most citedOpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching

8 citations · 8 across the 4 of their papers we have counts for

collaborators

9 papers

cs.CV20228 cited

OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching

Ostap Viniavskyi, Mariia Dobko, Dmytro Mishkin +1

We present OpenGlue: a free open-source framework for image matching, that uses a Graph Neural Network-based matcher inspired by SuperGlue \cite{sarlin20superglue}. We show that in…

cs.CV2022

Towards realistic symmetry-based completion of previously unseen point clouds

Taras Rumezhak, Oles Dobosevych, Rostyslav Hryniv +3

3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, sp…

cs.CV2020

Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration

Yaroslava Lochman, Oles Dobosevych, Rostyslav Hryniv +1

This paper proposes minimal solvers that use combinations of imaged translational symmetries and parallel scene lines to jointly estimate lens undistortion with either affine recti…

cs.CV2020

LID 2020: The Learning from Imperfect Data Challenge Results

Yunchao Wei, Shuai Zheng, Ming-Ming Cheng +32

Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotate…

math.SP2020

Direct and inverse spectral problems for rank-one perturbations of self-adjoint operators

Oles Dobosevych, Rostyslav Hryniv

For a given self-adjoint operator with discrete spectrum, we completely characterize possible eigenvalues of its rank-one perturbations~ and discuss the inverse problem of r…

cs.CV2020

Weakly-Supervised Segmentation for Disease Localization in Chest X-Ray Images

Ostap Viniavskyi, Mariia Dobko, Oles Dobosevych

Deep Convolutional Neural Networks have proven effective in solving the task of semantic segmentation. However, their efficiency heavily relies on the pixel-level annotations that…