• Publications
  • Influence
Seeing Through Fog Without Seeing Fog: Deep Sensor Fusion in the Absence of Labeled Training Data
TLDR
We present a deep fusion architecture that allows for robust fusion in fog and snow without having large labeled training data available for these scenarios. Expand
  • 19
  • 1
A Benchmark for Lidar Sensors in Fog: Is Detection Breaking Down?
TLDR
Autonomous driving at level five does not only means self-driving in the sunshine. Expand
  • 34
  • PDF
Benchmarking Image Sensors Under Adverse Weather Conditions for Autonomous Driving
TLDR
This work describes a testing and evaluation methodology that helps to benchmark novel sensor technologies and compare them to state-of-the-art sensors. Expand
  • 21
  • PDF
Gated2Depth: Real-Time Dense Lidar From Gated Images
TLDR
We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth accuracy comparable to pulsed lidar measurements. Expand
  • 8
  • PDF
Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather
TLDR
We present a deep fusion network for robust fusion without a large corpus of labeled training data covering all asymmetric distortions. Expand
  • 5
  • PDF
Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios
TLDR
This work introduces an evaluation benchmark for depth estimation and completion using high-resolution depth measurements with angular resolution of up to 25" (arcsecond), akin to a 50 megapixel camera with per-pixel depth available. Expand
  • 3
  • PDF
Robustness Against Unknown Noise for Raw Data Fusing Neural Networks
TLDR
We propose a simple data augmentation scheme that shows a neural network may be able to ignore data from underperforming sensors even though it has never seen that data during training. Expand
  • 6
  • PDF
DENSE: Environment Perception in Bad Weather—First Results
TLDR
This paper presents the first results of the publicly funded ECSEL project DENSE (Adverse weather environmental sensing system). Expand
  • 2
Suppression of topological Mott-Hubbard phases by multiple charge orders in the honeycomb extended Hubbard model
We investigate the competition between charge-density-wave (CDW) states and a Coulomb interaction-driven topological Mott insulator (TMI) in the honeycomb extended Hubbard model. For the spinfulExpand
  • 5
  • PDF
Recovering the Unseen: Benchmarking the Generalization of Enhancement Methods to Real World Data in Heavy Fog
TLDR
We present a newly developed metric providing more interpretable insights into the system behavior and show how it is superior to several current evaluation methods. Expand
  • 2
  • PDF