10 citations · 16 across the 14 of their papers we have counts for
17 papers
The Impact of CutMix on Reliability and Robustness in Semantic Segmentation
Steven Landgraf, Markus Ulrich
Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-critical applications such as auto…
A Critical Synthesis of Uncertainty Quantification and Foundation Models for Semantic Segmentation
Steven Landgraf, Joceline Hinz, Markus Ulrich
Foundation models are increasingly breaking what seemed to be impossible not long ago by enabling unprecedented accuracy and cross-domain generalization. Yet their lack of interpre…
MVM-IOD: An Industrial Object-Centric Benchmark Dataset for the Evaluation of 3D Reconstruction Methods
Robert Langendörfer, Markus Hillemann, Markus Ulrich
3D object reconstruction, and camera pose estimation in industrial applications are challenging tasks, as errors are costly while the computation time is often limited. The complex…
Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset
Markus Hillemann, Robert Langendörfer, Steven Landgraf +1
Visual Geometry Grounded Transformer (VGGT) has already attracted a great deal of attention in a short period of time, not least due to the Best Paper Award at CVPR-2025. Similar t…
MooMIns -- Monocular 3D Reconstruction and Object Pose Estimation from Multiple Instances
Robert Langendörfer, Markus Hillemann, Markus Ulrich
Simultaneous 3D reconstruction and 6D object pose estimation from a single monocular image is an inherently ill-posed problem. In industrial settings, however, multiple instances o…
Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model
Sunil Khatri, Steven Landgraf, Markus Ulrich +1
Visual in-Context Learning (VICL) aims at making progress towards adaptive vision models, that can -- based on a few examples -- adapt to a new task at test-time. With the history…
An Evaluation of DUSt3R/MASt3R/VGGT 3D Reconstruction on Photogrammetric Aerial Blocks
Xinyi Wu, Steven Landgraf, Markus Ulrich +1
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 D…
Rethinking Semi-supervised Segmentation Beyond Accuracy: Reliability and Robustness
Steven Landgraf, Markus Hillemann, Markus Ulrich
Semantic segmentation is critical for scene understanding but demands costly pixel-wise annotations, attracting increasing attention to semi-supervised approaches to leverage abund…
A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
Steven Landgraf, Rongjun Qin, Markus Ulrich
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 elu…
Novel View Synthesis with Neural Radiance Fields for Industrial Robot Applications
Markus Hillemann, Robert Langendörfer, Max Heiken +6
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 r…
Uncertainty Quantification with Deep Ensembles for 6D Object Pose Estimation
Kira Wursthorn, Markus Hillemann, Markus Ulrich
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 inspe…
A Comparative Study on Multi-task Uncertainty Quantification in Semantic Segmentation and Monocular Depth Estimation
Steven Landgraf, Markus Hillemann, Theodor Kapler +1
Deep neural networks excel in perception tasks such as semantic segmentation and monocular depth estimation, making them indispensable in safety-critical applications like autonomo…
Efficient Multi-task Uncertainties for Joint Semantic Segmentation and Monocular Depth Estimation
Steven Landgraf, Markus Hillemann, Theodor Kapler +1
Quantifying the predictive uncertainty emerged as a possible solution to common challenges like overconfidence or lack of explainability and robustness of deep neural networks, alb…
Sensitivity analysis of AI-based algorithms for autonomous driving on optical wavefront aberrations induced by the windshield
Dominik Werner Wolf, Markus Ulrich, Nikhil Kapoor
Autonomous driving perception techniques are typically based on supervised machine learning models that are trained on real-world street data. A typical training process involves c…
U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation
Steven Landgraf, Markus Hillemann, Kira Wursthorn +1
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 depl…
Segmentation of Industrial Burner Flames: A Comparative Study from Traditional Image Processing to Machine and Deep Learning
Steven Landgraf, Markus Hillemann, Moritz Aberle +2
In many industrial processes, such as power generation, chemical production, and waste management, accurately monitoring industrial burner flame characteristics is crucial for safe…
DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation
Steven Landgraf, Kira Wursthorn, Markus Hillemann +1
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…