Browse State-of-the-Art › Patch Matching
Patch Matching
42 papers with code · 2 benchmarks · 4 datasets archive 2025-07-28
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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Brown Dataset (2 rows) | Multiscale Transformer Encoder | Attention-Based Multimodal Image Matching | code | — | Compare |
| HPatches (2 rows) | Twin-Net | Twin-Net Descriptor: Twin Negative Mining With Quad Loss for... | — | — | 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
4 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 97 · with a code link: 42 · where Syntology ran a sample: 6 (5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 97 tagged: 5 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 97 of 97, 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.
-
30 May 2017 4 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We introduce a novel loss for learning local feature descriptors which is inspired by the Lowe's matching criterion for SIFT.
-
16 Mar 2020 3 repositories listedIn this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant.
-
29 Dec 2016 3 repositories listedIn many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image.
-
1 Sep 2024 2 repositories listed Syntology official (archive's flag): 3 ran · 4 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; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 1 pointer-only (licence)We further propose a selective geometry feature fusion module to adaptively fuse multi-range and multi-granularity geometry features in MGEV.
-
4 Mar 2022 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples)Stereo matching is a fundamental building block for many vision and robotics applications.
-
28 Mar 2016 2 repositories listedThe local expansion moves extend traditional expansion moves by two ways: localization and spatial propagation.
-
1 Jun 2015 2 repositories listedWe perform a comprehensive set of experiments on standard datasets to carefully study the contributions of each aspect of MatchNet, with direct comparisons to established methods.
-
5 Jan 2004 2 repositories listedThis paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene.
-
12 May 2025 1 repository listedVisual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly, bypassing the dependence on Optical Character Recognition (OCR) for document search.
-
17 Jan 2025 1 repository listedHowever, their handcrafted generic descriptions fail to capture the diverse range of anomalies that may emerge in different objects, and simple patch-level image-text matching often struggles to localize anomalous…
-
1 Jan 2025 1 repository listedTo begin with, we translate the issue of surface placement to surface selection and trace a large number of stream surfaces from a given flow field dataset.
-
15 Dec 2024 1 repository listedTo the best of our knowledge, this is the first time that hard negative sample mining for metric networks has been implemented and brings significant performance gains.
-
1 Aug 2024 1 repository listedTo address the efficiency issue of MESA, we further propose DMESA as its dense counterpart, applying a dense matching framework.
-
18 Mar 2024 1 repository listedTherefore, we propose an innovative relational representation learning idea that simultaneously focuses on sufficiently mining the intrinsic features of individual image patches and the relations between image patch…
-
22 Feb 2024 1 repository listedThe advent of 3D Gaussian Splatting (3DGS) has recently brought about a revolution in the field of neural rendering, facilitating high-quality renderings at real-time speed.
-
1 Jan 2024 1 repository listedTo achieve this our method leverages a joint framework to predict the 2D feature motion offsets and the 3D feature spatial position simultaneously.
-
15 Nov 2023 1 repository listedIn the interpolation mode, FastBlend surpasses video interpolation and model-based video processing approaches.
-
7 Nov 2023 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)For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing.
-
28 Oct 2023 1 repository listedTo this end, we present a simple yet effective patch-matching algorithm to find the corresponding patches across the augmented views.
-
10 Aug 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description.
-
13 Jun 2023 1 repository listedThe framework includes two parts: key frame translation and full video translation.
-
29 Mar 2023 1 repository listedFirstly, we propose to use salient points with prominent local features as nodes to increase patch repeatability, and introduce some uniformly distributed points to complete the point cloud, thus constituting hybrid…
-
28 Mar 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)A consistency loss is then enforced on the found matches.
-
17 Nov 2022 1 repository listedOur algorithm constructs artificial patch-craft images from these bursts by patch matching and stitching, and the obtained crafted images are used as targets for the training.
-
2 Dec 2021 1 repository listedIn this paper, we show that closed form formulae for subpixel disparity computation for the case of one dimensional matching, e. g., in the case of rectified stereo images where the search space is of one dimension…
-
27 Sep 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set.
-
15 Sep 2021 1 repository listedWe first evaluate a supervised learning approach on synthetic data for which we have the full ground-truth available and subsequently move to several real-world datasets.
-
23 Aug 2021 1 repository listedIn this paper, we propose a novel two-stage context-aware network named CANet for shadow removal, in which the contextual information from non-shadow regions is transferred to shadow regions at the embedded feature…
-
25 Mar 2021 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 8 harvested samples) · 8 pointer-only (licence)Our algorithm augments video sequences with patch-craft frames and feeds them to a CNN.
