A PyTorch implementation of "Vectorization of Raster Manga by Deep Reinforcement Learning". If the paper or code is useful for your research, please cite
@article{su2021vectorization,
title={Vectorization of Raster Manga by Deep Reinforcement Learning},
author={Su, Hao and Niu, Jianwei and Liu, Xuefeng and Cui, Jiahe and Wan, Ji},
journal={arXiv preprint arXiv:2110.04830},
year={2021}
}
- Linux or Windows
- CPU or NVIDIA GPU + CUDA CuDNN
- Python 3
- Pytorch 1.7.0
- Clone this repo:
git clone https://github.com/SwordHolderSH/Mang2Vec.git
cd Mang2Vec
- Install PyTorch and other dependencies.
- Download
actor.pkl
from Google Drive to path'./model/'
.
- Get detailed information about all parameters using
python main.py -h
- Generate your customized vectorized mangas:
python main.py --img=./image/Naruto.png --actor=./model/actor.pkl --max_step=40 --divide=32
Thanks for the reference codes of ICCV2019-LearningToPaint.