{"url":"/task/visual-odometry","name":"Visual Odometry","slug":"visual-odometry","description_markdown":"**Visual Odometry** is an important area of information fusion in which the central aim is to estimate the pose of a robot using data collected by visual sensors.\n\n\n<span class=\"description-source\">Source: [Bi-objective Optimization for Robust RGB-D Visual Odometry ](https://arxiv.org/abs/1411.7445)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":408,"papers_with_code":124,"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":26,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/visual-odometry-on-euroc-mav","slug":"visual-odometry-on-euroc-mav","dataset":"EuRoC MAV","dataset_url":"/dataset/euroc-mav","rows_in_archive":1,"metrics":["Relative Position Error Translation [cm]"],"first_row_in_archive_order":{"model":"CIVO","paper_title":"Brain-Inspired Visual Odometry: Balancing Speed and Interpretability through a System of Systems Approach","paper_url":"/paper/brain-inspired-visual-odometry-balancing","paper_date":"2023-12-20","arxiv_id":"2312.13162","code_links":[{"title":"habib-Boloorchi/CIVO-Visual-Odometry-","url":"https://github.com/habib-Boloorchi/CIVO-Visual-Odometry-"}],"syntology":null}}],"datasets":[{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/tum-rgb-d","name":"TUM RGB-D","full_name":"TUM RGB-D","num_papers_in_archive":235},{"url":"/dataset/virtual-kitti","name":"Virtual KITTI","full_name":"","num_papers_in_archive":133},{"url":"/dataset/tartanair","name":"TartanAir","full_name":"","num_papers_in_archive":107},{"url":"/dataset/virtual-kitti-2","name":"Virtual KITTI 2","full_name":"","num_papers_in_archive":53},{"url":"/dataset/event-camera-dataset","name":"Event-Camera Dataset","full_name":"","num_papers_in_archive":51},{"url":"/dataset/new-college","name":"New College","full_name":"","num_papers_in_archive":17},{"url":"/dataset/4seasons","name":"4Seasons","full_name":"","num_papers_in_archive":15},{"url":"/dataset/euroc-mav","name":"EuRoC MAV","full_name":"EuRoC MAV","num_papers_in_archive":13},{"url":"/dataset/tum-monovo","name":"TUM monoVO","full_name":"TUM monoVO","num_papers_in_archive":11},{"url":"/dataset/alto","name":"ALTO","full_name":"Aerial-view Large-scale Terrain-Oriented","num_papers_in_archive":4},{"url":"/dataset/endoslam","name":"EndoSLAM","full_name":"Endoscopic SLAM dataset","num_papers_in_archive":4},{"url":"/dataset/tum-visual-inertial-dataset","name":"TUM Visual-Inertial Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/aqualoc","name":"Aqualoc","full_name":"","num_papers_in_archive":2},{"url":"/dataset/baseprod","name":"BASEPROD","full_name":"The Bardenas Semi-Desert Planetary Rover Dataset","num_papers_in_archive":2},{"url":"/dataset/drunkard-s-dataset","name":"Drunkard's Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/slam2ref","name":"SLAM2REF","full_name":"ConSLAM BIM and GT Poses","num_papers_in_archive":2},{"url":"/dataset/aut-vi","name":"AUT-VI","full_name":"Amirkabir campus dataset","num_papers_in_archive":1},{"url":"/dataset/bpod","name":"BPOD","full_name":"","num_papers_in_archive":1},{"url":"/dataset/consinv-dataset","name":"ConsInv Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/conslam","name":"ConSLAM","full_name":"Construction Dataset for SLAM","num_papers_in_archive":1},{"url":"/dataset/kaist-vio-dataset","name":"KAIST VIO Dataset","full_name":"KAIST VIO Dataset","num_papers_in_archive":1},{"url":"/dataset/minenav","name":"MineNav","full_name":"","num_papers_in_archive":1},{"url":"/dataset/uma-vi-dataset","name":"UMA-VI Dataset","full_name":"The UMA-VI dataset: Visual--inertial odometry in low-textured and dynamic illumination environments","num_papers_in_archive":1},{"url":"/dataset/ms2-dataset-rgb-nir-thermal-images-lidar-gps","name":"Multi-Spectral Stereo Dataset  (RGB, NIR, thermal images, LiDAR, GPS/IMU)","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/face-anti-spoofing","name":"Face Anti-Spoofing"},{"url":"/task/monocular-visual-odometry","name":"Monocular Visual Odometry"}],"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":124,"tagged_in_all":408,"items":[{"url":"/paper/the-double-sphere-camera-model","title":"The Double Sphere Camera Model","date":"2018-07-24","arxiv_id":"1807.08957","repositories_listed":9,"syntology":null},{"url":"/paper/orb-slam2-an-open-source-slam-system-for","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","date":"2016-10-20","arxiv_id":"1610.06475","repositories_listed":7,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/deepvo-towards-end-to-end-visual-odometry","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","date":"2017-09-25","arxiv_id":"1709.08429","repositories_listed":5,"syntology":null},{"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/towards-better-generalization-joint-depth","title":"Towards Better Generalization: Joint Depth-Pose Learning without PoseNet","date":"2020-04-03","arxiv_id":"2004.01314","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-general-optimization-based-framework-for","title":"A