{"url":"/task/camera-pose-estimation","name":"Camera Pose Estimation","slug":"camera-pose-estimation","description_markdown":"Camera pose estimation is a crucial task in computer vision and robotics that involves determining the position and orientation (pose) of a camera relative to a given reference frame. This task is essential for various applications, such as augmented reality, 3D reconstruction, SLAM, and autonomous navigation.","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":304,"papers_with_code":134,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":3,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/camera-pose-estimation-on-kitti-odometry","slug":"camera-pose-estimation-on-kitti-odometry","dataset":"KITTI Odometry Benchmark","dataset_url":"/dataset/kitti-odometry-benchmark","rows_in_archive":7,"metrics":["Average Translational Error et[%]","Average Rotational Error er[%]","Absolute Trajectory Error [m]"],"first_row_in_archive_order":{"model":"Manydepth2","paper_title":"Manydepth2: Motion-Aware Self-Supervised Multi-Frame Monocular Depth Estimation in Dynamic Scenes","paper_url":"/paper/mgdepth-motion-guided-cost-volume-for-self","paper_date":"2023-12-23","arxiv_id":"2312.15268","code_links":[{"title":"kaichen-z/rad","url":"https://github.com/kaichen-z/rad"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/kitti-odometry-benchmark","name":"KITTI Odometry Benchmark","full_name":"","num_papers_in_archive":7},{"url":"/dataset/slam2ref","name":"SLAM2REF","full_name":"ConSLAM BIM and GT Poses","num_papers_in_archive":2},{"url":"/dataset/conslam","name":"ConSLAM","full_name":"Construction Dataset for SLAM","num_papers_in_archive":1}],"subtasks":[{"url":"/task/panorama-pose-estimation-n-view","name":"Panorama Pose Estimation (N-view)"}],"parent_tasks":[],"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":30,"of":134,"tagged_in_all":304,"items":[{"url":"/paper/superglue-learning-feature-matching-with","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","date":"2019-11-26","arxiv_id":"1911.11763","repositories_listed":19,"syntology":{"n":22,"n_ran":6,"n_unverified":16,"n_pointer_only":6}},{"url":"/paper/digging-into-self-supervised-monocular-depth","title":"Digging Into Self-Supervised Monocular Depth Estimation","date":"2018-06-04","arxiv_id":"1806.01260","repositories_listed":15,"syntology":{"n":24,"n_ran":17,"n_unverified":7,"n_pointer_only":6}},{"url":"/paper/cubeslam-monocular-3d-object-detection-and","title":"CubeSLAM: Monocular 3D Object SLAM","date":"2018-06-01","arxiv_id":"1806.00557","repositories_listed":5,"syntology":null},{"url":"/paper/loftr-detector-free-local-feature-matching","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","date":"2021-04-01","arxiv_id":"2104.00680","repositories_listed":4,"syntology":{"n":16,"n_ran":14,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/event-based-stereo-visual-odometry","title":"Event-based Stereo Visual Odometry","date":"2020-07-30","arxiv_id":"2007.15548","repositories_listed":4,"syntology":null},{"url":"/paper/dgc-net-dense-geometric-correspondence","title":"DGC-Net: Dense Geometric Correspondence Network","date":"2018-10-19","arxiv_id":"1810.08393","repositories_listed":4,"syntology":null},{"url":"/paper/fishnet-a-camera-localizer-using-deep","title":"FishNet: A Camera Localizer using Deep Recurrent Networks","date":"2019-04-22","arxiv_id":"1904.09722","repositories_listed":3,"syntology":null},{"url":"/paper/geonet-unsupervised-learning-of-dense-depth","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","date":"2018-03-06","arxiv_id":"1803.02276","repositories_listed":3,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/splatam-splat-track-map-3d-gaussians-for","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","date":"2023-12-04","arxiv_id":"2312.02126","repositories_listed":2,"syntology":null},{"url":"/paper/ap-n-p-a-less-constrained-p-n-p-solver-for","title":"AEP$n$P: A Less-constrained EP$n$P Solver for Pose Estimation with Anisotropic Scaling","date":"2023-10-15","arxiv_id":"2310.09982","repositories_listed":2,"syntology":null},{"url":"/paper/lightglue-local-feature-matching-at-light","title":"LightGlue: Local Feature Matching at Light