{"url":"/task/loop-closure-detection","name":"Loop Closure Detection","slug":"loop-closure-detection","description_markdown":"Loop closure detection is the process of detecting whether an agent has returned to a previously visited location.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Backtracking Regression Forests for Accurate Camera Relocalization](https://github.com/LiliMeng/btrf) )</span>","categories":[{"name":"Computer Code","url":"/area/computer-code"},{"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":89,"papers_with_code":31,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/kaist-urban","name":"KAIST Urban","full_name":"","num_papers_in_archive":19},{"url":"/dataset/new-college","name":"New College","full_name":"","num_papers_in_archive":17},{"url":"/dataset/aut-vi","name":"AUT-VI","full_name":"Amirkabir campus dataset","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles"}],"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":31,"tagged_in_all":89,"items":[{"url":"/paper/dxslam-a-robust-and-efficient-visual-slam","title":"DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features","date":"2020-08-12","arxiv_id":"2008.05416","repositories_listed":3,"syntology":null},{"url":"/paper/fast-and-incremental-loop-closure-detection-1","title":"Fast and Incremental Loop Closure Detection with Deep Features and Proximity Graphs","date":"2020-09-29","arxiv_id":"2010.11703","repositories_listed":2,"syntology":null},{"url":"/paper/forestlpr-lidar-place-recognition-in-forests","title":"ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images","date":"2025-03-06","arxiv_id":"2503.04475","repositories_listed":1,"syntology":null},{"url":"/paper/lidar-loop-closure-detection-using-semantic","title":"LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks","date":"2025-01-31","arxiv_id":"2501.19382","repositories_listed":1,"syntology":null},{"url":"/paper/a-minimal-subset-approach-for-efficient-and","title":"Balancing Accuracy and Efficiency for Large-Scale SLAM: A Minimal Subset Approach for Scalable Loop Closures","date":"2025-01-03","arxiv_id":"2501.01791","repositories_listed":1,"syntology":null},{"url":"/paper/why-sample-space-matters-keyframe-sampling","title":"Why Sample Space Matters: Keyframe Sampling Optimization for LiDAR-based Place Recognition","date":"2024-10-03","arxiv_id":"2410.02643","repositories_listed":1,"syntology":null},{"url":"/paper/gv-bench-benchmarking-local-feature-matching","title":"GV-Bench: Benchmarking Local Feature Matching for Geometric Verification of Long-term Loop Closure Detection","date":"2024-07-16","arxiv_id":"2407.11736","repositories_listed":1,"syntology":null},{"url":"/paper/overlapmamba-novel-shift-state-space-model","title":"OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition","date":"2024-05-13","arxiv_id":"2405.07966","repositories_listed":1,"syntology":null},{"url":"/paper/loop-closure-detection-based-on-object-level","title":"Loop Closure Detection Based on Object-level Spatial Layout and Semantic Consistency","date":"2023-04-11","arxiv_id":"2304.05146","repositories_listed":1,"syntology":null},{"url":"/paper/region-prediction-for-efficient-robot","title":"Region Prediction for Efficient Robot Localization on Large Maps","date":"2023-03-01","arxiv_id":"2303.00295","repositories_listed":1,"syntology":null},{"url":"/paper/orchnet-a-robust-global-feature-aggregation","title":"ORCHNet: A Robust Global Feature Aggregation approach for 3D LiDAR-based Place recognition in Orchards","date":"2023-03-01","arxiv_id":"2303.00477","repositories_listed":1,"syntology":null},{"url":"/paper/contour-context-abstract-structural","title":"Contour Context: Abstract Structural Distribution for 3D LiDAR Loop Detection and Metric Pose Estimation","date":"2023-02-13","arxiv_id":"2302.06149","repositories_listed":1,"syntology":null},{"url":"/paper/general-place-recognition-survey-towards-the","title":"General Place Recognition Survey: Towards the Real-world Autonomy Age","date":"2022-09-09","arxiv_id":"2209.04497","repositories_listed":1,"syntology":null},{"url":"/paper/phase-slam-phase-based-simultaneous","title":"Phase-SLAM: Phase Based Simultaneous Localization and Mapping for Mobile Structured Light Illumination Systems","date":"2022-01-22","arxiv_id":"2201.09048","repositories_listed":1,"syntology":null},{"url":"/paper/why-so-deep-towards-boosting-previously","title":"Why-So-Deep: Towards Boosting Previously Trained Models for Visual Place Recognition","date":"2022-01-10","arxiv_id":"2201.03212","repositories_listed":1,"syntology":null},{"url":"/paper/loop-closure-detection-using-local-3d-deep","title":"Loop closure detection using local 3D deep descriptors","date":"2021-10-31","arxiv_id":"2111.00440","repositories_listed":1,"syntology":null},{"url":"/paper/ct-icp-real-time-elastic-lidar-odometry-with","title":"CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closure","date":"2021-09-27","arxiv_id":"2109.12979","repositories_listed":1,"syntology":null},{"url":"/paper/airloop-lifelong-loop-closure-detection","title":"AirLoop: Lifelong Loop Closure Detection","date":"2021-09-18","arxiv_id":"2109.08975","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-descriptive-power-of-lidar-intensity","title":"On the descriptive power of LiDAR intensity images for segment-based loop closing in 3-D SLAM","date":"2021-08-03","arxiv_id":"2108.01383","repositories_listed":1,"syntology":null},{"url":"/paper/probabilistic-appearance-invariant-topometric","title":"Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness","date":"2021-07-16","arxiv_id":"2107.07707","repositories_listed":1,"syntology":null},{"url":"/paper/attdlnet-attention-based-dl-network-for-3d","title":"AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition","date":"2021-06-17","arxiv_id":"2106.09637","repositories_listed":1,"syntology":null},{"url":"/paper/ndt-transformer-large-scale-3d-point-cloud","title":"NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation","date":"2021-03-23","arxiv_id":"2103.12292","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/lcdnet-deep-loop-closure-detection-for-lidar","title":"LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM","date":"2021-03-08","arxiv_id":"2103.05056","repositories_listed":1,"syntology":null},{"url":"/paper/visual-place-recognition-a-survey-from-deep","title":"Visual place recognition: A survey from deep learning perspective","date":"2020-11-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/place-recognition-in-forests-with-urquhart","title":"Place Recognition in Forests with Urquhart Tessellations","date":"2020-09-23","arxiv_id":"2010.03026","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-object-tracking-and-masking-for","title":"Dynamic Object Tracking and Masking for Visual SLAM","date":"2020-07-31","arxiv_id":"2008.00072","repositories_listed":1,"syntology":null},{"url":"/paper/intensity-scan-context-coding-intensity-and","title":"Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection","date":"2020-03-12","arxiv_id":"2003.05656","repositories_listed":1,"syntology":null},{"url":"/paper/kernel-learning-for-visual-perception","title":"Kernel learning for visual perception","date":"2019-12-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-incremental-loop-closure-detection","title":"Fast and Incremental Loop Closure Detection Using Proximity Graphs","date":"2019-11-25","arxiv_id":"1911.10752","repositories_listed":1,"syntology":null},{"url":"/paper/line-as-object-datasets-and-framework-for","title":"Sem-LSD: A Learning-based Semantic Line Segment Detector","date":"2019-09-14","arxiv_id":"1909.06591","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}