Please download the LOL-v1 and LOL-v2 from https://drive.google.com/drive/folders/1Kev7Np9hWEYHDxlcZXa7vIjBrX6O-Yry?usp=sharing
pip install -r requirements.txt
sh train.sh
We use PSNR and SSIM as the metrics for evaluation. Evaluate the model on the corresponding dataset using the test config.
For the evaluation, use the following command lines:
python test_LOLv1_v2_real.py
python test_LOLv2_synthetic.py
If you find the project useful, please cite:
@inproceedings{advLIE,
title={Adversarially Regularized Low-Light Image Enhancement},
author={Wang, William Y. and Liu, Lisa and Cai, Pingping},
booktitle={International Conference on Multimedia Modeling (MMM)},
year={2024}
}
This source code is inspired by SNR-aware Low-Light Image Enhancement, MIRNet.