-
20 Mar 2021 1 repository listedWe propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN.
-
1 Aug 2020 1 repository listed
-
17 Jun 2020 1 repository listed
-
20 May 2020 1 repository listed
-
24 Jan 2020 1 repository listed Syntology official (archive's flag): 8 ran · 8 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; 1 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples)
-
12 Dec 2018 1 repository listed
-
27 Jul 2018 1 repository listed
-
5 Jun 2018 1 repository listed
-
4 Jan 2018 1 repository listed
-
1 Jul 2017 1 repository listed
-
23 Jan 2017 1 repository listed
-
30 Apr 2016 1 repository listed
-
23 Apr 2015 1 repository listed
-
MicroFlow: Domain-Specific Optical Flow for Ground Deformation Estimation in Seismic Events18 Apr 2025 0 repositories listed
-
The Marine Debris Forward-Looking Sonar Datasets28 Mar 2025 0 repositories listed
-
Fence Theorem: Preprocessing is Dual-Objective Semantic Structure Isolator in 3D Anomaly Detection3 Mar 2025 0 repositories listed
-
NeRF-Texture: Synthesizing Neural Radiance Field Textures13 Dec 2024 0 repositories listed
-
Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition9 Dec 2024 0 repositories listed
-
UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection4 Dec 2024 0 repositories listed
-
HomoMatcher: Dense Feature Matching Results with Semi-Dense Efficiency by Homography Estimation11 Nov 2024 0 repositories listed
-
Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views8 Jul 2024 0 repositories listed
-
HySim: An Efficient Hybrid Similarity Measure for Patch Matching in Image Inpainting21 Mar 2024 0 repositories listed
-
FFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information28 Dec 2023 0 repositories listed
-
Image Patch-Matching with Graph-Based Learning in Street Scenes8 Nov 2023 0 repositories listed
-
Retinex-guided Channel-grouping based Patch Swap for Arbitrary Style Transfer19 Sep 2023 0 repositories listed
-
A Preliminary Investigation into Search and Matching for Tumour Discrimination in WHO Breast Taxonomy Using Deep Networks22 Aug 2023 0 repositories listed
-
Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching9 Aug 2023 0 repositories listed
-
Removing supervision in semantic segmentation with local-global matching and area balancing30 Mar 2023 0 repositories listed
-
Learning to Scale Temperature in Masked Self-Attention for Image Inpainting13 Feb 2023 0 repositories listed
-
Large-scale Global Low-rank Optimization for Computational Compressed Imaging8 Jan 2023 0 repositories listed
-
Compositional Scene Modeling with Global Object-Centric Representations21 Nov 2022 0 repositories listed
-
Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature Domain6 Sep 2022 0 repositories listed
-
Forward-Looking Sonar Patch Matching: Modern CNNs, Ensembling, and Uncertainty2 Aug 2021 0 repositories listed
-
DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer16 Jan 2021 0 repositories listed
-
Image Denoising by Gaussian Patch Mixture Model and Low Rank Patches20 Nov 2020 0 repositories listed
-
10 Aug 2020 0 repositories listed
-
Explaining Away Results in Accurate and Tolerant Template Matching11 Nov 2019 0 repositories listed
-
AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching1 Oct 2019 0 repositories listed
-
Better and Faster: Exponential Loss for Image Patch Matching1 Oct 2019 0 repositories listed
-
19 Sep 2019 0 repositories listed
-
Hue Modification Localization By Pair Matching5 Mar 2019 0 repositories listed
-
Feature Fusion for Robust Patch Matching With Compact Binary Descriptors11 Jan 2019 0 repositories listed
-
Sparse Over-complete Patch Matching9 Jun 2018 0 repositories listed
-
Kernelized Subspace Pooling for Deep Local Descriptors1 Jun 2018 0 repositories listed
-
Image Patch Matching Using Convolutional Descriptors with Euclidean Distance31 Oct 2017 0 repositories listed
-
Temporal Superpixels Based on Proximity-Weighted Patch Matching1 Oct 2017 0 repositories listed
-
Improving Sonar Image Patch Matching via Deep Learning7 Sep 2017 0 repositories listed
-
Adversarial Image Alignment and Interpolation30 Jun 2017 0 repositories listed
-
Local Feature Descriptor Learning with Adaptive Siamese Network16 Jun 2017 0 repositories listed
-
SLAM based Quasi Dense Reconstruction For Minimally Invasive Surgery Scenes25 May 2017 0 repositories listed
-
Learning Correspondence Structures for Person Re-identification20 Mar 2017 0 repositories listed
-
Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation7 Mar 2017 0 repositories listed
-
Improved Descriptors for Patch Matching and Reconstruction24 Jan 2017 0 repositories listed
-
Example-Based Image Synthesis via Randomized Patch-Matching23 Sep 2016 0 repositories listed
-
OnionNet: Sharing Features in Cascaded Deep Classifiers9 Aug 2016 0 repositories listed
-
CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss27 Jul 2016 0 repositories listed
-
Rotation Invariant Angular Descriptor Via A Bandlimited Gaussian-like Kernel8 Jun 2016 0 repositories listed
-
Needle-Match: Reliable Patch Matching Under High Uncertainty1 Jun 2016 0 repositories listed
-
Video-Story Composition via Plot Analysis1 Jun 2016 0 repositories listed
-
PatchBatch: a Batch Augmented Loss for Optical Flow6 Dec 2015 0 repositories listed
-
Learning Parametric Distributions for Image Super-Resolution: Where Patch Matching Meets Sparse Coding1 Dec 2015 0 repositories listed
-
Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification1 Jun 2015 0 repositories listed
-
Person Re-identification by Saliency Learning5 Dec 2014 0 repositories listed
-
Learning Mid-level Filters for Person Re-identification1 Jun 2014 0 repositories listed
-
Single Image Super-resolution using Deformable Patches1 Jun 2014 0 repositories listed
-
A novel framework for image forgery localization27 Nov 2013 0 repositories listed
-
Structured Face Hallucination1 Jun 2013 0 repositories listed
-
Unsupervised Salience Learning for Person Re-identification1 Jun 2013 0 repositories listed
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; 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