Browse State-of-the-Art › Homography Estimation
Homography Estimation
71 papers with code · 5 benchmarks · 9 datasets archive 2025-07-28
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.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): COCO 2014 (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| S-COCO (5 rows) | PFNet | Rethinking Planar Homography Estimation Using Perspective Fields | code | — | Compare |
| PDS-COCO (3 rows) | PFNet+biHomE | Perceptual Loss for Robust Unsupervised Homography Estimation | code | Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified | Compare |
| Oxford and Paris (2 rows) | LT | Line as a Visual Sentence: Context-aware Line Descriptor for... | code | — | Compare |
| COCO 2014 (1 row) | PFNet | Rethinking Planar Homography Estimation Using Perspective Fields | code | — | Compare |
| TS-CARWC (1 row) | BHITK | Video-based Sequential Bayesian Homography Estimation for Soccer... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
9 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 134 · with a code link: 71 · where Syntology ran a sample: 18 (16 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 134 tagged: 16 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 134, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
20 Dec 2017 36 repositories listed Syntology community repositories only · 11 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples) · 6 pointer-only (licence)This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision.
-
13 Jun 2016 8 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We present a deep convolutional neural network for estimating the relative homography between a pair of images.
-
6 Jul 2021 4 repositories listedHomography estimation is an important task in computer vision applications, such as image stitching, video stabilization, and camera calibration.
-
8 Jan 2020 3 repositories listedWe present a robust estimator for fitting multiple parametric models of the same form to noisy measurements.
-
9 Jul 2019 3 repositories listedIn this work, we introduce an unsupervised deep learning-based interest point detector and descriptor.
-
12 Sep 2017 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring.
-
12 Apr 2024 2 repositories listedCamera calibration in broadcast sports videos presents numerous challenges for accurate sports field registration due to multiple camera angles, varying camera parameters, and frequent occlusions of the field.
-
13 Mar 2024 2 repositories listedFeature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition.
-
23 Jun 2023 2 repositories listed Syntology official (archive's flag): 26 ran · 33 ran (of which 4 constructed an object rather than computing a result; 26 with no instrument failure: 0 honoured, 0 violated, 26 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified (of 40 harvested samples)We introduce LightGlue, a deep neural network that learns to match local features across images.
-
12 Apr 2023 2 repositories listed Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)Keypoint detection & descriptors are foundational tech-nologies for computer vision tasks like image matching, 3D reconstruction and visual odometry.
-
7 Apr 2023 2 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)Image keypoints and descriptors play a crucial role in many visual measurement tasks.
-
20 Feb 2023 2 repositories listedWe present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.
-
6 Dec 2021 2 repositories listed Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization.
-
30 Sep 2021 2 repositories listedWe perform an extensive evaluation of state-of-the-art (SOTA) Deep Neural Networks (DNNs) across multiple compute regimes, finding our method transfers from our camera motion free da Vinci surgery dataset to videos of…
-
30 Nov 2020 2 repositories listedIn this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation…
-
23 Dec 2019 2 repositories listedBy making the sampling of inlier-outlier sets from point-pair correspondences fully differentiable within the keypoint learning framework, we show that are able to simultaneously self-supervise keypoint description and…
-
20 Mar 2018 2 repositories listedA method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC.
-
6 May 2025 1 repository listedWe then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature.
-
16 Apr 2025 1 repository listedAdditionally, the Mask-Guided Homography Estimation (MGHE) module is presented for eliminating undesired features in the coarse-to-fine homography refinement process.
-
24 Mar 2025 1 repository listedIn our work, we propose a new theoretical model for scoring feature points (keypoints) in the context of the two-view geometry estimation problem.
-
3 Feb 2025 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)To address the challenges of GPS signal interruptions or low illumination, Thermal Geo-localization (TG) employs aerial thermal imagery to align with reference satellite maps to accurately determine the UAV's location.
-
1 Jan 2025 1 repository listedNotably, on 448x448 GoogleMap, GFNet achieves an improvement of +13.
-
1 Jan 2025 1 repository listedSSHNet reformulates the unsupervised cross-modal homography estimation into two supervised sub-problems, each addressed by its specialized network: a homography estimation network and a modality transfer network.
-
20 Nov 2024 1 repository listedTo address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs.
-
26 Sep 2024 1 repository listedWe propose a novel unsupervised cross-modal homography estimation framework, based on interleaved modality transfer and self-supervised homography prediction, named InterNet.
-
18 Jul 2024 1 repository listedIn our work, we seek another way to use the semantic information, that is semantic-aware feature representation learning framework.
-
11 Jul 2024 1 repository listedThe correlation-based homography estimation network and the consistent feature map projection are combined to form the learnable architecture of SCPNet, boosting the unsupervised learning framework.
