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

By Yuen Peng Loh, Chee Seng Chan. Computer Vision and Image Understanding, 2018

833 citations recorded by the source corpus.

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 this https URL

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/12e94e888a9966738c56430abff7ed7fa452221b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Toward Fast, Flexible, and Robust Low-Light Image Enhancement (2022, positive): “Here, we tested lots of challenging in-the-wild examples from the DARK FACE [31] and ExDark [15] datasets.”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, background): “We investigate the impact of light enhancement on the extremely dark ( ExDark ) dataset [53], which was speciﬁcally built for the task of low-light image recognition.”
Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, background): “In [73], an Exclusively Dark (ExDARK) dataset is proposed with a collection of 7,363 images captured from very low-light environments with 12 object classes annotated on both image class level and local object bounding boxes.”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, background): “…research on low-light image enhancement, not only are some low-light data available from widely used public benchmark datasets such as PASCAL VOC [281], ImageNet [282], and Microsoft COCO [283], but researchers are also building public datasets speciﬁcally designed for low-light image…”
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (2023, methodology): “We conduct low-light object detection experiments on the ExDark [33] dataset to compare the preprocessing effects of different enhancement algorithms for high-level vision understanding.”
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (2020, background): “There are also works on deep-learning based image enhancement from raw images [4], or the joint task of low-light image enhancement and high-level computer vision tasks, such as face detection [34], object detection [19], etc.”
Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation (2020, methodology): “Color [37] 10,000 pedestrian 24 LabelMeFacade [38] 395 building 25 UT Zappos50K [39] 10,000 shoes 26 TRANCOS [40] 1,244 traffic 27 FGVC [40] 10,000 aeroplane 28 Mall Dataset [41] 2,000 mall 29 Chars74K [42] 7,705 character 30 DomainNet [8] 10,000 painting 31 Paris Dataset [43] 3,187 street 32 Domain”
SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention (2024, positive): “Building on the above configurations, we further evaluate the proposed SCSA method’s detection performance and generalization capability on Pascal VOC [11], as well as in complex scenarios such as VisDrone [10], ExDark [34], and FLIR-ADAS V2 [13].”
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (2021, neutral): “2010) and the relatively comprehensive low-light detection dataset ExDark (Loh and Chan 2019) both contain ten categories of objects: Bicycle, Boat, Bottle, Bus, Car, Cat, Chair, Dog, Motorbike, People(Person).”
Benchmarking Low-Light Image Enhancement and Beyond (2021, background): “Recently, Exclusively Dark dataset (Loh and Chan 2019) is proposed including low-light images with image classes and local objectboundingboxannotationstoevaluatehigh-levelvision tasks, i.e. image recognition and object detection.”