[Paper] [Official Paddle Implementation] [Huggingface Gradio Demo] [Unofficial PyTorch Re-Implementation] [Colab]

This repository contains the officially unofficial PyTorch re-implementation of paper:

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction,

Songhua Liu*, Tianwei Lin*, Dongliang He, Fu Li, Ruifeng Deng, Xin Li, Errui Ding, Hao Wang (* indicates equal contribution)

ICCV 2021 (Oral)

• Linux or macOS
• Python 3
• PyTorch 1.7+ and other dependencies (torchvision, visdom, dominate, and other common python libs)

• Clone this repository:

  git clone https://github.com/Huage001/PaintTransformer
  cd PaintTransformer

• Download pretrained model from Google Drive and move it to inference directory:

  mv [Download Directory]/model.pth inference/
  cd inference

• Inference:

  python inference.py

  • Input image path, output path, and etc can be set in the main function.
  • Notably, there is a flag serial as one parameter of the main function:
    • If serial is True, strokes would be rendered serially. The consumption of video memory will be low but it requires more time.
    • If serial is False, strokes would be rendered in parallel. The consumption of video memory will be high but it would be faster.
    • If animated results are required, serial must be True.

• Train:

  • Before training, start visdom server:

    python -m visdom.server

  • Then, simply run:

    cd train
    bash train.sh

  • You can monitor training status at https://localhost:8097/ and models would be saved at checkpoints/painter folder.

• You may feel free to try other training options written in train.sh.

Input	Animated Output

• Do not want to run the code? Try an App 一刻相册 downloaded from here!

• If you find ideas or codes useful for your research, please cite:

  @inproceedings{liu2021paint,
    title={Paint Transformer: Feed Forward Neural Painting with Stroke Prediction},
    author={Liu, Songhua and Lin, Tianwei and He, Dongliang and Li, Fu and Deng, Ruifeng and Li, Xin and Ding, Errui and Wang, Hao},
    booktitle={Proceedings of the IEEE International Conference on Computer Vision},
    year={2021}
  }
  

• This implementation is developed based on the code framework of pytorch-CycleGAN-and-pix2pix by Junyan Zhu et al.