General Optimization-based Framework for Local Odometry Estimation with Multiple Sensors","date":"2019-01-11","arxiv_id":"1901.03638","repositories_listed":4,"syntology":null},{"url":"/paper/the-tum-vi-benchmark-for-evaluating-visual","title":"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry","date":"2018-04-17","arxiv_id":"1804.06120","repositories_listed":4,"syntology":null},{"url":"/paper/stereo-relative-pose-from-line-and-point-1","title":"Stereo relative pose from line and point feature triplets","date":"2019-06-29","arxiv_id":"1907.00276","repositories_listed":3,"syntology":null},{"url":"/paper/pl-slam-a-stereo-slam-system-through-the","title":"PL-SLAM: a Stereo SLAM System through the Combination of Points and Line Segments","date":"2017-05-26","arxiv_id":"1705.09479","repositories_listed":3,"syntology":null},{"url":"/paper/ecarla-scenes-a-synthetically-generated","title":"eCARLA-scenes: A synthetically generated dataset for event-based optical flow prediction","date":"2024-12-12","arxiv_id":"2412.09209","repositories_listed":2,"syntology":null},{"url":"/paper/fast-livo2-fast-direct-lidar-inertial-visual","title":"FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry","date":"2024-08-26","arxiv_id":"2408.14035","repositories_listed":2,"syntology":null},{"url":"/paper/imu-aided-event-based-stereo-visual-odometry","title":"IMU-Aided Event-based Stereo Visual Odometry","date":"2024-05-07","arxiv_id":"2405.04071","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/spatiotemporal-registration-for-event-based","title":"Spatiotemporal Registration for Event-based Visual Odometry","date":"2021-03-10","arxiv_id":"2103.05955","repositories_listed":2,"syntology":null},{"url":"/paper/df-vo-what-should-be-learnt-for-visual","title":"DF-VO: What Should Be Learnt for Visual Odometry?","date":"2021-03-01","arxiv_id":"2103.00933","repositories_listed":2,"syntology":null},{"url":"/paper/tartanvo-a-generalizable-learning-based-vo","title":"TartanVO: A Generalizable Learning-based VO","date":"2020-10-31","arxiv_id":"2011.00359","repositories_listed":2,"syntology":{"n":23,"n_ran":3,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/empty-cities-a-dynamic-object-invariant-space","title":"Empty Cities: a Dynamic-Object-Invariant Space for Visual SLAM","date":"2020-10-15","arxiv_id":"2010.07646","repositories_listed":2,"syntology":null},{"url":"/paper/robust-ego-and-object-6-dof-motion-estimation","title":"Robust Ego and Object 6-DoF Motion Estimation and Tracking","date":"2020-07-28","arxiv_id":"2007.13993","repositories_listed":2,"syntology":null},{"url":"/paper/nonparametric-continuous-sensor-registration","title":"Nonparametric Continuous Sensor Registration","date":"2020-01-08","arxiv_id":"2001.04286","repositories_listed":2,"syntology":null},{"url":"/paper/neural-outlier-rejection-for-self-supervised-1","title":"Neural Outlier Rejection for Self-Supervised Keypoint Learning","date":"2019-12-23","arxiv_id":"1912.10615","repositories_listed":2,"syntology":null},{"url":"/paper/190909803","title":"Visual Odometry Revisited: What Should Be Learnt?","date":"2019-09-21","arxiv_id":"1909.09803","repositories_listed":2,"syntology":null},{"url":"/paper/place-recognition-for-stereo-visualodometry","title":"A Fast and Robust Place Recognition Approach for Stereo Visual Odometry Using LiDAR Descriptors","date":"2019-09-16","arxiv_id":"1909.07267","repositories_listed":2,"syntology":null},{"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/edge-direct-visual-odometry","title":"Edge-Direct Visual Odometry","date":"2019-06-11","arxiv_id":"1906.04838","repositories_listed":2,"syntology":null},{"url":"/paper/cnn-svo-improving-the-mapping-in-semi-direct","title":"CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction","date":"2018-10-01","arxiv_id":"1810.01011","repositories_listed":2,"syntology":null},{"url":"/paper/fast-cylinder-and-plane-extraction-from-depth","title":"Fast Cylinder and Plane Extraction from Depth Cameras for Visual Odometry","date":"2018-03-06","arxiv_id":"1803.02380","repositories_listed":2,"syntology":null},{"url":"/paper/the-event-camera-dataset-and-simulator-event","title":"The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM","date":"2016-10-26","arxiv_id":"1610.08336","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/reducing-drift-in-visual-odometry-by","title":"Reducing Drift in Visual Odometry by Inferring Sun Direction Using a Bayesian Convolutional Neural Network","date":"2016-09-20","arxiv_id":"1609.05993","repositories_listed":2,"syntology":null},{"url":"/paper/direct-sparse-odometry","title":"Direct Sparse Odometry","date":"2016-07-09","arxiv_id":"1607.02565","repositories_listed":2,"syntology":null},{"url":"/paper/an-online-adaptation-method-for-robust-depth","title":"An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World","date":"2025-04-16","arxiv_id":"2504.11698","repositories_listed":1,"syntology":null}],"syntology_records":6,"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"}}