AncientPainitng2NaturalImage

Pytorch implementation for the paper [Ancient Painting to Natural Image: A New Solution for Painting Processing] .

Getting Started

Installation

Install PyTorch and dependencies from http://pytorch.org
Install Torch vision from the source.

git clone https://github.com/pytorch/vision
cd vision
python setup.py install

Install python libraries visdom and dominate.

pip install visdom
pip install dominate

Clone this repo:

git clone https://github.com/qiaott/AncientPainitng2NaturalImage.git
cd AncientPainitng2NaturalImage

Download our datasets (e.g. CBP, CFP) from here .

Train/Test

Train a model:

./do_train.sh

Test a model:

./do_test.sh

You can play with your own dataset by changing the dataroot.

##Citation If you use this code/datasets for your research, please cite our papers.

@inproceedings{qiao2019ancient,
  title={Ancient Painting to Natural Image: A New Solution for Painting Processing},
  author={Qiao, Tingting and Zhang, Weijing and Zhang, Miao and Ma, Zixuan and Xu, Duanqing},
  booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  pages={521--530},
  year={2019},
  organization={IEEE}
}

Acknowledgments

Code is inspired by pytorch-CycleGAN-and-pix2pix.