no code implementations • 7 May 2024 • Markus Hillemann, Robert Langendörfer, Max Heiken, Max Mehltretter, Andreas Schenk, Martin Weinmann, Stefan Hinz, Christian Heipke, Markus Ulrich
As input, NeRFs require multi-view images with corresponding camera poses as well as the interior orientation.
no code implementations • 12 Mar 2024 • Kira Wursthorn, Markus Hillemann, Markus Ulrich
In this work, we propose a method to quantify the uncertainty of multi-stage 6D object pose estimation approaches with deep ensembles.
no code implementations • 16 Feb 2024 • Steven Landgraf, Markus Hillemann, Theodor Kapler, Markus Ulrich
By implicitly leveraging the predictive uncertainties of the teacher, EMUFormer achieves new state-of-the-art results on Cityscapes and NYUv2 and additionally estimates high-quality predictive uncertainties for both tasks that are comparable or superior to a Deep Ensemble despite being an order of magnitude more efficient.
no code implementations • 19 Aug 2023 • Dominik Werner Wolf, Markus Ulrich, Nikhil Kapoor
To address this issue, this paper investigates the domain shift problem further by evaluating the sensitivity of two perception models to different windshield configurations.
no code implementations • 19 Jul 2023 • Steven Landgraf, Markus Hillemann, Kira Wursthorn, Markus Ulrich
Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their deployment in safety-critical applications like autonomous driving.
no code implementations • 26 Jun 2023 • Steven Landgraf, Markus Hillemann, Moritz Aberle, Valentin Jung, Markus Ulrich
In many industrial processes, such as power generation, chemical production, and waste management, accurately monitoring industrial burner flame characteristics is crucial for safe and efficient operation.
no code implementations • 23 May 2023 • Dominik Werner Wolf, Markus Ulrich, Alexander Braun
Further, as the industry is moving towards the modulation transfer function (MTF) as an alternative, we mathematically show that this metric cannot be used on windscreens alone, but that the windscreen forms a novel optical system together with the optics of the camera system.
no code implementations • 27 Apr 2023 • Dennis Haitz, Boris Jutzi, Markus Ulrich, Miriam Jaeger, Patrick Huebner
The HoloLens is connected via Wifi to a high-performance PC that is responsible for the training and 3D reconstruction.
no code implementations • 17 Mar 2023 • Steven Landgraf, Kira Wursthorn, Markus Hillemann, Markus Ulrich
Deep neural networks lack interpretability and tend to be overconfident, which poses a serious problem in safety-critical applications like autonomous driving, medical imaging, or machine vision tasks with high demands on reliability.
no code implementations • 14 May 2022 • Dennis Haitz, Boris Jutzi, Patrick Huebner, Markus Ulrich
Corrosion is a form of damage that often appears on the surface of metal-made objects used in industrial applications.
no code implementations • 5 Jul 2018 • Tobias Böttger, Markus Ulrich, Carsten Steger
We present a novel object tracking scheme that can track rigid objects in real time.
no code implementations • ECCV 2018 • Patrick Follmann, Tobias Böttger, Philipp Härtinger, Rebecca König, Markus Ulrich
The dataset covers several challenges highly relevant in the field, such as a limited amount of training data and a high diversity in the test and validation sets.