Markus Ulrich
YOU?
Author Swipe
View article: An evaluation of DUSt3R/MASt3R/VGGT 3D reconstruction on photogrammetric aerial blocks
An evaluation of DUSt3R/MASt3R/VGGT 3D reconstruction on photogrammetric aerial blocks Open
State-of-the-art 3D computer vision algorithms continue to improve on sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as dense and unconstrained stereo 3d reconstruction (DUSt3R), matching a…
View article: An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks
An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks Open
State-of-the-art 3D computer vision algorithms continue to advance in handling sparse, unordered image sets. Recently developed foundational models for 3D reconstruction, such as Dense and Unconstrained Stereo 3D Reconstruction (DUSt3R), M…
View article: Evaluation of Semi-supervised Semantic Segmentation for Remote Sensing, Medical Imaging, and Machine Vision Settings
Evaluation of Semi-supervised Semantic Segmentation for Remote Sensing, Medical Imaging, and Machine Vision Settings Open
Semi-supervised semantic segmentation (S4) has garnered significant attention in recent years due to the time-consuming and costly process of creating pixel-level annotations. Instead of only relying on labeled data, semi-supervised approa…
View article: A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation Open
While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting ab…
View article: A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation Open
While recent foundation models have enabled significant breakthroughs in monocular depth estimation, a clear path towards safe and reliable deployment in the real-world remains elusive. Metric depth estimation, which involves predicting ab…
View article: Managing complex foot deformities in paraplegia: Outcomes of intramedullary hindfoot arthrodesis for spastic pes cavovarus; A case series review
Managing complex foot deformities in paraplegia: Outcomes of intramedullary hindfoot arthrodesis for spastic pes cavovarus; A case series review Open
Background: Patients with spinal cord injury (SCI), particularly those with paraplegia, often develop rigid foot deformities such as spastic pes cavovarus due to unopposed muscle activity and chronic spasticity. These deformities compromis…
View article: Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration
Optical aberrations in autonomous driving: Physics-informed parameterized temperature scaling for neural network uncertainty calibration Open
'A trustworthy representation of uncertainty is desirable and should be considered as a key feature of any machine learning method' (Huellermeier and Waegeman, 2021). This conclusion of Huellermeier et al. underpins the importance of calib…
View article: Density-based Geometric Convergence of NeRFs at Training Time: Insights from Spatio-temporal Discretization
Density-based Geometric Convergence of NeRFs at Training Time: Insights from Spatio-temporal Discretization Open
Whereas emerging learning-based scene representations are predominantly evaluated based on image quality metrics such as PSNR, SSIM or LPIPS, only a few investigations focus on the evaluation of geometric accuracy of the underlying model. …
View article: Semantic segmentation and uncertainty quantification with vision transformers for industrial applications
Semantic segmentation and uncertainty quantification with vision transformers for industrial applications Open
Vision Transformers (ViTs) have recently achieved state-of-the-art performance in semantic segmentation tasks. However, their deployment in critical applications necessitates reliable uncertainty quantification to assess model confidence. …
View article: Evaluation of multi-task uncertainties in joint semantic segmentation and monocular depth estimation
Evaluation of multi-task uncertainties in joint semantic segmentation and monocular depth estimation Open
Deep neural networks achieve outstanding results in perception tasks such as semantic segmentation and monocular depth estimation, making them indispensable in safety-critical applications like autonomous driving and industrial inspection.…
View article: Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications
Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications Open
Neural Radiance Fields (NeRFs) have become a rapidly growing research field with the potential to revolutionize typical photogrammetric workflows, such as those used for 3D scene reconstruction. As input, NeRFs require multi-view images wi…
View article: Uncertainty-aware Cross-Entropy for Semantic Segmentation
Uncertainty-aware Cross-Entropy for Semantic Segmentation Open
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 driv…
View article: Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation Open
The estimation of 6D object poses is a fundamental task in many computer vision applications. Particularly, in high risk scenarios such as human-robot interaction, industrial inspection, and automation, reliable pose estimates are crucial.…
