{"url":"/sota/vehicle-pose-estimation-on-kitti-cars-hard","task":{"name":"Vehicle Pose Estimation","url":"/task/vehicle-pose-estimation","note":null},"dataset":{"name":"KITTI Cars Hard","url":"/dataset/kitti"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Image Credit: [GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision, ECCV'20](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123600511.pdf)","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":["Average Orientation Similarity"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average Orientation Similarity":null}},"counts":{"rows":19,"rows_with_code":11,"rows_with_paper_page":19,"rows_dated":19,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"Ego-Net (Monocular RGB only)","metrics":{"Average Orientation Similarity":"80.96"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/exploring-intermediate-representation-for","paper_url":"https://arxiv.org/abs/2011.08464v5","paper_title":"Exploring intermediate representation for monocular vehicle pose estimation","code":"https://github.com/Nicholasli1995/EgoNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Deep-Manta","metrics":{"Average Orientation Similarity":"80.39"},"uses_additional_data":true,"paper_date":"2017-03-22","paper":"/paper/deep-manta-a-coarse-to-fine-many-task-network","paper_url":"http://arxiv.org/abs/1703.07570v1","paper_title":"Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"3D R-CNN","metrics":{"Average Orientation Similarity":"80.07"},"uses_additional_data":true,"paper_date":"2018-06-01","paper":"/paper/3d-rcnn-instance-level-3d-object","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Kundu_3D-RCNN_Instance-Level_3D_CVPR_2018_paper.html","paper_title":"3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"SubCNN","metrics":{"Average Orientation Similarity":"78.68"},"uses_additional_data":false,"paper_date":"2016-04-16","paper":"/paper/subcategory-aware-convolutional-neural","paper_url":"http://arxiv.org/abs/1604.04693v3","paper_title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","code":"https://github.com/xiaohaoChen/rrc_detection","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"DSGN (Stereo)","metrics":{"Average Orientation Similarity":"78.27"},"uses_additional_data":false,"paper_date":"2020-01-10","paper":"/paper/dsgn-deep-stereo-geometry-network-for-3d","paper_url":"https://arxiv.org/abs/2001.03398v3","paper_title":"DSGN: Deep Stereo Geometry Network for 3D Object Detection","code":"https://github.com/chenyilun95/DSGN","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"RTM-3D","metrics":{"Average Orientation Similarity":"77.18"},"uses_additional_data":false,"paper_date":"2020-01-10","paper":"/paper/rtm3d-real-time-monocular-3d-detection-from","paper_url":"https://arxiv.org/abs/2001.03343v1","paper_title":"RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving","code":"https://github.com/Banconxuan/RTM3D","n_code_links":2,"syntology":{"n_ran":11,"n_unverified":5,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"FQNet","metrics":{"Average Orientation Similarity":"76.85"},"uses_additional_data":false,"paper_date":"2019-04-26","paper":"/paper/deep-fitting-degree-scoring-network-for","paper_url":"https://arxiv.org/abs/1904.12681v2","paper_title":"Deep Fitting Degree Scoring Network for Monocular 3D Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"Mono3D","metrics":{"Average Orientation Similarity":"76.84"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/monocular-3d-object-detection-for-autonomous","paper_url":"http://openaccess.thecvf.com/content_cvpr_2016/html/Chen_Monocular_3D_Object_CVPR_2016_paper.html","paper_title":"Monocular 3D Object Detection for Autonomous Driving","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"Deep3DBoX","metrics":{"Average Orientation Similarity":"76.76"},"uses_additional_data":false,"paper_date":"2016-12-01","paper":"/paper/3d-bounding-box-estimation-using-deep","paper_url":"http://arxiv.org/abs/1612.00496v2","paper_title":"3D Bounding Box Estimation Using Deep Learning and Geometry","code":"https://github.com/smallcorgi/3D-Deepbox","n_code_links":11,"syntology":{"n_ran":6,"n_unverified":21,"n_samples":27,"n_pointer_only_licence":5}},{"rank_in_archive_order":10,"model":"3DOP","metrics":{"Average Orientation Similarity":"76.52"},"uses_additional_data":false,"paper_date":"2015-12-01","paper":"/paper/3d-object-proposals-for-accurate-object-class","paper_url":"http://papers.nips.cc/paper/5644-3d-object-proposals-for-accurate-object-class-detection","paper_title":"3D Object Proposals for Accurate Object Class Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"MonoPair","metrics":{"Average Orientation Similarity":"76.45"},"uses_additional_data":false,"paper_date":"2020-03-01","paper":"/paper/monopair-monocular-3d-object-detection-using","paper_url":"https://arxiv.org/abs/2003.00504v1","paper_title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","code":"https://github.com/Nicholasli1995/EgoNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"ML-Fusion","metrics":{"Average Orientation Similarity":"76.37"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/multi-level-fusion-based-3d-object-detection","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Xu_Multi-Level_Fusion_Based_CVPR_2018_paper.html","paper_title":"Multi-Level Fusion Based 3D Object Detection From Monocular Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"MonoPSR","metrics":{"Average Orientation Similarity":"72.26"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/monocular-3d-object-detection-leveraging","paper_url":"http://arxiv.org/abs/1904.01690v1","paper_title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","code":"https://github.com/ZhixinLai/3D-detection-with-monocular-RGB-image","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":14,"model":"Disp-RCNN (Stereo)","metrics":{"Average Orientation Similarity":"67.16"},"uses_additional_data":false,"paper_date":"2020-04-07","paper":"/paper/disp-r-cnn-stereo-3d-object-detection-via","paper_url":"https://arxiv.org/abs/2004.03572v1","paper_title":"Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation","code":"https://github.com/zju3dv/disprcnn","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"M3D-RPN","metrics":{"Average Orientation Similarity":"67.08"},"uses_additional_data":false,"paper_date":"2019-07-13","paper":"/paper/m3d-rpn-monocular-3d-region-proposal-network","paper_url":"https://arxiv.org/abs/1907.06038v2","paper_title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","code":"https://github.com/garrickbrazil/M3D-RPN","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":16,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"RAR-Net","metrics":{"Average Orientation Similarity":"66.90"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/reinforced-axial-refinement-network-for","paper_url":"https://arxiv.org/abs/2008.13748v1","paper_title":"Reinforced Axial Refinement Network for Monocular 3D Object Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"D4LCN","metrics":{"Average Orientation Similarity":"63.98"},"uses_additional_data":false,"paper_date":"2019-12-10","paper":"/paper/learning-depth-guided-convolutions-for","paper_url":"https://arxiv.org/abs/1912.04799v2","paper_title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","code":"https://github.com/dingmyu/D4LCN","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":14,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"GS3D","metrics":{"Average Orientation Similarity":"61.85"},"uses_additional_data":false,"paper_date":"2019-03-26","paper":"/paper/gs3d-an-efficient-3d-object-detection","paper_url":"http://arxiv.org/abs/1903.10955v2","paper_title":"GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"Kinematic3D","metrics":{"Average Orientation Similarity":"34.81"},"uses_additional_data":false,"paper_date":"2020-07-19","paper":"/paper/kinematic-3d-object-detection-in-monocular","paper_url":"https://arxiv.org/abs/2007.09548v1","paper_title":"Kinematic 3D Object Detection in Monocular Video","code":"https://github.com/Nicholasli1995/EgoNet","n_code_links":2,"syntology":{"n_ran":19,"n_unverified":1,"n_samples":20,"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":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":8,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":51,"n_unverified":60,"n_samples":111,"n_pointer_only_licence":8,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":51,"n_unverified":60,"n_samples":111,"n_pointer_only_licence":8,"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"}}}