Skip to content

The implement of TCI paper "BUSIFusion: Blind Unsupervised Single Image Fusion of Hyperspectral and RGB Images"

Notifications You must be signed in to change notification settings

CPREgroup/Real-Spec-RGB-Fusion

Repository files navigation

train a single image

python train.py --model_dir=test/

use pretrained model to train a single image (inference)

*pretrained model was trained on image fake_and_real_peppers_ms from CAVE dataset. And It is not trained to converge.

python train.py --model_dir=test/ --start_epoch=499 --end_epoch=500

for better performance, you can set --end_epoch= to a larger number, like 1000

About

The implement of TCI paper "BUSIFusion: Blind Unsupervised Single Image Fusion of Hyperspectral and RGB Images"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages