Tobias Feigl

Fraunhofer Institute for Integrated Circuits

Papers

Total Citations

H-Index

About

Tobias Feigl is a leading researcher in computer vision and robotics, specializing in camera localization, visual odometry (VO), and multimodal sensor fusion. His work addresses the critical challenge of accurate 6DoF (six degrees of freedom) pose estimation for autonomous systems, including self-driving cars, aerial vehicles, and virtual reality applications. Feigl’s most cited paper, “ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization” (2020, 26 citations), introduces a novel hybrid approach that integrates convolutional neural networks (CNNs) with visual odometry to mitigate drift caused by moving obstacles, poor textures, and discontinuous feature observations. This work significantly improves long-term robot navigation robustness. In his subsequent research, “Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression” (2022, 4 citations), Feigl systematically evaluates deep fusion strategies for combining visual and inertial data, advancing absolute pose regression (APR) techniques. His contributions are pivotal for enhancing localization accuracy in dynamic, texture-poor environments, directly impacting real-world autonomous systems. Feigl’s work is widely cited by researchers developing next-generation navigation and mapping technologies.