4 papers
Detecting 3D Line Segments for 6DoF Pose Estimation with Limited Data
Matej Mok, Lukáš Gajdošech, Michal Mesároš +2
The task of 6DoF object pose estimation is one of the fundamental problems of 3D vision with many practical applications such as industrial automation. Traditional deep learning ap…
On Representation of 3D Rotation in the Context of Deep Learning
Viktória Pravdová, Lukáš Gajdošech, Hassan Ali +1
This paper investigates various methods of representing 3D rotations and their impact on the learning process of deep neural networks. We evaluated the performance of ResNet18 netw…
Enhancement of 3D Camera Synthetic Training Data with Noise Models
Katarína Osvaldová, Lukáš Gajdošech, Viktor Kocur +1
The goal of this paper is to assess the impact of noise in 3D camera-captured data by modeling the noise of the imaging process and applying it on synthetic training data. We compi…
Supersampling of Data from Structured-light Scanner with Deep Learning
Martin Melicherčík, Lukáš Gajdošech, Viktor Kocur +1
This paper focuses on increasing the resolution of depth maps obtained from 3D cameras using structured light technology. Two deep learning models FDSR and DKN are modified to work…