{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/monocular-3d-object-detection-leveraging","title":"Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction","arxiv_id":"1904.01690","date":"2019-04-02","proceeding":"CVPR 2019 6","authors":["Jason Ku","Alex D. Pon","Steven L. Waslander"],"abstract":"We present MonoPSR, a monocular 3D object detection method that leverages\nproposals and shape reconstruction. First, using the fundamental relations of a\npinhole camera model, detections from a mature 2D object detector are used to\ngenerate a 3D proposal per object in a scene. The 3D location of these\nproposals prove to be quite accurate, which greatly reduces the difficulty of\nregressing the final 3D bounding box detection. Simultaneously, a point cloud\nis predicted in an object centered coordinate system to learn local scale and\nshape information. However, the key challenge is how to exploit shape\ninformation to guide 3D localization. As such, we devise aggregate losses,\nincluding a novel projection alignment loss, to jointly optimize these tasks in\nthe neural network to improve 3D localization accuracy. We validate our method\non the KITTI benchmark where we set new state-of-the-art results among\npublished monocular methods, including the harder pedestrian and cyclist\nclasses, while maintaining efficient run-time.","url_abs":"http://arxiv.org/abs/1904.01690v1","url_pdf":"http://arxiv.org/pdf/1904.01690v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"monocular-3d-object-detection-leveraging","repo_url":"https://github.com/ZhixinLai/3D-detection-with-monocular-RGB-image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"monocular-3d-object-detection","task_name":"Monocular 3D Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"vehicle-pose-estimation","task_name":"Vehicle Pose Estimation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/vehicle-pose-estimation-on-kitti-cars-hard","task":"Vehicle Pose Estimation","dataset":"KITTI Cars Hard","model":"MonoPSR","rank_in_archive_order":13,"of":19,"metrics":{"Average Orientation Similarity":"72.26"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.01690","atlas_url":"https://app.syntology.ai/?focus=1904.01690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01690"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhixinLai/3D-detection-with-monocular-RGB-image","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"ddd1724d77acef32","entry":"create_corners","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ddd1724d77acef32"}},{"code_sha256_prefix":"502bf1a47f6d2dbe","entry":"rotation_matrix","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"502bf1a47f6d2dbe"}},{"code_sha256_prefix":"e309a2bcb8e15116","entry":"calc_location","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"e309a2bcb8e15116"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}