danini/cvpr2022-affine-tutorial

Stars
11
Rank 1,694,829 (Top 34 %)
Language SCSS
License
MIT License
Created over 2 years ago
Updated almost 2 years ago

danini/cvpr2022-affine-tutorial

danini

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

The official site of the CVPR 2022 Affine Correspondences and Their Applications tutorial

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

magsac

The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold

progressive-x

The Progressive-X algorithm proposed in paper: Daniel Barath and Jiri Matas; Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm, International Conference on Computer Vision, 2019. It is available at https://arxiv.org/pdf/1906.02290

Jupyter Notebook

homography-benchmark

pose-graph-initialization

affine-correspondences-for-camera-geometry

multi-h

The C++ implementation of Multi-H algorithm, which is a multi-plane fitting technique. If you use this work for Academic purposes, please cite Barath, D. and Matas, J. and Hajder, L., Multi-H: Efficient Recovery of Tangent Planes in Stereo Images. 27th British Machine Vision Conference, 2016

homography-from-sift-features

multi-x

The Multi-X algorithm proposed in paper: Daniel Barath and Jiri Matas, Multi-class model fitting by energy-minimization and mode-seeking, European Conference on Computer Vision, 2018. It is available at http://openaccess.thecvf.com/content_ECCV_2018/papers/Daniel_Barath_Multi-Class_Model_Fitting_ECCV_2018_paper.pdf

five-point-fundamental

The Matlab implementation of the 5 point fundamental matrix estimator. If you use this work for Academic purposes, please cite Barath, D., Five-point fundamental matrix estimation for uncalibrated cameras, Conference on Computer Vision and Pattern Recognition, 2018

absolute-pose-from-oriented-and-scaled-features

clustering-in-consensus-space

Jupyter Notebook

learning-good-models-in-ransac

recovering-affine-features

D. Barath, "Recovering affine features from orientation-and scale-invariant ones", Asian Conference on Computer Vision (ACCV), 2019

robust-line-based-estimator

Jupyter Notebook

sutd_hololens_mapping