Patrick Wenzel

AI Research Engineer at Helsing

I'm Patrick, an AI Research Engineer at Helsing, working on localization and mapping.

I previously completed a PhD in Computer Science in the Computer Vision Group at the Technical University of Munich with Prof. Daniel Cremers. I am interested in 3D computer vision and SLAM. I have previously done internships at Meta Reality Labs and Niantic.

Email  |  Google Scholar  |  Twitter

News

• May 2026: We are organizing a workshop on ViLMa – 2nd Workshop on Visual Localization and Mapping: From Optimization to 3D Foundation Models at ECCV 2026.
• February 2024: We are organizing a workshop on Visual Localization and Mapping Workshop (ViLMa) at CVPR 2024.
• January 2023: Excited to join Helsing as an AI Research Engineer.
• July 2022: We are organizing a workshop on Map-Based Localization for Autonomous Driving at ECCV 2022.
• December 2021: Excited to join Niantic as a Research Intern.
• May 2021: Excited to join Meta Reality Labs as a Research Intern.
• April 2021: 4Seasons dataset is now public.
• April 2021: We are organizing a workshop on Map-Based Localization for Autonomous Driving at ICCV 2021 (Stream).
• May 2020: We are organizing a workshop on Map-Based Localization for Autonomous Driving at ECCV 2020 (Morning Session, Afternoon Session).

Publications

• 4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions
  Patrick Wenzel, Nan Yang, Rui Wang, Niclas Zeller, Daniel Cremers
  International Journal of Computer Vision (IJCV), 2025
  [arXiv] [bibtex] [project webpage]
• Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
  Patrick Wenzel, Torsten Schön, Laura Leal-Taixé, Daniel Cremers
  Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2021
  [arXiv] [bibtex]
• Self-Supervised Steering Angle Prediction for Vehicle Control Using Visual Odometry
  Qadeer Khan, Patrick Wenzel, Daniel Cremers
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
  [arXiv] [bibtex]
• LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization
  Lukas von Stumberg*, Patrick Wenzel*, Nan Yang, Daniel Cremers
  Proceedings of the International Conference on 3D Vision (3DV), 2020
  [arXiv] [bibtex] [project webpage]
• 4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving
  Patrick Wenzel, Rui Wang, Nan Yang, Qing Cheng, Qadeer Khan, Lukas von Stumberg, Niclas Zeller, Daniel Cremers
  Proceedings of the German Conference on Pattern Recognition (GCPR), 2020
  [arXiv] [bibtex] [project webpage] [teaser] [spotlight]
• GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalization
  Lukas von Stumberg*, Patrick Wenzel*, Qadeer Khan, Daniel Cremers
  IEEE Robotics and Automation Letters (RA-L), 2020
  [arXiv] [bibtex] [project webpage] [video]
• Towards Generalizing Sensorimotor Control Across Weather Conditions
  Qadeer Khan*, Patrick Wenzel*, Daniel Cremers, Laura Leal-Taixé
  Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
  [arXiv] [bibtex]
• Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs
  Patrick Wenzel*, Qadeer Khan*, Daniel Cremers, Laura Leal-Taixé
  Conference on Robot Learning (CoRL), 2018
  [arXiv] [bibtex]