activity
20132023
most citedD2-Net: A Trainable CNN for Joint Detection and Description of Local Features

74 citations · 78 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

19 papers · 1 filter

cs.CV2023

Automatic Solver Generator for Systems of Laurent Polynomial Equations

Evgeniy Martyushev, Snehal Bhayani, Tomas Pajdla

In computer vision applications, the following problem often arises: Given a family of (Laurent) polynomial systems with the same monomial structure but varying coefficients, find…

cs.CV2022

D-InLoc++: Indoor Localization in Dynamic Environments

Martina Dubenova, Anna Zderadickova, Ondrej Kafka +2

Most state-of-the-art localization algorithms rely on robust relative pose estimation and geometry verification to obtain moving object agnostic camera poses in complex indoor envi…

cs.CV20221 cited

Optimizing Elimination Templates by Greedy Parameter Search

Evgeniy Martyushev, Jana Vrablikova, Tomas Pajdla

We propose a new method for constructing elimination templates for efficient polynomial system solving of minimal problems in structure from motion, image matching, and camera trac…

cs.CV2021

Reconstructing Small 3D Objects in front of a Textured Background

Petr Hruby, Tomas Pajdla

We present a technique for a complete 3D reconstruction of small objects moving in front of a textured background. It is a particular variation of multibody structure from motion,…

cs.CV2020

Making Affine Correspondences Work in Camera Geometry Computation

Daniel Barath, Michal Polic, Wolfgang Förstner +3

Local features e.g. SIFT and its affine and learned variants provide region-to-region rather than point-to-point correspondences. This has recently been exploited to create new min…

cs.CV2020

From two rolling shutters to one global shutter

Cenek Albl, Zuzana Kukelova, Viktor Larsson +2

Most consumer cameras are equipped with electronic rolling shutter, leading to image distortions when the camera moves during image capture. We explore a surprisingly simple camera…