cs-chan/Exclusively-Dark-Image-Dataset
Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection of low-light images taken in very low-light environments to twilight (i.e 10 different conditions) to-date with image class and object level annotations.
This dataset provides a large collection of images captured in diverse low-light conditions, from twilight to very dark environments. It includes both overall image classifications and precise bounding box annotations for 12 common object types. Researchers and developers working on computer vision tasks will use this to train and evaluate models that need to recognize objects or enhance images in challenging lighting.
618 stars.
Use this if you are developing or testing algorithms for object detection or image enhancement that must perform reliably in low-light conditions.
Not ideal if your project focuses on well-lit environments or requires annotations for object classes beyond the 12 provided.
Stars
618
Forks
109
Language
MATLAB
License
BSD-3-Clause
Category
Last pushed
Feb 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cs-chan/Exclusively-Dark-Image-Dataset"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ceciliavision/perceptual-reflection-removal
Single Image Reflection Separation with Perceptual Losses
Srameo/LED
[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising...
plemeri/InSPyReNet
Official PyTorch implementation of Revisiting Image Pyramid Structure for High Resolution...
cidautai/DarkIR
CVPR 2025 DarkIR: Robust Low-Light Image Restoration - State of the art low light deblurring....
York-SDCNLab/Ghost-DeblurGAN
This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size...