papers

Publications (24)

cs.RO2021

AlphaPilot: Autonomous Drone Racing

Philipp Foehn, Dario Brescianini, Elia Kaufmann +4

This paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The syst…

cs.CV2021

TimeLens: Event-based Video Frame Interpolation

Stepan Tulyakov, Daniel Gehrig, Stamatios Georgoulis +4

State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In the absence of additional informa…

cs.RO2019

Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing

Elia Kaufmann, Mathias Gehrig, Philipp Foehn +4

Autonomous micro aerial vehicles still struggle with fast and agile maneuvers, dynamic environments, imperfect sensing, and state estimation drift. Autonomous drone racing brings t…

cs.CV2022

Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation

Nico Messikommer, Daniel Gehrig, Mathias Gehrig +1

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging condition…

cs.CV2021

How to Calibrate Your Event Camera

Manasi Muglikar, Mathias Gehrig, Daniel Gehrig +1

We propose a generic event camera calibration framework using image reconstruction. Instead of relying on blinking LED patterns or external screens, we show that neural-network-bas…

cs.CV2026

Data-Driven Feature Tracking for Event Cameras With and Without Frames

Nico Messikommer, Carter Fang, Mathias Gehrig +2

Because of their high temporal resolution, increased resilience to motion blur, and very sparse output, event cameras have been shown to be ideal for low-latency and low-bandwidth…

cs.CV2024

Dense Continuous-Time Optical Flow from Events and Frames

Mathias Gehrig, Manasi Muglikar, Davide Scaramuzza

We present a method for estimating dense continuous-time optical flow from event data. Traditional dense optical flow methods compute the pixel displacement between two images. Due…

cs.CV2023

Neuromorphic Optical Flow and Real-time Implementation with Event Cameras

Yannick Schnider, Stanislaw Wozniak, Mathias Gehrig +5

Optical flow provides information on relative motion that is an important component in many computer vision pipelines. Neural networks provide high accuracy optical flow, yet their…

cs.CV2023

Recurrent Vision Transformers for Object Detection with Event Cameras

Mathias Gehrig, Davide Scaramuzza

We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at…

cs.CV2023

Revisiting Token Pruning for Object Detection and Instance Segmentation

Yifei Liu, Mathias Gehrig, Nico Messikommer +2

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in comp…

cs.RO2018

Visual Place Recognition with Probabilistic Vertex Voting

Mathias Gehrig, Elena Stumm, Timo Hinzmann +1

We propose a novel scoring concept for visual place recognition based on nearest neighbor descriptor voting and demonstrate how the algorithm naturally emerges from the problem for…

cs.CV2024

Reinforcement Learning Meets Visual Odometry

Nico Messikommer, Giovanni Cioffi, Mathias Gehrig +1

Visual Odometry (VO) is essential to downstream mobile robotics and augmented/virtual reality tasks. Despite recent advances, existing VO methods still rely on heuristic design cho…

cs.CV2021

DSEC: A Stereo Event Camera Dataset for Driving Scenarios

Mathias Gehrig, Willem Aarents, Daniel Gehrig +1

Once an academic venture, autonomous driving has received unparalleled corporate funding in the last decade. Still, the operating conditions of current autonomous cars are mostly r…

cs.CV2024

A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception

Asude Aydin, Mathias Gehrig, Daniel Gehrig +1

Spiking Neural Networks (SNN) are a class of bio-inspired neural networks that promise to bring low-power and low-latency inference to edge devices through asynchronous and sparse…

cs.CV2019

Focus Is All You Need: Loss Functions For Event-based Vision

Guillermo Gallego, Mathias Gehrig, Davide Scaramuzza

Event cameras are novel vision sensors that output pixel-level brightness changes ("events") instead of traditional video frames. These asynchronous sensors offer several advantage…

cs.CV2021

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

Daniel Gehrig, Michelle Rüegg, Mathias Gehrig +2

Event cameras are novel vision sensors that report per-pixel brightness changes as a stream of asynchronous "events". They offer significant advantages compared to standard cameras…

cs.RO2020

Towards Low-Latency High-Bandwidth Control of Quadrotors using Event Cameras

Rika Sugimoto Dimitrova, Mathias Gehrig, Dario Brescianini +1

Event cameras are a promising candidate to enable high speed vision-based control due to their low sensor latency and high temporal resolution. However, purely event-based feedback…

cs.CV2025

A Unified Framework for Event-based Frame Interpolation with Ad-hoc Deblurring in the Wild

Lei Sun, Daniel Gehrig, Christos Sakaridis +7

Effective video frame interpolation hinges on the adept handling of motion in the input scene. Prior work acknowledges asynchronous event information for this, but often overlooks…

cs.CV2021

E-RAFT: Dense Optical Flow from Event Cameras

Mathias Gehrig, Mario Millhäusler, Daniel Gehrig +1

We propose to incorporate feature correlation and sequential processing into dense optical flow estimation from event cameras. Modern frame-based optical flow methods heavily rely…

cs.CV2020

Video to Events: Recycling Video Datasets for Event Cameras

Daniel Gehrig, Mathias Gehrig, Javier Hidalgo-Carrió +1

Event cameras are novel sensors that output brightness changes in the form of a stream of asynchronous "events" instead of intensity frames. They offer significant advantages with…

cs.CV2024

State Space Models for Event Cameras

Nikola Zubić, Mathias Gehrig, Davide Scaramuzza

Today, state-of-the-art deep neural networks that process event-camera data first convert a temporal window of events into dense, grid-like input representations. As such, they exh…

cs.CV2023

From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection

Nikola Zubić, Daniel Gehrig, Mathias Gehrig +1

Today, state-of-the-art deep neural networks that process events first convert them into dense, grid-like input representations before using an off-the-shelf network. However, sele…

cs.CV2024

LEOD: Label-Efficient Object Detection for Event Cameras

Ziyi Wu, Mathias Gehrig, Qing Lyu +2

Object detection with event cameras benefits from the sensor's low latency and high dynamic range. However, it is costly to fully label event streams for supervised training due to…

cs.NE2020

Event-Based Angular Velocity Regression with Spiking Networks

Mathias Gehrig, Sumit Bam Shrestha, Daniel Mouritzen +1

Spiking Neural Networks (SNNs) are bio-inspired networks that process information conveyed as temporal spikes rather than numeric values. A spiking neuron of an SNN only produces a…