Home

Awesome

Important news

Graph-Cut RANSAC

The Graph-Cut RANSAC algorithm proposed in paper: Daniel Barath and Jiri Matas; Graph-Cut RANSAC, Conference on Computer Vision and Pattern Recognition, 2018. It is available at http://openaccess.thecvf.com/content_cvpr_2018/papers/Barath_Graph-Cut_RANSAC_CVPR_2018_paper.pdf

The journal paper with updated spatial coherence term and additional experiments is available at https://ieeexplore.ieee.org/document/9399280

The method is explained in the Latest developments in RANSAC presentation from CVPR tutorial RANSAC in 2020.

Experiments on homography, fundamental matrix, essential matrix, and 6D pose estimation are shown in the corresponding presentation from the tutorial RANSAC in 2020.

Install from PyPI with pip

There are pre-compiled wheels for Windows and Linux for Python 3.8 - 3.11 that you can install with:

pip install pygcransac

Thanks to @akaszynski for his contributions.

Installation C++

To build and install C++ only GraphCutRANSAC, clone or download this repository and then build the project by CMAKE.

$ git clone https://github.com/danini/graph-cut-ransac
$ cd build
$ cmake ..
$ make

Install Python package and compile C++

python3 ./setup.py install

or

pip3 install -e .

Example project

To build the sample project showing examples of fundamental matrix, homography and essential matrix fitting, set variable CREATE_SAMPLE_PROJECT = ON when creating the project in CMAKE. Then

$ cd build
$ ./SampleProject

Requirements

Example of usage in python

import pygcransac
h1, w1 = img1.shape
h2, w2 = img2.shape
H, mask = pygcransac.findHomography(src_pts, dst_pts, h1, w1, h2, w2, 3.0)
F, mask = pygcransac.findFundamentalMatrix(src_pts, dst_pts, h1, w1, h2, w2, 3.0)

Jupyter Notebook example

The example for homography fitting is available at: notebook.

The example for fundamental matrix fitting is available at: notebook.

The example for essential matrix fitting is available at: notebook.

The example for essential matrix fitting with planar motion assumption is available at: notebook.

The example for essential matrix fitting with known gravity is available at: notebook.

The example for essential matrix fitting is available at: notebook.

The example for 6D pose fitting is available at: notebook.

An example comparing different samplers on fundamental matrix fitting: notebook.

Jupyter Notebook example (Affine and SIFT correspondence-based solvers)

The example for homography fitting to SIFT correspondences is available at: notebook.

The example for essential matrix fitting to SIFT correspondences is available at: notebook.

The example for fundamental matrix fitting to SIFT correspondences is available at: notebook.

The example for homography fitting to affine correspondences is available at: notebook.

The example for essential matrix fitting to affine correspondences is available at: notebook.

The example for fundamental matrix fitting to affine correspondences is available at: notebook.

Requirements

Acknowledgements

When using the algorithm, please cite

@inproceedings{GCRansac2018,
	author = {Barath, Daniel and Matas, Jiri},
	title = {Graph-cut {RANSAC}},
	booktitle = {Conference on Computer Vision and Pattern Recognition},
	year = {2018},
}

If you use it together with Progressive NAPSAC sampling or DEGENSAC, please cite

@inproceedings{PNAPSAC2020,
	author = {Barath, Daniel and Noskova, Jana and Ivashechkin, Maksym and Matas, Jiri},
	title = {{MAGSAC}++, a Fast, Reliable and Accurate Robust Estimator},
	booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
	month = {June},
	year = {2020}
}

@inproceedings{Degensac2005,
	author = {Chum, Ondrej and Werner, Tomas and Matas, Jiri},
	title = {Two-View Geometry Estimation Unaffected by a Dominant Plane},
	booktitle = {Conference on Computer Vision and Pattern Recognition},
	year = {2005},
}

If you use with Space Partitioning turned on, please cite

@inproceedings{spaceransac2022,
	author = {Barath, Daniel and Valasek, Gabor},
	title = {Space-Partitioning {RANSAC}},
	journal={European Conference on Computer Vision},
	year = {2022}
}

The Python wrapper part is based on the great Benjamin Jack python_cpp_example.