bupt-ai-cz/LLVIP

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

31
/ 100
Emerging

Comprises 30,976 aligned visible-infrared image pairs with pedestrian bounding box annotations for low-light detection and fusion tasks. Includes baseline implementations for image fusion (FusionGAN, Densefuse) and pedestrian detection (YOLOv5, YOLOv3) with format conversion tools supporting COCO, YOLO, and XML annotation standards. Pre-trained pix2pixGAN models and raw unregistered image pairs are available to enable downstream research in image registration and cross-modal vision.

801 stars. No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 1 / 25
Community 18 / 25

How are scores calculated?

Stars

801

Forks

74

Language

Jupyter Notebook

License

Last pushed

Aug 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/bupt-ai-cz/LLVIP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.