The implementation of the paper "Brightness-Adjustable Low-Light Image Enhancement via Noise-Only Training Scheme"
NOTNet is inspired by NoiSER, and our implementation is developed from Zero-DCE. Thanks for your attention to these work!
- Python 3.8
- Pytorch 2.1.0
- torchvision 0.16.0
- opencv 4.5.3
- cuda 12.0
All you need is basic environment.
python train_with_noises.py
python test_with_real_images.py --V=0.6
Please adjust the V value manually to meet your need.