{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:53:28Z","timestamp":1782834808957,"version":"3.54.5"},"reference-count":170,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3449912","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:46:40Z","timestamp":1725904000000},"page":"10978-10997","source":"Crossref","is-referenced-by-count":89,"title":["Vision-Centric BEV Perception: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7237-988X","authenticated-orcid":false,"given":"Yuexin","family":"Ma","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Intelligent Perception and Human-Machine Collaboration, Shanghai Frontiers Science Center of Human-centered Artificial Intelligence, ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3308-9262","authenticated-orcid":false,"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7414-0319","authenticated-orcid":false,"given":"Xuyang","family":"Bai","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huitong","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Queensland, St Lucia, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2844-7416","authenticated-orcid":false,"given":"Yuenan","family":"Hou","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaming","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Maryland, College Park, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5296-6307","authenticated-orcid":false,"given":"Ruigang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-8099","authenticated-orcid":false,"given":"Xinge","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Ma Liu Shui, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00201978"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00895"},{"key":"ref4","article-title":"Level 5 perception dataset 2020","author":"Kesten","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793925"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref8","article-title":"CityScapes 3D: Dataset and benchmark for 9 DoF vehicle detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshop","author":"G\u00e4hlert"},{"key":"ref9","article-title":"LET-3D-AP: Longitudinal error tolerant 3D average precision for camera-only 3D detection","author":"Wei-Chih","year":"2022"},{"key":"ref10","volume-title":"Multiple View Geometry in Computer Vision","author":"Richard","year":"2003"},{"key":"ref11","first-page":"4095","article-title":"A geometric approach to obtain a bird\u2019s eye view from an image","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. Workshops","author":"Syed"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814050"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4324\/9780203978948-13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_21"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636384"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294462"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00301"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00115"},{"key":"ref20","first-page":"51","article-title":"Driving among flatmobiles: Bird-eye-view occupancy grids from a monocular camera for holistic trajectory planning","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Abdelhak"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3146898"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385958"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00599"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967624"},{"key":"ref27","first-page":"1689","article-title":"MonoLayout: Amodal scene layout from a single image","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Kaustubh"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2019.8814056"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref30","article-title":"Pseudo-LiDAR++: Accurate depth for 3D object detection in autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yurong"},{"key":"ref31","article-title":"Orthographic feature transform for monocular 3D object detection","volume-title":"Proc. 30th Brit. Mach. Vis. Conf.","author":"Roddick"},{"key":"ref32","first-page":"194","article-title":"Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly unprojecting to 3D","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Jonah"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3098789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref35","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01899"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_19"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00321"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00592"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref43","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","author":"Junjie","year":"2021"},{"key":"ref44","article-title":"BEVDet4D: Exploit temporal cues in multi-camera 3D object detection","author":"Junjie","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00314"},{"key":"ref47","article-title":"MV-FCOS3D++: Multi-View camera-only 4D object detection with pretrained monocular backbones","author":"Tai","year":"2022"},{"key":"ref48","first-page":"2397","article-title":"ImVoxelNet: Image to voxels projection for monocular and multi-view general-purpose 3D object detection","volume-title":"Proc. Winter Conf. Appl. Comput. Vis.","author":"Danila"},{"key":"ref49","first-page":"386","article-title":"Monocular 3D object detection with depth from motion","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Tai"},{"key":"ref50","article-title":"STS: Surround-view temporal stereo for multi-view 3D detection","author":"Zengran","year":"2022"},{"key":"ref51","first-page":"1486","article-title":"BEVStereo: Enhancing depth estimation in multi-view 3D object detection with temporal stereo","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Yinhao"},{"key":"ref52","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","author":"Jinhyung","year":"2023"},{"key":"ref53","article-title":"Exploring recurrent long-term temporal fusion for multi-view 3D perception","author":"Chunrui","year":"2023"},{"key":"ref54","article-title":"DORT: Modeling dynamic objects in recurrent for multi-camera 3D object detection and tracking","author":"Qing","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00494"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142418"},{"key":"ref57","article-title":"M2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","author":"Enze","year":"2022"},{"key":"ref58","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","author":"Yunpeng","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891028"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004325"},{"key":"ref62","article-title":"Fishing net: Future inference of semantic heatmaps in grids","author":"Hendy","year":"2020"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561169"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161214"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1162\/089976603321891846"},{"key":"ref69","article-title":"Tesla AI day 2021","year":"2021"},{"key":"ref70","first-page":"213","article-title":"End-to-end object detection with transformers","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Nicolas"},{"key":"ref71","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Pro. Conf. Robot