{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:32:57Z","timestamp":1777656777631,"version":"3.51.4"},"reference-count":52,"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\/icra55743.2025.11128708","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"12647-12654","source":"Crossref","is-referenced-by-count":4,"title":["Deep Height Decoupling for Precise Vision-Based 3D Occupancy Prediction"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiqiang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University,Tianjin,China,300071"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Hui","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Electronics and Information,Xi'an,China,710072"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology,PCA Lab, Key Lab of Intelligent Perception and Systems for HighDimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bevdet: Highperformance multi-camera 3d object detection in bird-eye-view","author":"Huang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref3","article-title":"Context and geometry aware voxel transformer for semantic scene completion","author":"Yu","year":"2024","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00979"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00466"},{"key":"ref7","article-title":"Dcdepth: Progressive monocular depth estimation in discrete cosine domain","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00115"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref13","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","author":"Tian","year":"2024","journal-title":"NIPS"},{"key":"ref14","article-title":"Gaussianocc: Fully self-supervised and efficient 3d occupancy estimation with gaussian splatting","author":"Gan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"ref20","article-title":"Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Panoptic-flashocc: An efficient baseline to marry semantic occupancy with panoptic via instance center","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Milo: Multitask learning with localization ambiguity suppression for occupancy prediction cvpr 2023 occupancy challenge report","author":"Myeongjin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"39099","article-title":"Distortion and uncertainty aware loss for panoramic depth completion","volume-title":"ICML","author":"Yan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_22"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref27","article-title":"Bevdet4d: Exploit temporal cues in multicamera 3d object detection","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Fully sparse 3d panoptic occupancy prediction","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01885"},{"key":"ref30","article-title":"Occnerf: Self-supervised multi-camera occupancy prediction with neural radiance fields","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision","author":"Pan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25415"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00048-9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01575"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02509"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02470-y"},{"key":"ref37","article-title":"Occdepth: A depth-aware method for 3d semantic scene completion","author":"Miao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00310"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"ref40","article-title":"Bevpoolv2: A cutting-edge implementation of bevdet toward deployment","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01675"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref46","article-title":"FB-OCC: 3D occupancy prediction based on forward-backward view transformation","author":"Li","year":"2023","journal-title":"arXiv:2307.01492"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2025.3539627"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref51","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref52","volume-title":"MMDetection3D: OpenMMLab next-generation platform for general 3D object detection","author":"Contributors","year":"2020"}],"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\/11128708.pdf?arnumber=11128708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:24:28Z","timestamp":1756880668000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128708\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128708","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}