activity
20132022
most citedUsing Dimension Reduction to Improve the Classification of High-dimensional Data

10 citations · 19 across the 15 of their papers we have counts for

collaborators
Showing cs.CVShow all

13 papers · 1 filter

cs.CV20223 cited

Grasping the Inconspicuous

Hrishikesh Gupta, Stefan Thalhammer, Markus Leitner +1

Transparent objects are common in day-to-day life and hence find many applications that require robot grasping. Many solutions toward object grasping exist for non-transparent obje…

cs.CV20211 cited

Event-Based high-speed low-latency fiducial marker tracking

Adam Loch, Germain Haessig, Markus Vincze

Motion and dynamic environments, especially under challenging lighting conditions, are still an open issue for robust robotic applications. In this paper, we propose an end-to-end…

cs.CV20211 cited

UnrealROX+: An Improved Tool for Acquiring Synthetic Data from Virtual 3D Environments

Pablo Martinez-Gonzalez, Sergiu Oprea, John Alejandro Castro-Vargas +4

Synthetic data generation has become essential in last years for feeding data-driven algorithms, which surpassed traditional techniques performance in almost every computer vision…

cs.CV2021

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

Dominik Bauer, Timothy Patten, Markus Vincze

Point cloud registration is a common step in many 3D computer vision tasks such as object pose estimation, where a 3D model is aligned to an observation. Classical registration met…

cs.CV20211 cited

Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme

Jean-Baptiste Weibel, Timothy Patten, Markus Vincze

While object semantic understanding is essential for most service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates th…

cs.CV2020

PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift

Stefan Thalhammer, Markus Leitner, Timothy Patten +1

Object pose estimation enables robots to understand and interact with their environments. Training with synthetic data is necessary in order to adapt to novel situations. Unfortuna…