
M.Sc. Frank Bieder
- Research Associate
- Room: 237
- Phone: +49 721 608-48423
- frank biederGxs2∂kit edu
Karlsruher Institut für Technologie
Institut für Mess- und Regelungstechnik
Engler-Bunte-Ring 21
Gebäude 40.32
D-76131 Karlsruhe
Research
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
Teaching
- Übungsleiter der Vorlesung Messtechnik II (SS20, WS20/21)
- Aufgabensteller Grundlagen der Mess- und Regelungstechnik (SS19, WS19/20, SS20)
- Mechatronik-Praktikum (WS19/20)
- Rechnergestützte Verfahren in der Mess- und Regelungstechnik (WS19/20, WS20/21)
Academic Services
- Reviewer for
- IEEE ITS Intelligent Vehicles (IV2020)
- IEEE RAS International Conference for Robotics and Automatisation (ICRA2021)
Open Theses
- Semantic Segmentation of Video Sequences
- Multi-Task Learning for Multi-Pose Estimation of Traffic Participants using Tailored Output Representations
- Multi-Task Learning for 3D Urban Scene Understanding Using Complementary Road Feature Representations
- Leveraging State-of-the-Art Semantic Segmentation Networks for Extracting Accurate Object Boundaries
Completed Theses
- 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
Publications
Frank Bieder, Sascha Wirges, Johannes Janosovits, Sven Richter, Zheyuan Wang, Christoph Stiller. Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Data. In Proc. IEEE Int. Conf. Intelligent Vehicles, Las Vegas, USA, June 2020.
Frank Bieder, Muti Ur Rehman, Christoph Stiller. Fusion of Sequential Information for Semantic Grid Map Estimation. In Forum Bildverarbeitung, Karlsruhe, Germany, Nov 2020.