bupt-ai-cz/LLVIP
LLVIP: A Visible-infrared Paired Dataset for Low-light Vision
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.
Stars
801
Forks
74
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
cs-chan/Exclusively-Dark-Image-Dataset
Exclusively Dark (ExDARK) dataset which to the best of our knowledge, is the largest collection...
Srameo/LED
[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising...
ceciliavision/perceptual-reflection-removal
Single Image Reflection Separation with Perceptual Losses
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....