 3d occupancy estimation with gaussian splatting"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160831"},{"key":"ref11","article-title":"FIERY: Future instance segmentation in bird\u2019s-eye view from surround monocular cameras","volume-title":"In ICCV","author":"Hu","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_31"},{"key":"ref13","author":"Huang","year":"2022","journal-title":"BEVDet4D: Exploit temporal cues in multi-camera 3d object detection"},{"key":"ref14","article-title":"Bevdet: High-performance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref16","article-title":"Gaussianformer-2: Probabilistic gaussian superposition for efficient 3d occupancy prediction","author":"Huang","year":"2024","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"ref20","article-title":"Gausstr: Foundation model-aligned gaussian transformer for self-supervised 3d spatial understanding","author":"Jiang","year":"2024","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00411"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00114"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01440"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802143"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref33","article-title":"FB-OCC: 3d occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3179507"},{"key":"ref35","article-title":"Sparse4d: Multi-view 3d object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022","journal-title":"CoRR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_4"},{"key":"ref37","article-title":"Paparazzi: surface editing by way of multi-view image processing","author":"Derek Liu","year":"2018","journal-title":"ACM"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2528"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_25"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref44","article-title":"Motion transformer with global intention localization and local movement refinement","volume-title":"In NeuRIPS","author":"Shi","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3352811"},{"key":"ref46","author":"Silva","year":"2024","journal-title":"Unified spatio-temporal tri-perspective view representation for 3d semantic occupancy prediction"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00452"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref49","article-title":"Gsrender: Deduplicated occupancy prediction via weakly supervised 3d gaussian splatting","author":"Sun","year":"2024","journal-title":"CoRR"},{"key":"ref50","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume-title":"In NeuRIPS","author":"Tian","year":"2023"},{"key":"ref51","article-title":"Mambaocc: Visual state space model for bev-based occupancy prediction with local adaptive reordering","author":"Tian","year":"2024","journal-title":"CoRR"},{"key":"ref52","article-title":"Pop3d: Open-vocabulary 3d occupancy prediction from images","volume-title":"In NeuRIPS","author":"Vobecky","year":"2023"},{"key":"ref53","article-title":"Occsora: 4d occupancy generation models as world simulators for autonomous driving","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CAIT59945.2023.10469138"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610201"},{"key":"ref57","article-title":"PPT: pre-training with pseudo-labeled trajectories for motion forecasting","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref58","article-title":"Driving in the occupancy world: Vision-centric 4d occupancy forecasting and planning via world models for autonomous driving","author":"Yang","year":"2024","journal-title":"CoRR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73464-9_23"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00967"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00936"},{"key":"ref63","article-title":"Unim2ae: Multimodal masked autoencoders with unified 3d representation for 3d perception in autonomous driving","volume-title":"In ECCV","author":"Zou","year":"2024"}],"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\/11445287.pdf?arnumber=11445287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:37:40Z","timestamp":1777531060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445287\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02507","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}