{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T03:25:48Z","timestamp":1784431548657,"version":"3.55.0"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160968","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"2774-2781","source":"Crossref","is-referenced-by-count":1031,"title":["BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation"],"prefix":"10.1109","author":[{"given":"Zhijian","family":"Liu","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotian","family":"Tang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Amini","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huizi","family":"Mao","sequence":"additional","affiliation":[{"name":"OmniML,San Jose,CA,USA,95131"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniela L.","family":"Rus","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Cambridge,MA,USA,02139"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","article-title":"Class-Balanced Grouping and Sampling for Point Cloud 3D Object Detection","author":"zhu","year":"2019","journal-title":"ArXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_39"},{"key":"ref15","article-title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","author":"qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref14","article-title":"End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds","author":"zhou","year":"2019","journal-title":"CoRL"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref52","article-title":"Deep Continuous Fusion for Multi-Sensor 3D Object Detection","author":"liang","year":"2018","journal-title":"ECCV"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.3390\/s18103337","article-title":"SECOND: Sparsely Embedded Convolutional Detection","author":"yan","year":"2018","journal-title":"SENSORS"},{"key":"ref55","article-title":"MT-Net Submission to the Waymo 3D Detection Leaderboard","author":"chen","year":"2022","journal-title":"ArXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref19","article-title":"Object a Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots","author":"chen","year":"2020","journal-title":"ECCV"},{"key":"ref18","article-title":"1st Place Solutions to the Real-time 3D Detection and the Most Efficient Model of the Waymo Open Dataset Challenge 2021","author":"ge","year":"2021","journal-title":"cvprw"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/116"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9564951"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref48","article-title":"FUTR3D: A Unified Sensor Fusion Framework for 3D Detection","author":"chen","year":"2022","journal-title":"ArXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00157"},{"key":"ref42","article-title":"Categorical depth distributionnetwork for monocular 3d object detection","author":"reading","year":"2021","journal-title":"CVPR"},{"key":"ref41","article-title":"M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation","author":"xie","year":"2022","journal-title":"ArXiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref43","article-title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","author":"li","year":"2022","journal-title":"ArXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref4","article-title":"Multimodal Virtual Point 3D Detection","author":"yin","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"ref6","article-title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","author":"philion","year":"2020","journal-title":"ECCV"},{"key":"ref5","author":"pan","year":"2020","journal-title":"Cross-view semantic segmentation for sensing surroundings"},{"key":"ref40","article-title":"BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View","author":"huang","year":"2021","journal-title":"ArXiv"},{"key":"ref35","article-title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","author":"liu","year":"2022","journal-title":"ArXiv"},{"key":"ref34","article-title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","author":"wang","year":"2021","journal-title":"CoRL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"ref36","article-title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","author":"zhu","year":"2021","journal-title":"ICLRE"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"ref32","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","author":"wang","year":"2021","journal-title":"CoRL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref38","article-title":"Orthographic Feature Transform for Monocular 3D Object Detection","author":"roddick","year":"2019","journal-title":"BMVC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref23","article-title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","author":"wang","year":"2021","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2020.2977026","article-title":"From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network","author":"shi","year":"2020","journal-title":"TPAMI"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00987"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00607"},{"key":"ref22","article-title":"PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars","author":"chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"ref28","article-title":"PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection","author":"shi","year":"2021","journal-title":"ArXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160968.pdf?arnumber=10160968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:29:58Z","timestamp":1690219798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160968","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}