no code implementations • 21 May 2024 • Volker Knauthe, Arne Rak, Tristan Wirth, Thomas Pöllabauer, Simon Metzler, Arjan Kuijper, Dieter W. Fellner
The robustness of semantic segmentation models against distribution shifts caused by differing camera or lighting setups, lens distortions, adversarial inputs and image corruptions has been topic of recent research.
no code implementations • 21 May 2024 • Volker Knauthe, Paul Weitz, Thomas Pöllabauer, Tristan Wirth, Arne Rak, Arjan Kuijper, Dieter W. Fellner
Computer vision techniques are on the rise for industrial applications, like process supervision and autonomous agents, e. g., in the healthcare domain and dangerous environments.
no code implementations • 13 May 2024 • Thomas Pöllabauer, Volker Knauthe, André Boller, Arjan Kuijper, Dieter Fellner
Instead of chroma keying, we propose luminance keying for fast and straightforward training image acquisition.
no code implementations • 8 Feb 2024 • Thomas Pöllabauer, Jan Emrich, Volker Knauthe, Arjan Kuijper
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task.
no code implementations • 22 Nov 2023 • Anton Winter, Nicolas Jourdan, Tristan Wirth, Volker Knauthe, Arjan Kuijper
In safety-critical domains such as autonomous driving and medical diagnosis, the reliability of machine learning models is crucial.