HUE Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ercan, Burak, Eker, Onur, Erdem, Aykut, Erdem, Erkut
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913563514241024
author Ercan, Burak
Eker, Onur
Erdem, Aykut
Erdem, Erkut
author_facet Ercan, Burak
Eker, Onur
Erdem, Aykut
Erdem, Erkut
contents Low-light environments pose significant challenges for image enhancement methods. To address these challenges, in this work, we introduce the HUE dataset, a comprehensive collection of high-resolution event and frame sequences captured in diverse and challenging low-light conditions. Our dataset includes 106 sequences, encompassing indoor, cityscape, twilight, night, driving, and controlled scenarios, each carefully recorded to address various illumination levels and dynamic ranges. Utilizing a hybrid RGB and event camera setup. we collect a dataset that combines high-resolution event data with complementary frame data. We employ both qualitative and quantitative evaluations using no-reference metrics to assess state-of-the-art low-light enhancement and event-based image reconstruction methods. Additionally, we evaluate these methods on a downstream object detection task. Our findings reveal that while event-based methods perform well in specific metrics, they may produce false positives in practical applications. This dataset and our comprehensive analysis provide valuable insights for future research in low-light vision and hybrid camera systems.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HUE Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision
Ercan, Burak
Eker, Onur
Erdem, Aykut
Erdem, Erkut
Computer Vision and Pattern Recognition
Low-light environments pose significant challenges for image enhancement methods. To address these challenges, in this work, we introduce the HUE dataset, a comprehensive collection of high-resolution event and frame sequences captured in diverse and challenging low-light conditions. Our dataset includes 106 sequences, encompassing indoor, cityscape, twilight, night, driving, and controlled scenarios, each carefully recorded to address various illumination levels and dynamic ranges. Utilizing a hybrid RGB and event camera setup. we collect a dataset that combines high-resolution event data with complementary frame data. We employ both qualitative and quantitative evaluations using no-reference metrics to assess state-of-the-art low-light enhancement and event-based image reconstruction methods. Additionally, we evaluate these methods on a downstream object detection task. Our findings reveal that while event-based methods perform well in specific metrics, they may produce false positives in practical applications. This dataset and our comprehensive analysis provide valuable insights for future research in low-light vision and hybrid camera systems.
title HUE Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.19164