{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:04Z","timestamp":1777890184842,"version":"3.51.4"},"reference-count":53,"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\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["SRG2022-00023-IOTSC"],"award-info":[{"award-number":["SRG2022-00023-IOTSC"]}],"id":[{"id":"10.13039\/501100004733","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\/iccv51701.2025.02307","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24878-24888","source":"Crossref","is-referenced-by-count":0,"title":["Semantic Causality-Aware Vision-Based 3D Occupancy Prediction"],"prefix":"10.1109","author":[{"given":"Dubing","family":"Chen","sequence":"first","affiliation":[{"name":"SKL-IOTSC, CIS University of Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Zheng","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS University of Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS University of Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianfei","family":"Li","sequence":"additional","affiliation":[{"name":"COWAROBOT Co. Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlong","family":"Liao","sequence":"additional","affiliation":[{"name":"COWAROBOT Co. Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"COWAROBOT Co. Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pai","family":"Peng","sequence":"additional","affiliation":[{"name":"COWAROBOT Co. Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"SKL-IOTSC, CIS University of Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref2","article-title":"Langocc: Self-supervised open vocabulary occupancy estimation via volume rendering","author":"Boeder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Occflownet: Towards self-supervised occupancy estimation via differentiable rendering and occupancy flow","author":"Boeder","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02313"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref7","article-title":"Alocc: adaptive lifting-based 3d semantic occupancy and cost volume-based flow prediction","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Adaocc: Adaptive forward view transformation and flow modeling for 3d occupancy and flow prediction","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00148"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"ref11","article-title":"Robust learning with jacobian regularization","author":"Hoffman","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Bevdet4d: Exploit temporal cues in multi-camera 3d object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Bevdet: High-performance multi-camera 3d object de-tection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00890"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01117"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32450"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3414835"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref27","article-title":"Fb-occ: 3d occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref29","article-title":"Cascadeflow: 3d occupancy and flow prediction with cascaded sparsity sampling refinement framework","volume-title":"CVPR 2024 Autonomous Grand Challenge Track On Occupancy and Flow","author":"Liao","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02042"},{"key":"ref31","article-title":"See and think: Disentangling semantic scene completion","volume":"31","author":"Liu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Let occ flow: Selfsupervised 3d occupancy flow prediction","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2528"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01884"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","article-title":"Lift, splat, shoot:Encoding images from arbitrary camera rigs by implicitly unprojecting to 3d","volume-title":"Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16","author":"Philion","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2809"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.609"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref45","article-title":"Deep height decoupling for precise vision-based 3d occupancy prediction","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Renderworld: World model with self-supervised 3d label","author":"Yan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202212"},{"key":"ref48","article-title":"Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Occnerf: Selfsupervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Lightweight spatial embedding for vision-based 3d occupancy prediction","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.940"}],"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\/11444469.pdf?arnumber=11444469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:38Z","timestamp":1777613378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02307","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}