All Projects → HeZhang1994 → hypergraph-matching

HeZhang1994 / hypergraph-matching

Licence: MIT license
Code of the paper "Game theoretic hypergraph matching for multi-source image correspondences". [论文代码] 超图匹配和多源图像特征点匹配。

Programming Languages

matlab
3953 projects

Projects that are alternatives of or similar to hypergraph-matching

kaliningraph
🕸️ Graphs, finite fields and discrete dynamical systems in Kotlin
Stars: ✭ 62 (+37.78%)
Mutual labels:  graph-matching
ThinkMatch
Code & pretrained models of novel deep graph matching methods.
Stars: ✭ 639 (+1320%)
Mutual labels:  graph-matching
chgl
Chapel HyperGraph Library (CHGL) - HPC-class Hypergraphs in Chapel
Stars: ✭ 23 (-48.89%)
Mutual labels:  hypergraph
cv-arxiv-daily
🎓Automatically Update CV Papers Daily using Github Actions (Update Every 12th hours)
Stars: ✭ 216 (+380%)
Mutual labels:  image-matching
REGAL
Representation learning-based graph alignment based on implicit matrix factorization and structural embeddings
Stars: ✭ 78 (+73.33%)
Mutual labels:  graph-matching
sfm-disambiguation-colmap
Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures
Stars: ✭ 189 (+320%)
Mutual labels:  image-matching
LayoutGMN-pytorch
Pytorch implementation of LayoutGMN.
Stars: ✭ 30 (-33.33%)
Mutual labels:  graph-matching
HyperGraphLib
C++ Hypergraph modelling Library using Boost and OpenMP with some algorithms, including isomorphism using Gecode.
Stars: ✭ 19 (-57.78%)
Mutual labels:  hypergraph
mods
MODS (Matching On Demand with view Synthesis) is algorithm for wide-baseline matching.
Stars: ✭ 84 (+86.67%)
Mutual labels:  image-matching
codebase
The jBPT code library is a compendium of technologies that support research on design, execution, and evaluation of business processes. The library offers a broad range of basis analysis and utility functionality and, due to its open publishing model, can easily be extended.
Stars: ✭ 26 (-42.22%)
Mutual labels:  hypergraph
MATCHA
multiway chromatin interaction, 3D genome, single-nucleus
Stars: ✭ 19 (-57.78%)
Mutual labels:  hypergraph
hypergraph
Hypergraph is data structure library to create a directed hypergraph in which a hyperedge can join any number of vertices.
Stars: ✭ 205 (+355.56%)
Mutual labels:  hypergraph
visualsc
A simplicial complex and hypergraph visualization tool similar to Graphviz.
Stars: ✭ 31 (-31.11%)
Mutual labels:  hypergraph
FRGM
a functional representation for graph matching
Stars: ✭ 22 (-51.11%)
Mutual labels:  graph-matching
vf3lib
VF3 Algorithm - The fastest algorithm to solve subgraph isomorphism on large and dense graphs
Stars: ✭ 58 (+28.89%)
Mutual labels:  graph-matching
mods-light-zmq
MODS with external deep descriptors/detectors
Stars: ✭ 46 (+2.22%)
Mutual labels:  image-matching
rectified-features
[ECCV 2020] Single image depth prediction allows us to rectify planar surfaces in images and extract view-invariant local features for better feature matching
Stars: ✭ 57 (+26.67%)
Mutual labels:  image-matching
lookup
🔍 Pure Go implementation of fast image search and simple OCR, focused on reading info from screenshots
Stars: ✭ 35 (-22.22%)
Mutual labels:  image-matching
image-matching-toolbox
This is a toolbox repository to help evaluate various methods that perform image matching from a pair of images.
Stars: ✭ 252 (+460%)
Mutual labels:  image-matching

Hypergraph Matching

image image image image

English Version | 中文版

This is a MATLAB implementation of the hypergraph matching algorithm for multi-source image correspondences.

This algorithm is published in the paper: Game theoretic hypergraph matching for multi-source image correspondences.

Dependency

  • sift win32

Execute siftWin32.exe software to install SIFT libraries on Windows system (32-bit/64-bit).

Usage

  1. Prepare several multi-source image pairs in a folder (e.g., images/).

  2. Set parameters (distRatio, imresizerate1 and imresizerate2) in run_matching.m (see comments).

  3. Run run_matching.m to match key points of multi-source image pairs via hypergraph matching algorithm.

Notes:

  • Tuning distRatio to a larger value in [0, 1] will generate more key points and lower the matching speed.

  • The reported running time does not include the establishment of hypergraphs and the calculation of edge weights.

Citation

Please cite the following paper if you used this implementation in your work.

@Article{zhang17hypergraphmatch,
  title      = {Game theoretic hypergraph matching for multi-source image correspondences},
  author     = {Zhang, He and Ren, Peng},
  journal    = {Pattern Recognition Letters},
  volume     = {87},
  pages      = {87--95},
  year       = {2017},
  publisher  = {Elsevier}
}

Please report an issue if you have any question about this repository, I will respond ASAP.

Please star this repository if you found its content useful. Thank you very much. ^_^

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].