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

Burak Ercan 1 Onur Eker 1,2 Aykut Erdem 3,4 Erkut Erdem 1
1 Hacettepe University, Computer Engineering Department 2 HAVELSAN Inc.
3 Koç University, Computer Engineering Department 4 Koç University, KUIS AI Center
ECCV Workshop on Neuromorphic Vision, 2024

Paper

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.

Dataset Download

Dataset parts are hosted on Zenodo:

BibTeX

@inproceedings{ercan2024hue,
title={{HUE} Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision},
author={Ercan, Burak and Eker, Onur and Erdem, Aykut and Erdem, Erkut},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV) Workshops 2024},
year={2024},
pages={0-0}}

Acknowledgements
This work was supported by TUBITAK-1001 Program Award No. 121E454.