Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Daniel Barath

USACv20: robust essential, fundamental and homography matrix estimation


Apr 11, 2021
Maksym Ivashechkin, Daniel Barath, Jiri Matas

* arXiv admin note: text overlap with arXiv:1912.05909 

  Access Paper or Ask Questions

Progressive-X+: Clustering in the Consensus Space


Mar 25, 2021
Daniel Barath, Denys Rozumny, Ivan Eichhardt, Levente Hajder, Jiri Matas


  Access Paper or Ask Questions

Calibrated and Partially Calibrated Semi-Generalized Homographies


Mar 17, 2021
Snehal Bhayani, Torsten Sattler, Daniel Barath, Patrik Beliansky, Janne Heikkila, Zuzana Kukelova


  Access Paper or Ask Questions

Minimal Solutions for Panoramic Stitching Given Gravity Prior


Dec 01, 2020
Yaqing Ding, Daniel Barath, Zuzana Kukelova


  Access Paper or Ask Questions

Globally Optimal Relative Pose Estimation with Gravity Prior


Dec 01, 2020
Yaqing Ding, Daniel Barath, Jian Yang, Hui Kong, Zuzana Kukelova


  Access Paper or Ask Questions

Efficient Initial Pose-graph Generation for Global SfM


Nov 26, 2020
Daniel Barath, Dmytro Mishkin, Ivan Eichhardt, Ilia Shipachev, Jiri Matas

* Added supplementary material 

  Access Paper or Ask Questions

Pose Estimation for Vehicle-mounted Cameras via Horizontal and Vertical Planes


Aug 13, 2020
Istan Gergo Gal, Daniel Barath, Levente Hajder


  Access Paper or Ask Questions

Relative Pose Estimation for Multi-Camera Systems from Affine Correspondences


Jul 21, 2020
Banglei Guan, Ji Zhao, Daniel Barath, Friedrich Fraundorfer


  Access Paper or Ask Questions

Relative Pose from Deep Learned Depth and a Single Affine Correspondence


Jul 20, 2020
Ivan Eichhardt, Daniel Barath


  Access Paper or Ask Questions

Making Affine Correspondences Work in Camera Geometry Computation


Jul 20, 2020
Daniel Barath, Michal Polic, Wolfgang Förstner, Torsten Sattler, Tomas Pajdla, Zuzana Kukelova


  Access Paper or Ask Questions

EPOS: Estimating 6D Pose of Objects with Symmetries


Apr 01, 2020
Tomas Hodan, Daniel Barath, Jiri Matas

* Accepted to CVPR 2020 

  Access Paper or Ask Questions

Relative planar motion for vehicle-mounted cameras from a single affine correspondence


Dec 13, 2019
Levente Hajder, Daniel Barath


  Access Paper or Ask Questions

Least-squares Optimal Relative Planar Motion for Vehicle-mounted Cameras


Dec 13, 2019
Levente Hajder, Daniel Barath


  Access Paper or Ask Questions

MAGSAC++, a fast, reliable and accurate robust estimator


Dec 11, 2019
Daniel Barath, Jana Noskova, Maksym Ivashechkin, Jiri Matas

* arXiv admin note: substantial text overlap with arXiv:1906.02295 

  Access Paper or Ask Questions

Homography from two orientation- and scale-covariant features


Jun 27, 2019
Daniel Barath, Zuzana Kukelova


  Access Paper or Ask Questions

Progressive NAPSAC: sampling from gradually growing neighborhoods


Jun 05, 2019
Daniel Barath, Maksym Ivashechkin, Jiri Matas


  Access Paper or Ask Questions

Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm


Jun 05, 2019
Daniel Barath, Jiri Matas


  Access Paper or Ask Questions

Optimal Multi-view Correction of Local Affine Frames


May 01, 2019
Ivan Eichhardt, Daniel Barath


  Access Paper or Ask Questions

Recovering affine features from orientation- and scale-invariant ones


Jul 10, 2018
Daniel Barath


  Access Paper or Ask Questions

MAGSAC: marginalizing sample consensus


Mar 20, 2018
Daniel Barath, Jiri Matas


  Access Paper or Ask Questions

Five-point Fundamental Matrix Estimation for Uncalibrated Cameras


Mar 01, 2018
Daniel Barath


  Access Paper or Ask Questions

Graph-Cut RANSAC


Nov 16, 2017
Daniel Barath, Jiri Matas


  Access Paper or Ask Questions

Multi-Class Model Fitting by Energy Minimization and Mode-Seeking


Nov 16, 2017
Daniel Barath, Jiri Matas


  Access Paper or Ask Questions

A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences


Jun 06, 2017
Daniel Barath, Tekla Toth, Levente Hajder


  Access Paper or Ask Questions