High-frequency near-eye ground truth for event-based eye tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Simpsi, Andrea, Aspesi, Andrea, Mentasti, Simone, Merigo, Luca, Ongarello, Tommaso, Matteucci, Matteo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913678810415104
author Simpsi, Andrea
Aspesi, Andrea
Mentasti, Simone
Merigo, Luca
Ongarello, Tommaso
Matteucci, Matteo
author_facet Simpsi, Andrea
Aspesi, Andrea
Mentasti, Simone
Merigo, Luca
Ongarello, Tommaso
Matteucci, Matteo
contents Event-based eye tracking is a promising solution for efficient and low-power eye tracking in smart eyewear technologies. However, the novelty of event-based sensors has resulted in a limited number of available datasets, particularly those with eye-level annotations, crucial for algorithm validation and deep-learning training. This paper addresses this gap by presenting an improved version of a popular event-based eye-tracking dataset. We introduce a semi-automatic annotation pipeline specifically designed for event-based data annotation. Additionally, we provide the scientific community with the computed annotations for pupil detection at 200Hz.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-frequency near-eye ground truth for event-based eye tracking
Simpsi, Andrea
Aspesi, Andrea
Mentasti, Simone
Merigo, Luca
Ongarello, Tommaso
Matteucci, Matteo
Computer Vision and Pattern Recognition
Event-based eye tracking is a promising solution for efficient and low-power eye tracking in smart eyewear technologies. However, the novelty of event-based sensors has resulted in a limited number of available datasets, particularly those with eye-level annotations, crucial for algorithm validation and deep-learning training. This paper addresses this gap by presenting an improved version of a popular event-based eye-tracking dataset. We introduce a semi-automatic annotation pipeline specifically designed for event-based data annotation. Additionally, we provide the scientific community with the computed annotations for pupil detection at 200Hz.
title High-frequency near-eye ground truth for event-based eye tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.03057