Markus Käppeler

	PhD Student
	Postal address:	Albert-Ludwigs-Universität Freiburg Technische Fakultät Robot Learning Lab Georges-Köhler-Allee 080 D-79110 Freiburg i. Br., Germany
	Office:	080-00-023
	Email:	kaeppelm@cs.uni-freiburg.de

About me

01/2024 - current: Ph.D. Student in the Robot Learning Lab, University of Freiburg
04/2020 - 12/2023: M.Sc. in Computer Science, University of Freiburg
10/2016 - 02/2020: B.Sc. in Applied Computer Science, Konstanz University of Applied Sciences

Research Interests

Robot Perception
Map-Based Perception and Planning
Leveraging Foundation Models for Autonomous Driving
Self-Supervised and Label-Efficient Learning

Research Projects

Hybrid Intelligence for Advanced Collective Awarness and Decision Making in Complex Urban Environments (HIDDEN)(2026 - current)
AI-based System Architectures for Autonomous Driving (2024 - 2026)

Teaching

TA, Deep Learning Lab, University of Freiburg, SS2026
TA, FreiCAR - Practical Autonomous Driving, University of Freiburg, WS2025/26
TA, Deep Learning Lab, University of Freiburg, SS2025
TA, Advanced Deep Learning, University of Freiburg, SS2025
TA, Robot Learning Seminar, University of Freiburg, WS2024/25
TA, Advanced Deep Learning, University of Freiburg, SS2024

Publications

2026

Markus Käppeler, Rohit Mohan, Abhinav Valada,
Leveraging Vision-Based Point Cloud Map Priors for Camera-Based 3D Object Detection and Online Vectorized HD Mapping
IROS Workshop on Long-Term Perception for Human-Centric Autonomy, 2026.
Best Paper Award at the IROS'26 Workshop on Long-Term Perception.
Download BibTeX

@article{kaeppeler2026irosws,
      author={Käppeler, Markus and Mohan, Rohit and Valada, Abhinav},
      title={Leveraging Vision-Based Point Cloud Map Priors for Camera-Based 3D Object Detection and Online Vectorized HD Mapping}, 
      journal={IROS Workshop on Long-Term Perception for Human-Centric Autonomy},
      year={2026},
}

Markus Käppeler, Özgün Çiçek, Yakov Miron, Abhinav Valada,
Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026.
Paper Video Website BibTeX

@article{kaeppeler2026dvmd,
      author={Käppeler, Markus and Çiçek, Özgün and Miron, Yakov and Valada, Abhinav},
      title={Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking}, 
      journal={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
      year={2026},
}

2025

Markus Käppeler, Özgün Çiçek, Daniele Cattaneo, Claudius Gläser, Yakov Miron, Abhinav Valada,
Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking
arXiv preprint arXiv:2510.10287, 2025.
Paper Video Website nuScenes Tracking Leaderboard nuScenes Detection Leaderboard BibTeX

@article{kaeppeler2025dvd,
      author={Käppeler, Markus and Çiçek, Özgün and Cattaneo, Daniele and Gläser, Claudius and Miron, Yakov and Valada, Abhinav},
      title={Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking}, 
      journal={arXiv preprint arXiv:2510.10287},
      year={2025},
}

Niclas Vödisch*, Kürsat Petek*, Markus Käppeler*, Abhinav Valada Wolfram Burgard,
A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation
IEEE Automation and Robotics Letters (RA-L), vol. 10, no. 1, pp. 216-223, 2025.
Paper IEEE Xplore Video Website BibTeX

@ARTICLE{voedisch2025pastel,
  author={Vödisch, Niclas and Petek, Kürsat and Käppeler, Markus and Valada, Abhinav and Burgard, Wolfram},
  journal={IEEE Robotics and Automation Letters}, 
  title={A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation}, 
  year={2025},
  volume={10},
  number={1},
  pages={216-223},
}

2024

Markus Käppeler*, Kürsat Petek*, Niclas Vödisch*, Wolfram Burgard, Abhinav Valada
SPINO: Few-Shot Panoptic Segmentation With Foundation Models
IEEE International Conference on Robotics and Automation (ICRA), 2024.,
Paper IEEE Xplore Video Website BibTeX

@inproceedings{kaeppeler2024spino,
    title={Few-Shot Panoptic Segmentation With Foundation Models},
    author={Käppeler, Markus and Petek, Kürsat and Vödisch, Niclas and Burgard, Wolfram and Valada, Abhinav},
    booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
    year={2024},
    pages={7718-7724}
}