no code implementations • 9 Feb 2024 • Peter Hönig, Stefan Thalhammer, Markus Vincze
In this study, we compare image-to-image translation networks based on GANs and diffusion models for the downstream task of 6D object pose estimation.
1 code implementation • 7 Feb 2024 • Peter Hönig, Stefan Thalhammer, Jean-Baptiste Weibel, Matthias Hirschmanner, Markus Vincze
To achieve a focus on learning shape features, the textures are randomized during the rendering of the training data.
no code implementations • 25 Oct 2023 • Gerald Ebmer, Adam Loch, Minh Nhat Vu, Germain Haessig, Roberto Mecca, Markus Vincze, Christian Hartl-Nesic, Andreas Kugi
Experimental results in static and dynamic scenarios are presented to demonstrate the performance of the proposed approach in terms of computational speed and absolute accuracy, using the OptiTrack system as the basis for measurement.
no code implementations • 21 Sep 2023 • Philipp Ausserlechner, David Haberger, Stefan Thalhammer, Jean-Baptiste Weibel, Markus Vincze
The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects.
no code implementations • 28 Jul 2023 • Konstantin Röhrl, Dominik Bauer, Timothy Patten, Markus Vincze
Tracking an object's 6D pose, while either the object itself or the observing camera is moving, is important for many robotics and augmented reality applications.
no code implementations • 22 Jul 2023 • Stefan Thalhammer, Dominik Bauer, Peter Hönig, Jean-Baptiste Weibel, José García-Rodríguez, Markus Vincze
Object pose estimation is a core perception task that enables, for example, object grasping and scene understanding.
1 code implementation • 31 May 2023 • Stefan Thalhammer, Jean-Baptiste Weibel, Markus Vincze, Jose Garcia-Rodriguez
This work evaluates and demonstrates the differences between self-supervised CNNs and Vision Transformers for deep template matching.
no code implementations • 23 Feb 2023 • Stefan Thalhammer, Peter Hönig, Jean-Baptiste Weibel, Markus Vincze
Object pose estimation is a non-trivial task that enables robotic manipulation, bin picking, augmented reality, and scene understanding, to name a few use cases.
no code implementations • 15 Nov 2022 • Hrishikesh Gupta, Stefan Thalhammer, Markus Leitner, Markus Vincze
Towards this, we study deep learning 6D pose estimation from RGB images only for transparent object grasping.
no code implementations • 18 Aug 2022 • Stefan Thalhammer, Timothy Patten, Markus Vincze
We present an approach that learns an intermediate geometric representation of multiple objects to directly regress 6D poses of all instances in a test image.
1 code implementation • 1 Jan 2022 • Dominik Bauer, Timothy Patten, Markus Vincze
Observational noise, inaccurate segmentation and ambiguity due to symmetry and occlusion lead to inaccurate object pose estimates.
no code implementations • 12 Oct 2021 • Adam Loch, Germain Haessig, Markus Vincze
Motion and dynamic environments, especially under challenging lighting conditions, are still an open issue for robust robotic applications.
1 code implementation • 23 Apr 2021 • Pablo Martinez-Gonzalez, Sergiu Oprea, John Alejandro Castro-Vargas, Alberto Garcia-Garcia, Sergio Orts-Escolano, Jose Garcia-Rodriguez, Markus Vincze
Synthetic data generation has become essential in last years for feeding data-driven algorithms, which surpassed traditional techniques performance in almost every computer vision problem.
2 code implementations • CVPR 2021 • 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.
no code implementations • 10 Mar 2021 • 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.
1 code implementation • 30 Oct 2020 • Stefan Thalhammer, Markus Leitner, Timothy Patten, Markus Vincze
We also perform grasping experiments in the real world to demonstrate the advantage of using synthetic data to generalize to novel environments.
1 code implementation • ECCV 2020 • Kiru Park, Timothy Patten, Markus Vincze
Recent methods for 6D pose estimation of objects assume either textured 3D models or real images that cover the entire range of target poses.
3 code implementations • 21 Apr 2020 • Mohammad Reza Loghmani, Luca Robbiano, Mirco Planamente, Kiru Park, Barbara Caputo, Markus Vincze
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions.
1 code implementation • 24 Feb 2020 • Zhi Yan, Simon Schreiberhuber, Georg Halmetschlager, Tom Duckett, Markus Vincze, Nicola Bellotto
The proposed system is based on multiple sensors including 3D and 2D lidar, two RGB-D cameras and a stereo camera.
Robotics
no code implementations • 15 Jan 2020 • Timothy Patten, Kiru Park, Markus Vincze
This article presents a method for grasping novel objects by learning from experience.
Robotics
no code implementations • 28 Oct 2019 • Jean-Baptiste Weibel, Timothy Patten, Markus Vincze
In this work, we examine this gap in a robotic context by specifically addressing the problem of classification when transferring from artificial CAD models to real reconstructed objects.
1 code implementation • 12 Sep 2019 • Dominik Bauer, Timothy Patten, Markus Vincze
The generality of the approach is shown by using three state-of-the-art pose estimators and three baseline refiners.
4 code implementations • ICCV 2019 • Kiru Park, Timothy Patten, Markus Vincze
Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries.
Ranked #1 on 6D Pose Estimation using RGB on T-LESS
no code implementations • 5 Feb 2019 • Markus Suchi, Timothy Patten, David Fischinger, Markus Vincze
This paper presents the EasyLabel tool for easily acquiring high quality ground truth annotation of objects at the pixel-level in densely cluttered scenes.
1 code implementation • 5 Jun 2018 • Mohammad Reza Loghmani, Mirco Planamente, Barbara Caputo, Markus Vincze
Providing machines with the ability to recognize objects like humans has always been one of the primary goals of machine vision.
1 code implementation • 20 Apr 2018 • Sergey V. Alexandrov, Johann Prankl, Michael Zillich, Markus Vincze
The research in dense online 3D mapping is mostly focused on the geometrical accuracy and spatial extent of the reconstructions.
no code implementations • 18 Sep 2017 • Mohammad Reza Loghmani, Barbara Caputo, Markus Vincze
The ability to recognize objects is an essential skill for a robotic system acting in human-populated environments.
no code implementations • 26 May 2015 • Andreas Grünauer, Markus Vincze
In this work we show that the classification performance of high-dimensional structural MRI data with only a small set of training examples is improved by the usage of dimension reduction methods.
no code implementations • 21 May 2015 • Aitor Aldoma, Johann Prankl, Alexander Svejda, Markus Vincze
This work presents a flexible system to reconstruct 3D models of objects captured with an RGB-D sensor.
no code implementations • 23 Apr 2014 • Daniel Wolf, Markus Bajones, Johann Prankl, Markus Vincze
In this paper, we propose an efficient semantic segmentation framework for indoor scenes, tailored to the application on a mobile robot.