This is the official implementation of the paper in AAAI2020. We provide the sample codes for training and testing and pretrained models on photo enhancement.
Clone the repository.
# Make sure to clone with --recursive
git clone --recursive git@github.com:satoshi-kosugi/Unpaired-Image-Enhancement.git
$ROOT/fivek_dataset/original/
and $ROOT/fivek_dataset/expertC/
, respectively.python train.py settings/photo_enhancement.yaml logs
python test.py settings/photo_enhancement.yaml logs --result_dir logs/20200115T223451.986831/96000_finish/test_results --load logs/20200115T223451.986831/96000_finish/
python demo.py settings/photo_enhancement.yaml --load_generator generator_weights_for_demo.npz --file_name $image_name
The following windows will be displayed.
Our implementation is based on chainer_spiral. We would like to thank them.
If you find our research useful in your research, please consider citing:
@inproceedings{kosugi2020unpaired,
title={Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software},
author={Kosugi, Satoshi and Yamasaki, Toshihiko},
booktitle = {AAAI},
year = {2020}
}