Daniel Gehrig ☕️

Daniel Gehrig

Postdoctoral Researcher & Incoming Assistant Professor

GRASP Lab, University of Pennsylvania

Incoming AP, Mechanical Engineering, NUS (March 2027)

Professional Summary

I am a postdoctoral researcher at the GRASP Lab, University of Pennsylvania, working under the supervision of Prof. Kostas Daniilidis. In March 2027, I will be joining the Department of Mechanical Engineering at the National University of Singapore (NUS) as an Assistant Professor.

Education

Ph.D. Computer Vision and Robotics

University of Zurich

MSc Mechanical Engineering

ETH Zurich

BSc Mechanical Engineering

ETH Zurich

📚 My Research

I am a postdoctoral researcher at the GRASP Lab under the supervision of Prof. Kostas Daniilidis working on the intersection of computer vision, robotics and machine learning with and without event cameras.

My research focuses on event-based sensing, and recently extended from vision-based (i.e., event cameras) to IMUs as part of my recent work on Lie Events for IMU-based navigation, and event-based computation in the embedding space via asynchronous neural networks. At NUS, I will be starting a research group working broadly at the intersection of robotics, computer vision, machine learning, and event-driven computation. A central goal of the group will be to develop intelligent systems that perceive, predict, and act efficiently in dynamic, high-speed environments, with a particular interest in event-driven and adaptive approaches.

Please reach out to collaborate!

Featured Publications
Neural Inertial Odometry from Lie Events featured image

Neural Inertial Odometry from Lie Events

Note This work extended event-based sampling to IMU-based navigation opening the door to new event-based sensing paradigms!

Royina Karegoudra Ayanth,
•
Low Latency Automotive Vision with Event Cameras featured image

Low Latency Automotive Vision with Event Cameras

Note This work lead to me winning the UZH Annual Award, which is awarded to the best Ph.D. in the department of Informatics!

Daniel Gehrig
•
Event-based Agile Object Catching with a Quadrupedal Robot featured image

Event-based Agile Object Catching with a Quadrupedal Robot

Note Here we explore the advantages of using event cameras to catch high-speed objects at up 15 m/s with the quadrupedal robot ANYmal. Our paper “Event-based Agile Object Catching …

Benedek Forrai*
•
Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction featured image

Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction

Note The work by Michelle Rüegg that contributed to the paper “Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction”, …

Daniel Gehrig
•
EKLT: Asynchronous, Photometric Feature Tracking using Events and Frames featured image

EKLT: Asynchronous, Photometric Feature Tracking using Events and Frames

Note This paper received an oral at ECCV 2018 and was invited as a journal extension at IJCV!

Daniel Gehrig
•
ESIM: an Open Event Camera Simulator featured image

ESIM: an Open Event Camera Simulator

Henri Rebecq
•
Recent Publications
(2026). A 25-μs/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the Edge. IEEE European Solid-State Electronics Research Conference (ESSERC).
PDF
(2026). Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision. arXiv.
PDF
(2026). RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
(2025). A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks. IEEE/CVF International Conference on Computer Vision (ICCV).
(2025). EqNIO: Subequivariant Neural Inertial Odometry. International Conference on Learning Representations (ICLR).
Recent & Upcoming Talks
Data-driven Event-based Perception: From cameras to IMUs featured image

Data-driven Event-based Perception: From cameras to IMUs

A talk discussing event-based sensing for cameras and IMU, and emergent equivariant properties.

Daniel Gehrig
•
Geometric and Algebraic Structure in Event Camera Data featured image

Geometric and Algebraic Structure in Event Camera Data

A talk discussing algebraic and geometric properties of event data.

Daniel Gehrig
•
Efficient, Data-driven Perception with Event Cameras featured image

Efficient, Data-driven Perception with Event Cameras

A talk discussing deep learning techniques for efficient event processing.

Daniel Gehrig
•
Efficient, Data-driven Perception with Event Cameras featured image

Efficient, Data-driven Perception with Event Cameras

A talk discussing deep learning techniques for efficient event processing.

Daniel Gehrig
•
Efficient, Data-driven Perception with Event Cameras featured image

Efficient, Data-driven Perception with Event Cameras

A talk discussing deep learning techniques for efficient event processing..

Daniel Gehrig
•
Recent News