#245 · Primary category： Computer Vision
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.
Project last updated：02/13/26
GitHub Stars
641
Forks
114
Contributors
2
License
BSD-3-Clause
Why we included this project
Most object detection and image enhancement models are validated on well-lit images, so it is easy to overestimate how they will behave once the lights go down. ExDark was built to close that gap: 7,363 photographs taken in ten conditions from near-darkness to twilight, with 12 object classes labeled both at the image level and as bounding boxes. The repository also ships the source code for the authors' low-light enhancement method, which is a convenient baseline when you are comparing your own results. For anyone training or testing vision models that need to hold up in dim environments, this is a solid reference set.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)