View article: Decoupling of neural network calibration measures
Decoupling of neural network calibration measures Open
A lot of effort is currently invested in safeguarding autonomous driving systems, which heavily rely on deep neural networks for computer vision. We investigate the coupling of different neural network calibration measures with a special f…
View article: A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation
A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation Open
Deep neural networks excel in perception tasks such as semantic segmentation and monocular depth estimation, making them indispensable in safety-critical applications like autonomous driving and industrial inspection. However, they often s…
View article: A Novel Treatment Algorithem for Infected Diabetic Foot Ulcers- One Step Procedure
A Novel Treatment Algorithem for Infected Diabetic Foot Ulcers- One Step Procedure Open
Background Foot and ankle infections are the most common reason for hospital admissions and have the most devastating and costly complications in patients with diabetes mellitus worldwide. Foot ulceration can lead to a limb or even life-th…
View article: Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications
Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications Open
Neural Radiance Fields (NeRFs) have become a rapidly growing research field with the potential to revolutionize typical photogrammetric workflows, such as those used for 3D scene reconstruction. As input, NeRFs require multi-view images wi…
View article: DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation
DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation Open
The intersection of deep learning and photogrammetry unveils a critical need for balancing the power of deep neural networks with interpretability and trustworthiness, especially for safety-critical application like autonomous driving, med…
View article: Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation Open
The estimation of 6D object poses is a fundamental task in many computer vision applications. Particularly, in high risk scenarios such as human-robot interaction, industrial inspection, and automation, reliable pose estimates are crucial.…
View article: Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation
Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation Open
Quantifying the predictive uncertainty emerged as a possible solution to common challenges like overconfidence or lack of explainability and robustness of deep neural networks, albeit one that is often computationally expensive. Many real-…
View article: SEGMENTATION OF INDUSTRIAL BURNER FLAMES: A COMPARATIVE STUDY FROM TRADITIONAL IMAGE PROCESSING TO MACHINE AND DEEP LEARNING
SEGMENTATION OF INDUSTRIAL BURNER FLAMES: A COMPARATIVE STUDY FROM TRADITIONAL IMAGE PROCESSING TO MACHINE AND DEEP LEARNING Open
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. A key step involves separating th…
View article: Novel developments of refractive power measurement techniques in the automotive world
Novel developments of refractive power measurement techniques in the automotive world Open
Refractive power measurements serve as the primary quality standard in the automotive glazing industry. In the light of autonomous driving new optical metrics are becoming more and more popular for specifying optical quality requirements f…
View article: U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation
U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation Open
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 driv…
View article: COMBINING HOLOLENS WITH INSTANT-NERFS: ADVANCED REAL-TIME 3D MOBILE MAPPING
COMBINING HOLOLENS WITH INSTANT-NERFS: ADVANCED REAL-TIME 3D MOBILE MAPPING Open
This work represents a large step into modern ways of fast 3D reconstruction based on RGB camera images. Utilizing a Microsoft HoloLens 2 as a multisensor platform that includes an RGB camera and an inertial measurement unit for SLAM-based…
View article: Windscreen Optical Quality for AI Algorithms: Refractive Power and MTF not Sufficient
Windscreen Optical Quality for AI Algorithms: Refractive Power and MTF not Sufficient Open
Windscreen optical quality is an important aspect of any advanced driver assistance system, and also for future autonomous driving, as today at least some cameras of the sensor suite are situated behind the windscreen. Automotive mass prod…
View article: Combining HoloLens with Instant-NeRFs: Advanced Real-Time 3D Mobile Mapping
Combining HoloLens with Instant-NeRFs: Advanced Real-Time 3D Mobile Mapping Open
This work represents a large step into modern ways of fast 3D reconstruction based on RGB camera images. Utilizing a Microsoft HoloLens 2 as a multisensor platform that includes an RGB camera and an inertial measurement unit for SLAM-based…
View article: DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation
DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation Open
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. Quan…