{"url":"/sota/3d-object-detection-from-monocular-images-on-7","task":{"name":"3D Object Detection From Monocular Images","url":"/task/3d-object-detection-from-monocular-images","note":null},"dataset":{"name":"KITTI-360","url":"/dataset/kitti-360"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"This is the task of detecting 3D objects from monocular images (as opposed to LiDAR based counterparts). It is usually associated with autonomous driving based tasks.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Orthographic Feature Transform for Monocular 3D Object Detection](https://arxiv.org/pdf/1811.08188v1.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AP50","AP25"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP50":null,"AP25":null}},"counts":{"rows":11,"rows_with_code":11,"rows_with_paper_page":11,"rows_dated":11,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"SeaBird + PanopticBEV","metrics":{"AP25":"37.12","AP50":"4.64"},"uses_additional_data":false,"paper_date":"2024-03-29","paper":"/paper/seabird-segmentation-in-bird-s-view-with-dice","paper_url":"https://arxiv.org/abs/2403.20318v1","paper_title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","code":"https://github.com/abhi1kumar/seabird","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"BoxNet","metrics":{"AP25":"23.59","AP50":"4.08"},"uses_additional_data":false,"paper_date":"2019-04-21","paper":"/paper/deep-hough-voting-for-3d-object-detection-in","paper_url":"https://arxiv.org/abs/1904.09664v2","paper_title":"Deep Hough Voting for 3D Object Detection in Point Clouds","code":"https://github.com/open-mmlab/mmdetection3d","n_code_links":13,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":3,"model":"VoteNet","metrics":{"AP25":"30.61","AP50":"3.40"},"uses_additional_data":false,"paper_date":"2019-04-21","paper":"/paper/deep-hough-voting-for-3d-object-detection-in","paper_url":"https://arxiv.org/abs/1904.09664v2","paper_title":"Deep Hough Voting for 3D Object Detection in Point Clouds","code":"https://github.com/open-mmlab/mmdetection3d","n_code_links":13,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":10}},{"rank_in_archive_order":4,"model":"SeaBird + Image2Maps","metrics":{"AP25":"35.04","AP50":"3.14"},"uses_additional_data":false,"paper_date":"2024-03-29","paper":"/paper/seabird-segmentation-in-bird-s-view-with-dice","paper_url":"https://arxiv.org/abs/2403.20318v1","paper_title":"SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects","code":"https://github.com/abhi1kumar/seabird","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MonoDTR","metrics":{"AP25":"39.76","AP50":"3.02"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/monodtr-monocular-3d-object-detection-with","paper_url":"https://arxiv.org/abs/2203.10981v2","paper_title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","code":"https://github.com/kuanchihhuang/monodtr","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"DEVIANT","metrics":{"AP25":"26.96","AP50":"0.88"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/deviant-depth-equivariant-network-for","paper_url":"https://arxiv.org/abs/2207.10758v1","paper_title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","code":"https://github.com/abhi1kumar/deviant","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"GUPNet","metrics":{"AP25":"27.25","AP50":"0.87"},"uses_additional_data":false,"paper_date":"2021-07-29","paper":"/paper/geometry-uncertainty-projection-network-for","paper_url":"https://arxiv.org/abs/2107.13774v2","paper_title":"Geometry Uncertainty Projection Network for Monocular 3D Object Detection","code":"https://github.com/supermhp/gupnet","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":13,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"MonoDLE","metrics":{"AP25":"28.99","AP50":"0.85"},"uses_additional_data":false,"paper_date":"2021-03-30","paper":"/paper/delving-into-localization-errors-for","paper_url":"https://arxiv.org/abs/2103.16237v1","paper_title":"Delving into Localization Errors for Monocular 3D Object Detection","code":"https://github.com/xinzhuma/monodle","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"Cube R-CNN","metrics":{"AP25":"15.57","AP50":"0.80"},"uses_additional_data":false,"paper_date":"2022-07-21","paper":"/paper/omni3d-a-large-benchmark-and-model-for-3d","paper_url":"https://arxiv.org/abs/2207.10660v2","paper_title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","code":"https://github.com/facebookresearch/omni3d","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"MonoDETR","metrics":{"AP25":"27.13","AP50":"0.79"},"uses_additional_data":false,"paper_date":"2022-03-24","paper":"/paper/monodetr-depth-aware-transformer-for","paper_url":"https://arxiv.org/abs/2203.13310v5","paper_title":"MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection","code":"https://github.com/zrrskywalker/monodetr","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"GrooMeD-NMS","metrics":{"AP25":"16.12","AP50":"0.17"},"uses_additional_data":false,"paper_date":"2021-03-31","paper":"/paper/groomed-nms-grouped-mathematically","paper_url":"https://arxiv.org/abs/2103.17202v1","paper_title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","code":"https://github.com/abhi1kumar/groomed_nms","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 7,081 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":35,"n_unverified":27,"n_samples":62,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":40,"n_unverified":32,"n_samples":72,"n_pointer_only_licence":20,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}