{"url":"/task/homography-estimation","name":"Homography Estimation","slug":"homography-estimation","description_markdown":"**Homography estimation** is a technique used in computer vision and image processing to find the relationship between two images of the same scene, but captured from different viewpoints. It is used to align images, correct for perspective distortions, or perform image stitching. In order to estimate the homography, a set of corresponding points between the two images must be found, and a mathematical model must be fit to these points. There are various algorithms and techniques that can be used to perform homography estimation, including direct methods, RANSAC, and machine learning-based approaches.","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":134,"papers_with_code":71,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/homography-estimation-on-s-coco","slug":"homography-estimation-on-s-coco","dataset":"S-COCO","dataset_url":"/dataset/s-coco","rows_in_archive":5,"metrics":["MACE"],"first_row_in_archive_order":{"model":"PFNet","paper_title":"Rethinking Planar Homography Estimation Using Perspective Fields","paper_url":"/paper/rethinking-planar-homography-estimation-using","paper_date":"2019-05-26","arxiv_id":null,"code_links":[{"title":"ruizengalways/PFNet","url":"https://github.com/ruizengalways/PFNet"}],"syntology":null}},{"leaderboard":"/sota/homography-estimation-on-pds-coco","slug":"homography-estimation-on-pds-coco","dataset":"PDS-COCO","dataset_url":"/dataset/pds-coco","rows_in_archive":3,"metrics":["MACE"],"first_row_in_archive_order":{"model":"PFNet+biHomE","paper_title":"Perceptual Loss for Robust Unsupervised Homography Estimation","paper_url":"/paper/perceptual-loss-for-robust-unsupervised","paper_date":"2021-04-20","arxiv_id":"2104.10011","code_links":[{"title":"NeurAI-Lab/biHomE","url":"https://github.com/NeurAI-Lab/biHomE"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/homography-estimation-on-oxford-and-paris","slug":"homography-estimation-on-oxford-and-paris","dataset":"Oxford and Paris","dataset_url":null,"rows_in_archive":2,"metrics":["AUC@10px","AUC@20px","AUC@5px","F","P","R"],"first_row_in_archive_order":{"model":"LT","paper_title":"Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization","paper_url":"/paper/line-as-a-visual-sentence-context-aware-line","paper_date":"2021-09-10","arxiv_id":"2109.04753","code_links":[{"title":"yosungho/LineTR","url":"https://github.com/yosungho/LineTR"}],"syntology":null}},{"leaderboard":"/sota/homography-estimation-on-coco-2014","slug":"homography-estimation-on-coco-2014","dataset":"COCO 2014","dataset_url":"/dataset/coco","rows_in_archive":1,"metrics":["MACE"],"first_row_in_archive_order":{"model":"PFNet","paper_title":"Rethinking Planar Homography Estimation Using Perspective Fields","paper_url":"/paper/rethinking-planar-homography-estimation-using","paper_date":"2019-05-26","arxiv_id":null,"code_links":[{"title":"ruizengalways/PFNet","url":"https://github.com/ruizengalways/PFNet"}],"syntology":null}},{"leaderboard":"/sota/homography-estimation-on-ts-carwc","slug":"homography-estimation-on-ts-carwc","dataset":"TS-CARWC","dataset_url":null,"rows_in_archive":1,"metrics":["Mean IoU entire","Mean IoU part","Mean projection error","Mean re-projection error"],"first_row_in_archive_order":{"model":"BHITK","paper_title":"Video-based Sequential Bayesian Homography Estimation for Soccer Field Registration","paper_url":"/paper/video-based-sequential-bayesian-homography","paper_date":"2023-11-17","arxiv_id":"2311.10361","code_links":[{"title":"paulkie99/keypointannotator","url":"https://github.com/paulkie99/keypointannotator"}],"syntology":null}}],"datasets":[{"url":"/dataset/coco","name":"COCO (Common Objects in Context)","full_name":"Common Objects in Context","num_papers_in_archive":11922},{"url":"/dataset/pot-210","name":"POT-210","full_name":"Planar Object Tracking in the Wild: A Benchmark","num_papers_in_archive":7},{"url":"/dataset/s-coco","name":"S-COCO","full_name":"Synthetic COCO","num_papers_in_archive":7},{"url":"/dataset/yud","name":"YUD+","full_name":"Additional Vanishing Point Labels for the York Urban Database","num_papers_in_archive":7},{"url":"/dataset/nyu-vp","name":"NYU-VP","full_name":"","num_papers_in_archive":5},{"url":"/dataset/pds-coco","name":"PDS-COCO","full_name":"Photometrically Distorted Synthetic COCO","num_papers_in_archive":4},{"url":"/dataset/boson-nighttime","name":"Boson-nighttime","full_name":"","num_papers_in_archive":3},{"url":"/dataset/carwc","name":"CARWC","full_name":"Consolidated and refined world cup dataset","num_papers_in_archive":2},{"url":"/dataset/vidset","name":"VidSet","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/interest-point-detection","name":"Interest Point Detection"}],"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":71,"tagged_in_all":134,"items":[{"url":"/paper/superpoint-self-supervised-interest-point","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","date":"2017-12-20","arxiv_id":"1712.07629","repositories_listed":36,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/deep-image-homography-estimation","title":"Deep Image Homography