Getting to Know Low-light Images with The Exclusively Dark Dataset

TL;DR

This paper introduces the Exclusively Dark dataset, a comprehensive collection of low-light images with annotations, to facilitate research in low-light image enhancement and object detection, revealing that low-light conditions deeply affect feature representations.

Contribution

The paper presents the first dedicated low-light image dataset with diverse types and annotations, addressing the lack of benchmark data for low-light vision tasks.

Findings

Low-light significantly impacts feature extraction beyond simple illumination adjustments.

The dataset enables better understanding of low-light effects on object detection.

Insights into how low-light conditions influence learned and handcrafted features.

Abstract

Low-light is an inescapable element of our daily surroundings that greatly affects the efficiency of our vision. Research works on low-light has seen a steady growth, particularly in the field of image enhancement, but there is still a lack of a go-to database as benchmark. Besides, research fields that may assist us in low-light environments, such as object detection, has glossed over this aspect even though breakthroughs-after-breakthroughs had been achieved in recent years, most noticeably from the lack of low-light data (less than 2% of the total images) in successful public benchmark dataset such as PASCAL VOC, ImageNet, and Microsoft COCO. Thus, we propose the Exclusively Dark dataset to elevate this data drought, consisting exclusively of ten different types of low-light images (i.e. low, ambient, object, single, weak, strong, screen, window, shadow and twilight) captured in visible light only with image and object level annotations. Moreover, we share insightful findings in regards to the effects of low-light on the object detection task by analyzing visualizations of both hand-crafted and learned features. Most importantly, we found that the effects of low-light reaches far deeper into the features than can be solved by simple "illumination invariance'". It is our hope that this analysis and the Exclusively Dark dataset can encourage the growth in low-light domain researches on different fields. The Exclusively Dark dataset with its annotation is available at https://github.com/cs-chan/Exclusively-Dark-Image-Dataset