My research interest lies at the intersection of computer vision and machine learning in the context of mobile perception systems. Currently, I am working on deep learning methods for 3D scene understanding to enable map-less driving or self-localization in sparse planning maps. In particular, I am interested in exploring how to overcome data shortage by leveraging the 6D pose awareness of mobile systems in highly accurate semantic 3D maps . Exampels of my current research are:

• Map Learning: Automatic data generation for deep learning applications using HD maps and multi-drive mapping
• Leveraging Map Learning for self-localisation, semantic mapping and map-less driving
• Learning-based 3D scene understanding

Supervised Thesis

• Occlusion Handling for Automatic Data Generation using HD Maps and a highly accurate SLAM, master thesis, November 2020
• Fusion of Simultaneously Learned Semantic Information from Different Representations, master thesis, November 2020
• A Comparison of Different Approachesto Solve the SLAM Problem on a Formula Student Driverless Race Car, master thesis, November 2020
• Combining Sequential LiDAR Measurements For Semantic Segmentation of Multi-Layer Grid Maps, master thesis, November 2020
• Panoptic Segmentation of Urban Scenarios, master thesis, September 2020