/AncientPainitng2NaturalImage

Ancient Painting to Natural Image: A New Solution for Painting Processing

Primary LanguagePythonOtherNOASSERTION

AncientPainitng2NaturalImage

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

image

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
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.