About

I am a PhD Student at the Robotics and Perception Group, led by Prof. Davide Scaramuzza. My research interests lie at the intersection of computer vision, robotics and neuroscience. Currently, I am working on my PhD degree focusing on computer vision for event cameras.

I received my masters degree in Robotics, Systems and Control from ETH Zurich under the supervision of Prof. John Lygeros.

Interests
  • Computer Vision
  • Robotics
  • Machine Learning
Education

  • PhD in Computer Vision, 2017 - now

    Robotics and Perception Group

  • MSc in Robotics, Systems and Control, 2016

    ETH Zurich

  • BSc Mechanical Engineering, 2013

    ETH Zurich

Featured Publications

Recurrent Vision Transformers for Object Detection with Event Cameras
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Mathias Gehrig, Davide Scaramuzza
Cite DOI PDF Code
Recurrent Vision Transformers for Object Detection with Event Cameras
Dense Continuous-Time Optical Flow from Events and Frames
arXiv preprint, 2022
Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza
Cite DOI PDF
Dense Continuous-Time Optical Flow from Events and Frames
E-RAFT: Dense Optical Flow from Event Cameras
International Conference on 3D Vision (3DV), 2021, ORAL
Mathias Gehrig, Mario Millhausler, Daniel Gehrig, Davide Scaramuzza
Cite DOI PDF Project Code Dataset Benchmark Video
E-RAFT: Dense Optical Flow from Event Cameras
DSEC: A Stereo Event Camera Dataset for Driving Scenarios
IEEE Robotics and Automation Letters (RA-L), 2021
Mathias Gehrig, Willem Aarents, Daniel Gehrig, Davide Scaramuzza
Cite DOI PDF Project & Dataset Code Benchmark Video (Teaser) Video (ICRA)
DSEC: A Stereo Event Camera Dataset for Driving Scenarios
Video to Events: Recycling Video Datasets for Event Cameras
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Daniel Gehrig, Mathias Gehrig, Javier Hidalgo-Carrio, Davide Scaramuzza
Cite DOI PDF Code Video
Video to Events: Recycling Video Datasets for Event Cameras

Recent Publications

Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation
Robotics and Automation Letters (RA-L), 2022
Nico Messikommer, Daniel Gehrig, Mathias Gehrig, Davide Scaramuzza
Cite DOI PDF Code Video
Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation
How to Calibrate Your Event Camera
Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021
Manasi Muglikar, Mathias Gehrig, Daniel Gehrig, Davide Scaramuzza
Cite DOI PDF Code Video
How to Calibrate Your Event Camera
Time Lens: Event-based Video Frame Interpolation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
Stepan Tulyakov, Daniel Gehrig, Stamatios Georgoulis, Julius Erbach, Mathias Gehrig, Yuanyou Li, Davide Scaramuzza
Cite DOI PDF Project & Dataset Code Video Slides
Time Lens: Event-based Video Frame Interpolation
Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
IEEE Robotics and Automation Letters (RA-L), 2021
Daniel Gehrig, Michelle Ruegg, Mathias Gehrig, Javier Hidalgo-Carrio, Davide Scaramuzza
Cite DOI PDF Project & Dataset Code Video Slides
Combining Events and Frames Using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction
AlphaPilot: Autonomous Drone Racing
Robotics: Science and Systems (RSS), 2020
Philipp Foehn, Dario Brescianini, Elia Kaufmann, Titus Cieslewski, Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza
Cite DOI PDF Video (Teaser) Video (RSS)
AlphaPilot: Autonomous Drone Racing
Event-Based Angular Velocity Regression with Spiking Networks
International Conference on Robotics and Automation (ICRA), 2020
Mathias Gehrig, Sumit Bam Shrestha, Daniel Mouritzen, Davide Scaramuzza
Cite DOI PDF Code Video
Event-Based Angular Velocity Regression with Spiking Networks
Towards Low-Latency High-Bandwidth Control of Quadrotors using Event Cameras
International Conference on Robotics and Automation (ICRA), 2020
Rika Sugimoto Dimitrova, Mathias Gehrig, Dario Brescianini, Davide Scaramuzza
Cite DOI PDF Video (Teaser) Video (ICRA)
Towards Low-Latency High-Bandwidth Control of Quadrotors using Event Cameras
Focus Is All You Need: Loss Functions for Event-Based Vision
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
Guillermo Gallego, Mathias Gehrig, Davide Scaramuzza
Cite DOI PDF Video Poster
Focus Is All You Need: Loss Functions for Event-Based Vision
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
International Conference on Robotics and Automation (ICRA), 2019
Elia Kaufmann, Mathias Gehrig, Philipp Foehn, Rene Ranftl, Alexey Dosovitskiy, Vladlen Koltun, Davide Scaramuzza
Cite DOI PDF Video
Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing
Visual place recognition with probabilistic voting
International Conference on Robotics and Automation (ICRA), 2017
Mathias Gehrig, Elena Stumm, Timo Hinzmann, Roland Siegwart
Cite DOI PDF
Visual place recognition with probabilistic voting

Contact