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

Source: [Getting to Know Low-light Images with The Exclusively Dark Dataset](<https://www.sota2.com/research/paper/68fa64691e209131cea04887>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:04:03.574Z

Authors: Yuen Peng Loh, Chee Seng Chan

Published: 2018-05-29T02:59:41.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Nighttime Image Enhancement on ExDark 1,271 images](<https://www.sota2.com/research/sota/nighttime-image-enhancement-on-exdark-1-271-images.md>): Nighttime Image Enhancement; ExDark 1,271 images; CLIPIQA: 0.4281.

- [Object Detection on ExDark (test)](<https://www.sota2.com/research/sota/object-detection-on-exdark-test.md>): Object Detection; ExDark (test); mAP (Mean Average Precision): 76.32.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1805.11227>)

[PDF](<https://arxiv.org/pdf/1805.11227.pdf>)
