Image Matching

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

4 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

16 shown of 16 papers with code (18 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• SuperGlue: Learning Feature Matching with Graph Neural Networks
  26 Nov 2019 19 repositories listed Syntology ran 6 of 22 samples · 16 unverified · 6 pointer-only (licence)
  This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
• What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
  3 Apr 2019 13 repositories listed Syntology ran 0 of 19 samples · 19 unverified
  Many new proposals for scene text recognition (STR) models have been introduced in recent years.
• Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
  5 Oct 2019 5 repositories listed Syntology ran 0 of 20 samples · 20 unverified
  This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.
• LoFTR: Detector-Free Local Feature Matching with Transformers
  1 Apr 2021 4 repositories listed Syntology ran 14 of 16 samples · 2 unverified
  We present a novel method for local image feature matching.
• D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
  9 May 2019 4 repositories listed Syntology ran 1 of 13 samples · 12 unverified · 1 pointer-only (licence)
  In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions.
• Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters
  1 Apr 2019 3 repositories listed
  We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture.
• Repeatability Is Not Enough: Learning Affine Regions via Discriminability
  17 Nov 2017 3 repositories listed
  A method for learning local affine-covariant regions is presented.
• LightGlue: Local Feature Matching at Light Speed
  23 Jun 2023 2 repositories listed Syntology ran 18 of 40 samples · 22 unverified
  We introduce LightGlue, a deep neural network that learns to match local features across images.
• DISK: Learning local features with policy gradient
  24 Jun 2020 2 repositories listed Syntology ran 8 of 9 samples · 1 unverified
  Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints.
• R2D2: Reliable and Repeatable Detector and Descriptor
  1 Dec 2019 2 repositories listed
  We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
• GIM: Learning Generalizable Image Matcher From Internet Videos
  16 Feb 2024 1 repository listed Syntology ran 12 of 17 samples · 5 unverified
  Given an architecture, GIM first trains it on standard domain-specific datasets and then combines it with complementary matching methods to create dense labels on nearby frames of novel videos.
• RoMa: Robust Dense Feature Matching
  24 May 2023 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  The aim is to learn a robust model, i.
• Shared Coupling-bridge for Weakly Supervised Local Feature Learning
  14 Dec 2022 1 repository listed
  Sparse local feature extraction is usually believed to be of important significance in typical vision tasks such as simultaneous localization and mapping, image matching and 3D reconstruction.
• DKM: Dense Kernelized Feature Matching for Geometry Estimation
  1 Feb 2022 1 repository listed
  This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation.
• Decoupling Makes Weakly Supervised Local Feature Better
  8 Jan 2022 1 repository listed
  Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
• Three things everyone should know to improve object retrieval
  16 Jun 2012 1 repository listed
  The objective of this work is object retrieval in large scale image datasets, where the object is specified by an image query and retrieval should be immediate at run time in the manner of Video Google [28].

Syntology lines on 9 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. Read from the graph 2026-09-24.