Estimation","date":"2016-06-13","arxiv_id":"1606.03798","repositories_listed":8,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/depth-aware-multi-grid-deep-homography","title":"Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation","date":"2021-07-06","arxiv_id":"2107.02524","repositories_listed":4,"syntology":null},{"url":"/paper/consac-robust-multi-model-fitting-by","title":"CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus","date":"2020-01-08","arxiv_id":"2001.02643","repositories_listed":3,"syntology":null},{"url":"/paper/unsuperpoint-end-to-end-unsupervised-interest","title":"UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor","date":"2019-07-09","arxiv_id":"1907.04011","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-deep-homography-a-fast-and","title":"Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model","date":"2017-09-12","arxiv_id":"1709.03966","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/no-bells-just-whistles-sports-field","title":"PnLCalib: Sports Field Registration via Points and Lines Optimization","date":"2024-04-12","arxiv_id":"2404.08401","repositories_listed":2,"syntology":null},{"url":"/paper/nerf-supervised-feature-point-detection-and","title":"NeRF-Supervised Feature Point Detection and Description","date":"2024-03-13","arxiv_id":"2403.08156","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/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/aliked-a-lighter-keypoint-and-descriptor","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","date":"2023-04-07","arxiv_id":"2304.03608","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/a-large-scale-homography-benchmark","title":"A Large Scale Homography Benchmark","date":"2023-02-20","arxiv_id":"2302.09997","repositories_listed":2,"syntology":null},{"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/deep-homography-estimation-in-dynamic","title":"Deep Homography Estimation in Dynamic Surgical Scenes for Laparoscopic Camera Motion Extraction","date":"2021-09-30","arxiv_id":"2109.15098","repositories_listed":2,"syntology":null},{"url":"/paper/dut-learning-video-stabilization-by-simply","title":"DUT: Learning Video Stabilization by Simply Watching Unstable Videos","date":"2020-11-30","arxiv_id":"2011.14574","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/magsac-marginalizing-sample-consensus","title":"MAGSAC: marginalizing sample consensus","date":"2018-03-20","arxiv_id":"1803.07469","repositories_listed":2,"syntology":null},{"url":"/paper/liftfeat-3d-geometry-aware-local-feature","title":"LiftFeat: 3D Geometry-Aware Local Feature Matching","date":"2025-05-06","arxiv_id":"2505.03422","repositories_listed":1,"syntology":null},{"url":"/paper/codinghomo-bootstrapping-deep-homography-with","title":"CodingHomo: Bootstrapping Deep Homography With Video Coding","date":"2025-04-16","arxiv_id":"2504.12165","repositories_listed":1,"syntology":null},{"url":"/paper/good-keypoints-for-the-two-view-geometry","title":"Good Keypoints for the Two-View Geometry Estimation Problem","date":"2025-03-24","arxiv_id":"2503.18767","repositories_listed":1,"syntology":null},{"url":"/paper/uasthn-uncertainty-aware-deep-homography","title":"UASTHN: Uncertainty-Aware Deep Homography Estimation for UAV Satellite-Thermal Geo-localization","date":"2025-02-03","arxiv_id":"2502.01035","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/sshnet-unsupervised-cross-modal-homography","title":"SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/adapting-dense-matching-for-homography","title":"Adapting Dense Matching for Homography Estimation with Grid-based Acceleration","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-homography-estimation-on","title":"Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization","date":"2024-11-20","arxiv_id":"2411.13036","repositories_listed":1,"syntology":null},{"url":"/paper/internet-unsupervised-cross-modal-homography","title":"InterNet: Unsupervised Cross-modal Homography Estimation Based on Interleaved Modality Transfer and Self-supervised Homography Prediction","date":"2024-09-26","arxiv_id":"2409.17993","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-aware-representation-learning-for","title":"Semantic-aware Representation Learning for Homography Estimation","date":"2024-07-18","arxiv_id":"2407.13284","repositories_listed":1,"syntology":null},{"url":"/paper/scpnet-unsupervised-cross-modal-homography","title":"SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning","date":"2024-07-11","arxiv_id":"2407.08148","repositories_listed":1,"syntology":null},{"url":"/paper/sthn-deep-homography-estimation-for-uav","title":"STHN: Deep Homography Estimation for UAV Thermal Geo-localization with Satellite Imagery","date":"2024-05-30","arxiv_id":"2405.20470","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/earthmatch-iterative-coregistration-for-fine","title":"EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography","date":"2024-05-08","arxiv_id":"2405.05422","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/deep-homography-estimation-for-visual-place","title":"Deep Homography Estimation for Visual Place Recognition","date":"2024-02-25","arxiv_id":"2402.16086","repositories_listed":1,"syntology":{"n":17,"n_ran":8,"n_unverified":9,"n_pointer_only":0}}],"syntology_records":11,"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"}}