Home

Awesome

Interactive Deep Colorization in PyTorch

Project Page | Paper | Video | Talk | UI code

<img src='imgs/demo.gif' width=600>

Real-Time User-Guided Image Colorization with Learned Deep Priors.
Richard Zhang*, Jun-Yan Zhu*, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, and Alexei A. Efros.
In ACM Transactions on Graphics (SIGGRAPH 2017).

This is our PyTorch reimplementation for interactive image colorization, written by Richard Zhang and Jun-Yan Zhu.

This repository contains training usage. The original, official GitHub repo (with an interactive GUI, and originally Caffe backend) is here. The official repo has been updated to support PyTorch models on the backend, which can be trained in this repository.

Prerequisites

Getting Started

Installation

pip install -r requirements.txt
git clone https://github.com/richzhang/colorization-pytorch
cd colorization-pytorch

Dataset preparation

Training interactive colorization

Testing interactive colorization

Citation

If you use this code for your research, please cite our paper:

@article{zhang2017real,
  title={Real-Time User-Guided Image Colorization with Learned Deep Priors},
  author={Zhang, Richard and Zhu, Jun-Yan and Isola, Phillip and Geng, Xinyang and Lin, Angela S and Yu, Tianhe and Efros, Alexei A},
  journal={ACM Transactions on Graphics (TOG)},
  volume={9},
  number={4},
  year={2017},
  publisher={ACM}
}

Acknowledgments

This code borrows heavily from the pytorch-CycleGAN repository.