Learn.","author":"Yue"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01537"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01675"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00302"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547859"},{"key":"ref77","article-title":"ORA3D: Overlap region aware multi-view 3D object detection","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Roh"},{"key":"ref78","article-title":"Polar parametrization for vision-based surround-view 3D detection","author":"Shaoyu","year":"2022"},{"key":"ref79","article-title":"SRCN3D: Sparse R-CNN 3D surround-view camera object detection and tracking for autonomous driving","author":"Shi","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00351"},{"key":"ref82","first-page":"1042","article-title":"PolarFormer: Multi-camera 3D object detection with polar transformer","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Yanqin"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref84","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"ref88","first-page":"550","article-title":"PersFormer: 3D lane detection via perspective transformer and the openlane benchmark","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Li"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref91","first-page":"129","article-title":"Learning ego 3D representation as ray tracing","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Jiachen"},{"key":"ref92","article-title":"Efficient and robust 2D-to-BEV representation learning via geometry-guided kernel transformer","author":"Chen","year":"2022"},{"key":"ref93","first-page":"989","article-title":"CoBEVT: Cooperative bird\u2019s eye view semantic segmentation with sparse transformers","volume-title":"Proc. Conf. Robot Learn.","author":"Xu"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811901"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_23"},{"key":"ref96","first-page":"1663","article-title":"LaRa: Latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation","volume-title":"Proc. Conf. Robot Learn.","author":"Bartoccioni"},{"key":"ref97","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev"},{"key":"ref98","first-page":"9438","article-title":"Sparse sinkhorn attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tay"},{"key":"ref99","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref103","first-page":"3580","article-title":"3DPPE: 3D point positional encoding for multi-camera 3D object detection transformers","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Shu"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00840"},{"key":"ref105","article-title":"DA-BEV: Depth aware BEV transformer for 3D object detection","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00637"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01703"},{"key":"ref109","article-title":"DynamicBEV: Leveraging dynamic queries and temporal context for 3D object detection","author":"Yao","year":"2023"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00615"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28033"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00138"},{"key":"ref113","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial-temporal fusion","author":"Lin","year":"2022"},{"key":"ref114","article-title":"Sparse4D v2: Recurrent temporal fusion with sparse model","author":"Lin","year":"2023"},{"key":"ref115","article-title":"Sparse4D v3: Advancing end-to-end 3D detection and tracking","author":"Lin","year":"2023"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01515"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00033"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_39"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref123","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"ref129","article-title":"A simple baseline for BEV perception without LiDAR","author":"Harley","year":"2022"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00022"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref132","first-page":"16494","article-title":"Multimodal virtual point 3D detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yin"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref138","article-title":"Uniformer: Unified multi-view fusion transformer for spatial-temporal representation in bird\u2019s-eye-view","author":"Qin","year":"2022"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref140","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","author":"Dosovitskiy"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_26"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00134"},{"key":"ref143","article-title":"Tesla AI day 2022","year":"2022"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref146","article-title":"OccDepth: A depth-aware method for 3D semantic scene completion","author":"Miao","year":"2023"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01692"},{"key":"ref152","article-title":"OctreeOcc: Efficient and multi-granularity occupancy prediction using octree queries","author":"Lu","year":"2023"},{"key":"ref153","article-title":"BEVPoolv2: A cutting-edge implementation of BEVDet toward deployment","author":"Junjie","year":"2022"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.3390\/s18103337"},{"key":"ref156","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. Conf. Robot Learn.","author":"Wang"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01635"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00096"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191849"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref163","article-title":"Monodistill: Learning spatial features for monocular 3D object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhiyu"},{"key":"ref164","first-page":"87","article-title":"Cross-modality knowledge distillation network for monocular 3D object detection","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yu"},{"key":"ref165","article-title":"Bevdistill: Cross-modal BEV distillation for multi-view 3D object detection","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref166","article-title":"Unipad: A universal pre-training paradigm for autonomous driving","author":"Honghui","year":"2023"},{"key":"ref167","first-page":"574","article-title":"PointContrast: Unsupervised pre-training for 3D point cloud understanding","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Saining"},{"key":"ref168","first-page":"604","article-title":"Masked autoencoders for point cloud self-supervised learning","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Yatian"},{"key":"ref169","first-page":"27061","article-title":"Point-M2AE: Multi-scale masked autoencoders for hierarchical point cloud pre-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Renrui"},{"key":"ref170","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10670223.pdf?arnumber=10670223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:35:17Z","timestamp":1732667717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":170,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3449912","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}