Search Results for author: Wolfgang Förstner

Found 6 papers, 2 papers with code

A Large Scale Homography Benchmark

2 code implementations20 Feb 2023 Daniel Barath, Dmytro Mishkin, Michal Polic, Wolfgang Förstner, Jiri Matas

We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.

Homography Estimation Surface Normal Estimation

Making Affine Correspondences Work in Camera Geometry Computation

1 code implementation ECCV 2020 Daniel Barath, Michal Polic, Wolfgang Förstner, Torsten Sattler, Tomas Pajdla, Zuzana Kukelova

The main advantage of such solvers is that their sample size is smaller, e. g., only two instead of four matches are required to estimate a homography.

Homography Estimation valid

Incremental Import Vector Machines for Classifying Hyperspectral Data

no code implementations20 Aug 2017 Ribana Roscher, Björn Waske, Wolfgang Förstner

The performance of the IVM in comparison to support vector machines (SVM) is evaluated in terms of accuracy and experiments are conducted to assess the potential of the probabilistic outputs of the IVM.

Classification General Classification +1

Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction

no code implementations ECCV 2018 Michal Polic, Wolfgang Förstner, Tomas Pajdla

Estimating uncertainty of camera parameters computed in Structure from Motion (SfM) is an important tool for evaluating the quality of the reconstruction and guiding the reconstruction process.

3D Reconstruction

A Large-Scale Homography Benchmark

no code implementations CVPR 2023 Daniel Barath, Dmytro Mishkin, Michal Polic, Wolfgang Förstner, Jiri Matas

We present a large-scale dataset of Planes in 3D, Pi3D, of roughly 1000 planes observed in 10 000 images from the 1DSfM dataset, and HEB, a large-scale homography estimation benchmark leveraging Pi3D.

Homography Estimation Surface Normal Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.