Mathias Gehrig

Papers

Total Citations

H-Index

About

Mathias Gehrig is a leading researcher at the intersection of event-based vision and robotic perception, whose work is redefining how machines see in extreme conditions. His primary focus lies in bridging the gap between traditional frame-based cameras and neuromorphic event sensors, which excel in high-speed motion and high dynamic range environments. Gehrig’s most impactful contribution, "Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation" (2022, 49 citations), introduces a novel framework that adapts conventional computer vision models to event data without requiring labeled event datasets, significantly lowering the barrier for event-based perception in robotics. He has also advanced neuromorphic optical flow estimation, developing real-time implementations that prioritize efficiency and low latency for edge applications (2023, 20 citations). More recently, Gehrig has explored reinforcement learning for visual odometry (2024, 10 citations), pushing the boundaries of autonomous navigation. His work is notable for its practical focus on deploying event cameras in real-world robotic systems, where reliability during fast maneuvers or challenging lighting is critical. With a growing citation impact, Gehrig is a key figure in making event-based vision a viable, robust alternative to traditional camera pipelines.