GERD: Geometric event response data generation

Jens Egholm Pedersen, Dimitris Korakovounis, Jörg Conradt
12/4/2024
cs.CV

Official code: ncskth/gerd (0 stars, last commit 2026-03-29).

Abstract

Event-based vision sensors are appealing because of their time resolution, higher dynamic range, and low-power consumption. They also provide data that is fundamentally different from conventional frame-based cameras: events are sparse, discrete, and require integration in time. Unlike conventional models grounded in established geometric and physical principles, event-based models lack comparable foundations. We introduce a method to generate event-based data under controlled transformations. Specifically, we subject a prototypical object to transformations that change over time to produce carefully curated event videos. We hope this work simplifies studies for geometric approaches in event-based vision. GERD is available at https://github.com/ncskth/gerd

View on arXivView PDF

Code Implementations(1)

ncskth/gerdOfficial100%

Artificially generated event-based vision datasets

03Python, Jupyter NotebookJun 29, 20226 months ago

Similar Papers

Recent Event Camera Innovations: A Survey

86% match1 repo3262024

Gradient events: improved acquisition of visual information in event cameras

85% match2024

E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning

85% match1 repo212024

An Event-Oriented Diffusion-Refinement Method for Sparse Events Completion

85% match2024

Rethinking Video with a Universal Event-Based Representation

85% match2024

YCB-Ev SD: Synthetic event-vision dataset for 6DoF object pose estimation

84% match2025

Cite this paper

@article{pedersen2024gerd,
  title  = {GERD: Geometric event response data generation},
  author = {Jens Egholm Pedersen and Dimitris Korakovounis and Jörg Conradt},
  year   = {2024},
  eprint = {2412.03259},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.03259v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.03259.svg)](https://codeofpaper.com/paper/2412.03259)

Discussion