{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:24:53Z","timestamp":1778171093748,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Foundation for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62225605"],"award-info":[{"award-number":["62225605"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LD24F020016"],"award-info":[{"award-number":["LD24F020016"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20222"],"award-info":[{"award-number":["U20A20222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Science and Technology Innovation Project","award":["2024Z294"],"award-info":[{"award-number":["2024Z294"]}]},{"DOI":"10.13039\/501100013114","name":"Zhejiang Key Research and Development Program","doi-asserted-by":"publisher","award":["2023C03196"],"award-info":[{"award-number":["2023C03196"]}],"id":[{"id":"10.13039\/501100013114","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2024.3427701","type":"journal-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T18:05:37Z","timestamp":1725905137000},"page":"689-700","source":"Crossref","is-referenced-by-count":21,"title":["HeightFormer: Explicit Height Modeling Without Extra Data for Camera-Only 3D Object Detection in Bird\u2019s Eye View"],"prefix":"10.1109","volume":"34","author":[{"given":"Yiming","family":"Wu","sequence":"first","affiliation":[{"name":"Polytechnic Institute, Zhejiang University, Hangzhou, China"}]},{"given":"Ruixiang","family":"Li","sequence":"additional","affiliation":[{"name":"Polytechnic Institute, Zhejiang University, Hangzhou, China"}]},{"given":"Zequn","family":"Qin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"given":"Xinhai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Noah’s Ark Laboratory, Huawei Technologies, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3023-1662","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3057287"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3245337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"ref4","first-page":"1663","article-title":"LaRa: Latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation","volume-title":"Proc. CoRL","author":"Bartoccioni"},{"key":"ref5","article-title":"Sparse4D: Multi-view 3D object detection with sparse spatial\u2013temporal fusion","volume-title":"arXiv:2211.10581","author":"Lin","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref7","article-title":"Orthographic feature transform for monocular 3D object detection","volume-title":"arXiv:1811.08188","author":"Roddick","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"ref10","article-title":"NuScenes: A multimodal dataset for autonomous driving","volume-title":"arXiv:1903.11027","author":"Caesar","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00864"},{"key":"ref12","first-page":"1","article-title":"Pseudo-LiDAR++: Accurate depth for 3D object detection in autonomous driving","volume-title":"Proc. ICLR","author":"You"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref17","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","volume-title":"arXiv:2112.11790","author":"Huang","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","volume":"33","author":"Brown"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. CoRL","volume":"164","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"ref27","article-title":"Time will tell: New outlooks and a baseline for temporal multi-view 3D object detection","volume-title":"arXiv:2210.02443","author":"Park","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00138"},{"issue":"1","key":"ref29","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1023\/A:1014573219977","article-title":"A taxonomy and evaluation of dense two-frame stereo correspondence algorithms","volume":"47","author":"Scharstein","year":"2002","journal-title":"Int. J. Comput. Vis."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2013.09.011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126364"},{"key":"ref32","first-page":"5515","article-title":"DeepStereo: Learning to predict new views from the world\u2019s imagery","volume-title":"Proc. CVPR","author":"Flynn"},{"key":"ref33","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. NeurIPS","volume":"27","author":"Eigen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00249"},{"key":"ref36","article-title":"Recent advances and trends in multimodal deep learning: A review","volume-title":"arXiv:2105.11087","author":"Summaira","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933920"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6618"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"ref42","first-page":"1475","article-title":"Probabilistic and geometric depth: Detecting objects in perspective","volume-title":"Proc. CoRL","author":"Wang"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"ref46","article-title":"Polar parametrization for vision-based surround-view 3D detection","volume-title":"arXiv:2206.10965","author":"Chen","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02070"},{"key":"ref48","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. NeurIPS","volume":"30","author":"Kendall"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref50","article-title":"M\u00b2BEV: Multi-camera joint 3D detection and segmentation with unified birds-eye view representation","volume-title":"arXiv:2204.05088","author":"Xie","year":"2022"},{"key":"ref51","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","volume-title":"arXiv:1908.09492","author":"Zhu","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref53","first-page":"18442","article-title":"Unifying voxel-based representation with transformer for 3D object detection","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10670218.pdf?arnumber=10670218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T19:17:26Z","timestamp":1738178246000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3427701","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}