-
30 May 2024 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)However, the efficiency and effectiveness of current TG approaches, are hindered by dense sampling on satellite maps and geometric noises in thermal query images.
-
8 May 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Precise, pixel-wise geolocalization of astronaut photography is critical to unlocking the potential of this unique type of remotely sensed Earth data, particularly for its use in disaster management and climate change…
-
25 Feb 2024 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified (of 17 harvested samples)Moreover, we design a re-projection error of inliers loss to train the DHE network without additional homography labels, which can also be jointly trained with the backbone network to help it extract the features that…
-
1 Jan 2024 1 repository listed
-
17 Nov 2023 1 repository listed
-
31 Aug 2023 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
7 Jul 2023 1 repository listed
-
22 Jun 2023 1 repository listed
-
19 May 2023 1 repository listed
-
19 Apr 2023 1 repository listed
-
19 Apr 2023 1 repository listed
-
5 Apr 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
1 Jan 2023 1 repository listed
-
6 Dec 2022 1 repository listed
-
1 Nov 2022 1 repository listed
-
30 Aug 2022 1 repository listed
-
25 Aug 2022 1 repository listed
-
24 Jul 2022 1 repository listed
-
6 Jul 2022 1 repository listed
-
8 May 2022 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
30 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
17 Mar 2022 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 3 pointer-only (licence)
-
7 Mar 2022 1 repository listed
-
20 Feb 2022 1 repository listed
-
24 Nov 2021 1 repository listed
-
16 Oct 2021 1 repository listed
-
10 Sep 2021 1 repository listed
-
9 Aug 2021 1 repository listed
-
20 Apr 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
29 Mar 2021 1 repository listed
-
24 Dec 2020 1 repository listed
-
3 Dec 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
20 Jul 2020 1 repository listed
-
17 Jul 2020 1 repository listed
-
9 Jun 2020 1 repository listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (of 11 harvested samples) · 11 pointer-only (licence)
-
5 Apr 2020 1 repository listed
-
12 Sep 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
27 Jun 2019 1 repository listed
-
26 May 2019 1 repository listed
-
1 May 2019 1 repository listed
-
20 Feb 2018 1 repository listed
-
19 Jul 2017 1 repository listed
-
HomographyAD: Deep Anomaly Detection Using Self Homography Learning10 Jun 2025 0 repositories listed
-
Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025 0 repositories listed
-
Words as Geometric Features: Estimating Homography using Optical Character Recognition as Compressed Image Representation25 May 2025 0 repositories listed
-
Decoupled Geometric Parameterization and its Application in Deep Homography Estimation22 May 2025 0 repositories listed
-
SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement9 Dec 2024 0 repositories listed
-
HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation11 Nov 2024 0 repositories listed
-
ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shifts26 Sep 2024 0 repositories listed
-
TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image14 May 2024 0 repositories listed
-
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV16 Mar 2024 0 repositories listed
-
Are Semi-Dense Detector-Free Methods Good at Matching Local Features?13 Feb 2024 0 repositories listed
-
Noisy One-point Homographies are Surprisingly Good1 Jan 2024 0 repositories listed
-
Automated Camera Calibration via Homography Estimation with GNNs5 Nov 2023 0 repositories listed
-
FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer20 Oct 2023 0 repositories listed
-
Scene-Aware Feature Matching19 Aug 2023 0 repositories listed
-
Homography Estimation in Complex Topological Scenes2 Aug 2023 0 repositories listed
-
AffineGlue: Joint Matching and Robust Estimation28 Jul 2023 0 repositories listed
-
Pentagon-Match (PMatch): Identification of View-Invariant Planar Feature for Local Feature Matching-Based Homography Estimation27 May 2023 0 repositories listed
-
Medical Image Analysis using Deep Relational Learning28 Mar 2023 0 repositories listed
-
PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignment21 Mar 2023 0 repositories listed
-
Nonlinear constructive observer design for direct homography estimation10 Mar 2023 0 repositories listed
-
ParaFormer: Parallel Attention Transformer for Efficient Feature Matching2 Mar 2023 0 repositories listed
-
GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning23 Jan 2023 0 repositories listed
-
A Large-Scale Homography Benchmark1 Jan 2023 0 repositories listed
-
SiLK: Simple Learned Keypoints1 Jan 2023 0 repositories listed
-
AbHE: All Attention-based Homography Estimation6 Dec 2022 0 repositories listed
-
SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation30 Aug 2022 0 repositories listed
-
Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution23 Jun 2022 0 repositories listed
-
Road-aware Monocular Structure from Motion and Homography Estimation16 Dec 2021 0 repositories listed
-
Pixel-wise Deep Image Stitching12 Dec 2021 0 repositories listed
Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections