One-Step Event-Driven High-Speed Autofocus

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bao, Yuhan, Gao, Shaohua, Li, Wenyong, Wang, Kaiwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929738905288704
author Bao, Yuhan
Gao, Shaohua
Li, Wenyong
Wang, Kaiwei
author_facet Bao, Yuhan
Gao, Shaohua
Li, Wenyong
Wang, Kaiwei
contents High-speed autofocus in extreme scenes remains a significant challenge. Traditional methods rely on repeated sampling around the focus position, resulting in ``focus hunting''. Event-driven methods have advanced focusing speed and improved performance in low-light conditions; however, current approaches still require at least one lengthy round of ``focus hunting'', involving the collection of a complete focus stack. We introduce the Event Laplacian Product (ELP) focus detection function, which combines event data with grayscale Laplacian information, redefining focus search as a detection task. This innovation enables the first one-step event-driven autofocus, cutting focusing time by up to two-thirds and reducing focusing error by 24 times on the DAVIS346 dataset and 22 times on the EVK4 dataset. Additionally, we present an autofocus pipeline tailored for event-only cameras, achieving accurate results across a range of challenging motion and lighting conditions. All datasets and code will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01214
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-Step Event-Driven High-Speed Autofocus
Bao, Yuhan
Gao, Shaohua
Li, Wenyong
Wang, Kaiwei
Computer Vision and Pattern Recognition
Optics
High-speed autofocus in extreme scenes remains a significant challenge. Traditional methods rely on repeated sampling around the focus position, resulting in ``focus hunting''. Event-driven methods have advanced focusing speed and improved performance in low-light conditions; however, current approaches still require at least one lengthy round of ``focus hunting'', involving the collection of a complete focus stack. We introduce the Event Laplacian Product (ELP) focus detection function, which combines event data with grayscale Laplacian information, redefining focus search as a detection task. This innovation enables the first one-step event-driven autofocus, cutting focusing time by up to two-thirds and reducing focusing error by 24 times on the DAVIS346 dataset and 22 times on the EVK4 dataset. Additionally, we present an autofocus pipeline tailored for event-only cameras, achieving accurate results across a range of challenging motion and lighting conditions. All datasets and code will be made publicly available.
title One-Step Event-Driven High-Speed Autofocus
topic Computer Vision and Pattern Recognition
Optics
url https://arxiv.org/abs/2503.01214