{"url":"/task/vehicle-pose-estimation","name":"Vehicle Pose Estimation","slug":"vehicle-pose-estimation","description_markdown":"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)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":37,"papers_with_code":20,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/vehicle-pose-estimation-on-kitti-cars-hard","slug":"vehicle-pose-estimation-on-kitti-cars-hard","dataset":"KITTI Cars Hard","dataset_url":"/dataset/kitti","rows_in_archive":19,"metrics":["Average Orientation Similarity"],"first_row_in_archive_order":{"model":"Ego-Net (Monocular RGB only)","paper_title":"Exploring intermediate representation for monocular vehicle pose estimation","paper_url":"/paper/exploring-intermediate-representation-for","paper_date":"2020-11-17","arxiv_id":"2011.08464","code_links":[{"title":"Nicholasli1995/EgoNet","url":"https://github.com/Nicholasli1995/EgoNet"}],"syntology":null}},{"leaderboard":"/sota/vehicle-pose-estimation-on-apollocar3d","slug":"vehicle-pose-estimation-on-apollocar3d","dataset":"ApolloCar3D","dataset_url":"/dataset/apollocar3d","rows_in_archive":1,"metrics":["A3DP"],"first_row_in_archive_order":{"model":"GSNet","paper_title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","paper_url":"/paper/gsnet-joint-vehicle-pose-and-shape","paper_date":"2020-07-26","arxiv_id":"2007.13124","code_links":[{"title":"lkeab/gsnet","url":"https://github.com/lkeab/gsnet"}],"syntology":null}},{"leaderboard":"/sota/vehicle-pose-estimation-on-kitti","slug":"vehicle-pose-estimation-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":1,"metrics":["Average Orientation Similarity"],"first_row_in_archive_order":{"model":"Ego-Net","paper_title":"Exploring intermediate representation for monocular vehicle pose estimation","paper_url":"/paper/exploring-intermediate-representation-for","paper_date":"2020-11-17","arxiv_id":"2011.08464","code_links":[{"title":"Nicholasli1995/EgoNet","url":"https://github.com/Nicholasli1995/EgoNet"}],"syntology":null}},{"leaderboard":"/sota/vehicle-pose-estimation-on-vehicle-pose","slug":"vehicle-pose-estimation-on-vehicle-pose","dataset":"CarFusion","dataset_url":"/dataset/vehicle-pose-estimation","rows_in_archive":1,"metrics":["PCK"],"first_row_in_archive_order":{"model":"Occlusion-NET","paper_title":"Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks","paper_url":"/paper/occlusion-net-2d3d-occluded-keypoint","paper_date":"2019-06-01","arxiv_id":null,"code_links":[{"title":"dineshreddy91/Occlusion_Net","url":"https://github.com/dineshreddy91/Occlusion_Net"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/apollocar3d","name":"ApolloCar3D","full_name":"","num_papers_in_archive":17},{"url":"/dataset/vehicle-pose-estimation","name":"CarFusion","full_name":"","num_papers_in_archive":9},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/pose-estimation","name":"Pose Estimation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":20,"of":20,"tagged_in_all":37,"items":[{"url":"/paper/3d-bounding-box-estimation-using-deep","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","date":"2016-12-01","arxiv_id":"1612.00496","repositories_listed":11,"syntology":{"n":27,"n_ran":3,"n_unverified":24,"n_pointer_only":5}},{"url":"/paper/m3d-rpn-monocular-3d-region-proposal-network","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","date":"2019-07-13","arxiv_id":"1907.06038","repositories_listed":4,"syntology":{"n":21,"n_ran":1,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/pose-anything-a-graph-based-approach-for","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","date":"2023-11-29","arxiv_id":"2311.17891","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/kinematic-3d-object-detection-in-monocular","title":"Kinematic 3D Object Detection in Monocular Video","date":"2020-07-19","arxiv_id":"2007.09548","repositories_listed":2,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/rtm3d-real-time-monocular-3d-detection-from","title":"RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving","date":"2020-01-10","arxiv_id":"2001.03343","repositories_listed":2,"syntology":{"n":16,"n_ran":6,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/learning-depth-guided-convolutions-for","title":"Learning Depth-Guided Convolutions for Monocular 3D Object Detection","date":"2019-12-10","arxiv_id":"1912.04799","repositories_listed":2,"syntology":{"n":16,"n_ran":2,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/capex-category-agnostic-pose-estimation-from","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","date":"2024-06-01","arxiv_id":"2406.00384","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-convex-hull-based-vehicle-pose","title":"An Efficient Convex Hull-based Vehicle Pose Estimation Method for 3D LiDAR","date":"2023-02-02","arxiv_id":"2302.01034","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-and-robust-category-level-perception","title":"Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypoints","date":"2022-06-24","arxiv_id":"2206.12498","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-pose-and-shape-estimation-for","title":"Optimal Pose and Shape Estimation for Category-level 3D Object Perception","date":"2021-04-16","arxiv_id":"2104.08383","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-intermediate-representation-for","title":"Exploring intermediate representation for monocular vehicle pose estimation","date":"2020-11-17","arxiv_id":"2011.08464","repositories_listed":1,"syntology":null},{"url":"/paper/gsnet-joint-vehicle-pose-and-shape","title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","date":"2020-07-26","arxiv_id":"2007.13124","repositories_listed":1,"syntology":null},{"url":"/paper/disp-r-cnn-stereo-3d-object-detection-via","title":"Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation","date":"2020-04-07","arxiv_id":"2004.03572","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/monopair-monocular-3d-object-detection-using","title":"MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships","date":"2020-03-01","arxiv_id":"2003.00504","repositories_listed":1,"syntology":null},{"url":"/paper/dsgn-deep-stereo-geometry-network-for-3d","title":"DSGN: Deep Stereo Geometry Network for 3D Object Detection","date":"2020-01-10","arxiv_id":"2001.03398","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/6d-vnet-end-to-end-6dof-vehicle-pose","title":"6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images","date":"2019-06-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/occlusion-net-2d3d-occluded-keypoint","title":"Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/monocular-3d-object-detection-leveraging","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","date":"2019-04-02","arxiv_id":"1904.01690","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/boxcars-improving-fine-grained-recognition-of","title":"BoxCars: Improving Fine-Grained Recognition of Vehicles using 3-D Bounding Boxes in Traffic Surveillance","date":"2017-03-02","arxiv_id":"1703.00686","repositories_listed":1,"syntology":null},{"url":"/paper/subcategory-aware-convolutional-neural","title":"Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection","date":"2016-04-16","arxiv_id":"1604.04693","repositories_listed":1,"syntology":null}],"syntology_records":9,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}