{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:36Z","timestamp":1777865376106,"version":"3.51.4"},"reference-count":122,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00821","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8777-8788","source":"Crossref","is-referenced-by-count":0,"title":["CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector"],"prefix":"10.1109","author":[{"given":"Abhinav","family":"Kumar","sequence":"first","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Guo","sequence":"additional","affiliation":[{"name":"Bosch Research North America,Bosch Center for AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Bosch Research North America,Bosch Center for AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Ren","sequence":"additional","affiliation":[{"name":"Bosch Research North America,Bosch Center for AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Liu","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1070-x"},{"key":"ref2","article-title":"VD3D: Taming large video diffusion transformers for 3D camera control","volume-title":"arXiv preprint arXiv","author":"Bahmani","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00938"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01264"},{"key":"ref6","article-title":"The non-existence of general-case view-invariants","volume-title":"Geometric invariance in computer vision","author":"Burns","year":"1992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.198"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1864"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27857"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00889"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_22"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3512"},{"key":"ref19","article-title":"OA-BEV: Bringing object awareness to bird\u2019s-eye-view representation for multi-camera 3D object detection","volume-title":"arXiv preprint arXiv","author":"Chu","year":"2023"},{"key":"ref20","article-title":"Group equivariant convolutional networks","volume-title":"ICML","author":"Cohen","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00227"},{"key":"ref22","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2021"},{"key":"ref23","article-title":"CAMConvs: Camera-aware multi-scale convolutions for singleview depth","volume-title":"CVPR","author":"Facil","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_40"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref29","article-title":"OPEN: Objectwise position embedding for multi-view 3D object detection","volume-title":"ECCV","author":"Hou","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00258"},{"key":"ref31","article-title":"BEVDet: High-performance multi-camera 3D object detection in bird-eye-view","volume-title":"arXiv preprint arXiv","author":"Huang","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02001"},{"key":"ref34","article-title":"MonoUNI: A unified vehicle and infrastructure-side monocular 3D object detection network with sufficient depth clues","volume-title":"NeurIPS","author":"Jia","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_7"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_2"},{"key":"ref37","article-title":"Last layer re-training is sufficient for robustness to spurious correlations","volume-title":"ICLR","author":"Kirichenko","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00782"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00826"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00886"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_39"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00978"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00870"},{"key":"ref44","article-title":"Diversify and disambiguate: Learning from underspecified data","volume-title":"ICLR","author":"Lee","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3414835"},{"key":"ref47","article-title":"UniDrive: Towards universal driving perception across camera configurations","volume-title":"ICLR","author":"Li","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_15"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01901"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01567"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_6"},{"key":"ref53","article-title":"Voxel-based 3D detection and reconstruction of multiple objects from a single image","volume-title":"NeurIPS","author":"Liu","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_12"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00592"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01579"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25270"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02075"},{"key":"ref61","article-title":"Towards generalizable multi-camera 3D object detection via perspective debiasing","volume-title":"arXiv preprint arXiv","author":"Lu","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00695"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"ref65","article-title":"3D object detection from images for autonomous driving: A survey","author":"Ma","year":"2023","journal-title":"TPAMI"},{"key":"ref66","article-title":"Vision-centric BEV perception: A survey","volume-title":"arXiv preprint arXiv","author":"Ma","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00801"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01448"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02050"},{"key":"ref70","article-title":"Lie group decompositions for equivariant neural networks","volume-title":"ICLR","author":"Mironenco","year":"2024"},{"key":"ref71","article-title":"Rotation matters: Generalized monocular 3D object detection for various camera systems","volume-title":"arXiv preprint arXiv","author":"Moon","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_19"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref74","article-title":"Time will tell: New outlooks and a baseline for temporal multiview 3D object detection","volume-title":"ICLR","author":"Park","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00776"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126342"},{"key":"ref77","volume-title":"Analytisch-geometrische Entwicklungen","author":"Pl\u00fccker","year":"1828"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3146"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01014"},{"key":"ref81","volume-title":"SemVecNet: Generalizable vector map generation for arbitrary sensor configurations","author":"Ranganatha","year":"2024"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"ref83","article-title":"Learning qualitatively diverse and interpretable rules for classification","volume-title":"ICML Workshops","author":"Ross","year":"2018"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00434"},{"key":"ref85","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worstcase generalization","volume-title":"ICLR","author":"Sagawa","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02658"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00086"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00331"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238627"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2004.1315080"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_1"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1080\/10867651.1999.10487506"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00145"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01626"},{"key":"ref96","article-title":"ID and OOD performance are sometimes inversely correlated on real-world datasets","volume-title":"NeurIPS","author":"Teney","year":"2023"},{"key":"ref97","article-title":"Overcoming simplicity bias in deep networks using a feature sieve","volume-title":"ICML","author":"Tiwari","year":"2023"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01281"},{"key":"ref100","article-title":"PseudoLiDAR from visual depth estimation: Bridging the gap in 3D object detection for autonomous driving","volume-title":"CVPR","author":"Wang","year":"2019"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01173"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"ref103","article-title":"STS: Surround-view temporal stereo for multi-view 3D detection","volume-title":"AAAI","author":"Wang","year":"2023"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01010"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00627"},{"key":"ref106","article-title":"How neural networks extrapolate: From feedforward to graph neural networks","volume-title":"ICLR","author":"Xu","year":"2021"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01516"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01023"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01168"},{"key":"ref111","doi-asserted-by":"crossref","DOI":"10.1109\/IROS58592.2024.10801535","article-title":"Improving out-of-distribution generalization of trajectory prediction for autonomous driving via polynomial representations","volume-title":"arXiv preprint arXiv","author":"Yao","year":"2024"},{"key":"ref112","article-title":"Feature space particle inference for neural network ensembles","volume-title":"ICML","author":"Yashima","year":"2022"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"ref114","article-title":"PoseCNN: A convolutional neural network for 6D object pose estimation in cluttered scenes","volume-title":"RSS","author":"Yu","year":"2018"},{"key":"ref115","article-title":"Towards robust 3D robot perception in urban environments: The UT Campus Object Dataset (CODa)","volume-title":"IROS","author":"Zhang","year":"2023"},{"key":"ref116","article-title":"DA-BEV: Depth aware BEV transformer for 3D object detection","volume-title":"arXiv preprint arXiv","author":"Zhang","year":"2023"},{"key":"ref117","article-title":"Cameras as rays: Pose estimation via ray diffusion","volume-title":"ICLR","author":"Zhang","year":"2024"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"ref119","article-title":"BEVerse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving","volume-title":"arXiv preprint arXiv","author":"Zhang","year":"2022"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3136899"},{"key":"ref121","article-title":"Understanding the robustness of 3D object detection with bird\u2019s-eye-view representations in autonomous driving","volume-title":"CVPR","author":"Zhu","year":"2023"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"}],"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\/11446169.pdf?arnumber=11446169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:03Z","timestamp":1777530123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":122,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00821","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}