Daniel Barath (@danini)
github

danini

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    1,197
  • Global Rank 25,767 (Top 0.9 %)
  • Followers 209
  • Following 1
  • Registered over 11 years ago
  • Most used languages
    C++
         37.5 %
    MATLAB
         18.8 %
    Jupyter Notebook
         18.8 %
    Python
         12.5 %
    C
         6.3 %
    SCSS     6.3 %

Top repositories

1

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
C++
429
star
2

magsac

The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold
C++
425
star
3

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
70
star
4

homography-benchmark

Python
65
star
5

pose-graph-initialization

C++
43
star
6

affine-correspondences-for-camera-geometry

C
43
star
7

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
C++
32
star
8

homography-from-sift-features

MATLAB
27
star
9

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
C++
15
star
10

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
MATLAB
14
star
11

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

C++
13
star
12

clustering-in-consensus-space

Jupyter Notebook
11
star
13

cvpr2022-affine-tutorial

The official site of the CVPR 2022 Affine Correspondences and Their Applications tutorial
SCSS
11
star
14

learning-good-models-in-ransac

10
star
15

recovering-affine-features

D. Barath, "Recovering affine features from orientation-and scale-invariant ones", Asian Conference on Computer Vision (ACCV), 2019
MATLAB
5
star
16

robust-line-based-estimator

Jupyter Notebook
3
star
17

sutd_hololens_mapping

Python
2
star