Skip to content

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MBLLEN

This is an unofficial PyTorch implementation of paper "MBLLEN: Low-light Image/Video Enhancement Using CNNs", thank Lv for his work!

Result

PSNR SSIM
MBLLEN_Dark 26.07 0.882
MBLLEN_Low 25.64 0.870

Installtion

pip install -r requirements.txt

Train

  1. Download MBLLEN dataset and unzip all files (Notice: test_dark directory contains 200 images but test directory only contains 144 images, you have to remove the extra images in test_dark).

  2. Modify config.py

  3. python main.py

Test

  1. python infer.py

  2. python metric.py

Reference

  1. Keras version by Lvfeifan

Related work

About

Unofficial PyTorch Code for “MBLLEN: Low-light Image/Video Enhancement Using CNNs”, BMVC 2018.

Resources

Stars

27 stars

Watchers

1 watching

Forks

Releases

Packages

Used by

Contributors

Languages