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

TL;DR

The HUE dataset offers high-resolution event and frame sequences in low-light conditions, enabling better evaluation and development of low-light enhancement and event-based vision methods.

Contribution

This work introduces the HUE dataset, a large-scale, high-resolution collection of event and frame sequences in diverse low-light scenarios for the first time.

Findings

Event-based methods excel in certain metrics but may generate false positives.

The dataset facilitates comprehensive evaluation of low-light vision techniques.

Hybrid camera data enhances understanding of low-light scene dynamics.

Abstract

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.