Speed","date":"2023-06-23","arxiv_id":"2306.13643","repositories_listed":2,"syntology":{"n":40,"n_ran":18,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/learning-how-to-robustly-estimate-camera-pose","title":"Learning How To Robustly Estimate Camera Pose in Endoscopic Videos","date":"2023-04-17","arxiv_id":"2304.08023","repositories_listed":2,"syntology":null},{"url":"/paper/silk-simple-learned-keypoints","title":"SiLK -- Simple Learned Keypoints","date":"2023-04-12","arxiv_id":"2304.06194","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/alike-accurate-and-lightweight-keypoint","title":"ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction","date":"2021-12-06","arxiv_id":"2112.02906","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/back-to-the-feature-learning-robust-camera","title":"Back to the Feature: Learning Robust Camera Localization from Pixels to Pose","date":"2021-03-16","arxiv_id":"2103.09213","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/self-supervised-geometric-perception","title":"Self-supervised Geometric Perception","date":"2021-03-04","arxiv_id":"2103.03114","repositories_listed":2,"syntology":null},{"url":"/paper/consensus-guided-correspondence-denoising","title":"Progressive Correspondence Pruning by Consensus Learning","date":"2021-01-03","arxiv_id":"2101.00591","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/why-having-10000-parameters-in-your-camera","title":"Why Having 10,000 Parameters in Your Camera Model is Better Than Twelve","date":"2019-12-05","arxiv_id":"1912.02908","repositories_listed":2,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/unsupervised-scale-consistent-depth-and-ego","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","date":"2019-08-28","arxiv_id":"1908.10553","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/benchmarking-6dof-outdoor-visual-localization","title":"Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions","date":"2017-07-28","arxiv_id":"1707.09092","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-learning-of-depth-and-ego-motion-1","title":"Unsupervised Learning of Depth and Ego-Motion from Video","date":"2017-04-25","arxiv_id":"1704.07813","repositories_listed":2,"syntology":null},{"url":"/paper/spatialtrackerv2-3d-point-tracking-made-easy-1","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","date":"2025-07-16","arxiv_id":"2507.12462","repositories_listed":1,"syntology":null},{"url":"/paper/princeton365-a-diverse-dataset-with-accurate","title":"Princeton365: A Diverse Dataset with Accurate Camera Pose","date":"2025-06-10","arxiv_id":"2506.09035","repositories_listed":1,"syntology":null},{"url":"/paper/recollection-from-pensieve-novel-view","title":"Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos","date":"2025-05-19","arxiv_id":"2505.13440","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-from-another-perspective-evaluating","title":"Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs","date":"2025-04-21","arxiv_id":"2504.15280","repositories_listed":1,"syntology":null},{"url":"/paper/easi3r-estimating-disentangled-motion-from","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","date":"2025-03-31","arxiv_id":"2503.24391","repositories_listed":1,"syntology":null},{"url":"/paper/uni4d-unifying-visual-foundation-models-for","title":"Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video","date":"2025-03-27","arxiv_id":"2503.21761","repositories_listed":1,"syntology":{"n":18,"n_ran":1,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/humanmm-global-human-motion-recovery-from","title":"HumanMM: Global Human Motion Recovery from Multi-shot Videos","date":"2025-03-10","arxiv_id":"2503.07597","repositories_listed":1,"syntology":null},{"url":"/paper/evloc-event-based-visual-localization-in","title":"EVLoc: Event-based Visual Localization in LiDAR Maps via Event-Depth Registration","date":"2025-02-28","arxiv_id":"2503.00167","repositories_listed":1,"syntology":null},{"url":"/paper/fast3r-towards-3d-reconstruction-of-1000","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","date":"2025-01-23","arxiv_id":"2501.13928","repositories_listed":1,"syntology":null}],"syntology_records":12,"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"}}