{"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/self-supervised-3d-keypoint-learning-for-ego","title":"Self-Supervised 3D Keypoint Learning for Ego-motion Estimation","arxiv_id":"1912.03426","date":"2019-12-07","proceeding":null,"authors":["Jiexiong Tang","Rares Ambrus","Vitor Guizilini","Sudeep Pillai","Hanme Kim","Patric Jensfelt","Adrien Gaidon"],"abstract":"Detecting and matching robust viewpoint-invariant keypoints is critical for visual SLAM and Structure-from-Motion. State-of-the-art learning-based methods generate training samples via homography adaptation to create 2D synthetic views with known keypoint matches from a single image. This approach, however, does not generalize to non-planar 3D scenes with illumination variations commonly seen in real-world videos. In this work, we propose self-supervised learning of depth-aware keypoints directly from unlabeled videos. We jointly learn keypoint and depth estimation networks by combining appearance and geometric matching via a differentiable structure-from-motion module based on Procrustean residual pose correction. We describe how our self-supervised keypoints can be integrated into state-of-the-art visual odometry frameworks for robust and accurate ego-motion estimation of autonomous vehicles in real-world conditions.","url_abs":"https://arxiv.org/abs/1912.03426v3","url_pdf":"https://arxiv.org/pdf/1912.03426v3.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":"self-supervised-3d-keypoint-learning-for-ego","repo_url":"https://github.com/TRI-ML/KP3D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"geometric-matching","task_name":"Geometric Matching"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"visual-odometry","task_name":"Visual Odometry"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.03426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.03426"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/TRI-ML/KP3D","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"official":{"samples":9,"ran":1,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"a739072b350093e7","entry":"upsample","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/networks/keypoint_resnet.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/networks/keypoint_resnet.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a739072b350093e7"}},{"code_sha256_prefix":"3a7ae036e8d2457d","entry":"construct_K","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/geometry/camera.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/geometry/camera.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a7ae036e8d2457d"}},{"code_sha256_prefix":"d462e2f3cd90e4fc","entry":"image_grid","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/utils/image.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/utils/image.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d462e2f3cd90e4fc"}},{"code_sha256_prefix":"a04d16d3da568d50","entry":"invert_pose","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/geometry/pose.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/geometry/pose.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a04d16d3da568d50"}},{"code_sha256_prefix":"5b11715c4e4a1c7f","entry":"meshgrid","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/utils/image.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/utils/image.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b11715c4e4a1c7f"}},{"code_sha256_prefix":"3c91deaa8c673fd6","entry":"read_calib_file","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/datasets/kitti_odometry_dataset.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/datasets/kitti_odometry_dataset.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c91deaa8c673fd6"}},{"code_sha256_prefix":"b9ff60bfcb5831da","entry":"scale_intrinsics","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/geometry/camera.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/geometry/camera.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9ff60bfcb5831da"}},{"code_sha256_prefix":"5487d34d4f82c3f1","entry":"select_k_best","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/evaluation/descriptor_evaluation.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/evaluation/descriptor_evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5487d34d4f82c3f1"}},{"code_sha256_prefix":"1359c08a986ae150","entry":"to_gray_normalized","repo":"TRI-ML/KP3D","repo_kind":"official","path":"kp3d/utils/image.py","file_url":"https://github.com/TRI-ML/KP3D/blob/HEAD/kp3d/utils/image.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1359c08a986ae150"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}