Datasets › HPatches

HPatches (Homography-patches dataset)

Introduced by Vassileios Balntas et al. in HPatches: A benchmark and evaluation of handcrafted and learned local descriptors1 Jan 2017 archive 2025-07-28

The HPatches is a recent dataset for local patch descriptor evaluation that consists of 116 sequences of 6 images with known homography. The dataset is split into two parts: viewpoint - 59 sequences with significant viewpoint change and illumination - 57 sequences with significant illumination change, both natural and artificial.

Source: RF-Net: An End-to-End Image Matching Network based on Receptive Field Image Source: https://www.robots.ox.ac.uk/~vgg/publications/2017/Balntas17/balntas17.pdf

Benchmarks archive 2025-07-28

All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Dense Pixel Correspondence Estimation HPatches RANSAC-DMP+ Viewpoint I AEPE 0.48 Deep Matching Prior: Test-Time Optimization for Dense... SunghwanHong/Deep-Matching-Prior 8 Compare
Patch Matching HPatches Twin-Net Patch Matching 53.95 Twin-Net Descriptor: Twin Negative Mining With Quad Loss... — 2 Compare
Geometric Matching HPatches IFCAT (Ours) Average End-Point Error 17.59 Integrative Feature and Cost Aggregation with... — 1 Compare
Image Stitching HPatches IF-Net 0..5sec 10000 IF-Net: An Illumination-invariant Feature Network — 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 11 · with a code link: 8 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (3 of 11 with a benchmark row: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 11 of 11 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 248. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A 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” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence 0 1 19 Sep 2022 not harvested
Deep Matching Prior: Test-Time Optimization for Dense Correspondence 1 1 6 Jun 2021 not harvested
COTR: Correspondence Transformer for Matching Across Images 1 2 25 Mar 2021 official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result
IF-Net: An Illumination-invariant Feature Network 0 1 10 Aug 2020 not harvested
LandscapeAR: Large Scale Outdoor Augmented Reality by Matching Photographs with Terrain Models Using Learned Descriptors 1 1 1 Aug 2020 not harvested
Twin-Net Descriptor: Twin Negative Mining With Quad Loss for Patch-Based Matching 0 1 19 Sep 2019 not harvested
DGC-Net: Dense Geometric Correspondence Network 4 1 19 Oct 2018 not harvested
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume 21 1 7 Sep 2017 community repositories only · 3 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; 3 where Syntology's instrument failed) · 0 unverified (3 pointer-only for licence)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks 12 1 6 Dec 2016 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (3 pointer-only for licence)
Optical Flow Estimation using a Spatial Pyramid Network 8 1 3 Nov 2016 not harvested
DeepMatching: Hierarchical Deformable Dense Matching 1 1 25 Jun 2015 not harvested

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • HPatches

1 variant name, as the archive lists them.

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