Papers
7
Total Citations
463
H-Index
7
About
Fredrik Kahl is a leading researcher in computer vision and robotics, whose work has fundamentally advanced the fields of 3D reconstruction, visual localization, and object detection. His most impactful contribution is a pioneering method for real-time camera tracking and 3D reconstruction using signed distance functions and RGB-D sensors, a paper that has garnered over 200 citations and laid the groundwork for modern dense mapping systems. Kahl has also made significant strides in long-term visual localization, introducing semantic match consistency to robustly handle challenging environmental changes, a technique that has become a benchmark in the field. His research extends to monocular 3D object detection, where he developed an end-to-end trained system using intersection-over-union loss, achieving high accuracy with a streamlined inference engine. With a career spanning from foundational computer vision toolboxes to cutting-edge deep learning approaches, Kahl's work is essential reading for anyone interested in enabling machines to perceive and navigate the 3D world. His contributions continue to shape applications from autonomous driving to augmented reality.
Research Focus
Key Achievements
Top Papers
- 1Real-Time Camera Tracking and 3D Reconstruction Using Signed Distance Functions204 citations · 2013
- 2Semantic Match Consistency for Long-Term Visual Localization150 citations · 2018
- 3
- 4A Computer Vision Toolbox14 citations · 1997
- 5CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization14 citations · 2021
- 6Direct Camera Pose Tracking and Mapping With Signed Distance Functions8 citations · 2013
- 7