wangyins / transformer-for-image-colorization

[ACM MM 2021] Yes, "Attention is All You Need", for Exemplar based Colorization

Transformer for Image Colorization (Pytorch Implementation)

Paper | Pretrained Model

Yes, "Attention Is All You Need", for Exemplar based Colorization, ACMMM2021

Wang Yin¹, Peng Lu¹, Zhaoran Zhao¹, Xujun Peng^2
1Beijing University of Posts and Telecommunications,²USC

Table of Contents

• Prerequisites
• Getting Started
• Citation

Prerequisites

• Ubuntu 16.04
• Python 3.6.10
• Pytorch 1.5.1
• CPU or NVIDIA GPU + CUDA 10.2 CuDNN

Getting Started

Installation

• Clone this repo:

git clone https://github.com/wangyins/transformer-for-image-colorization
cd transformer-for-image-colorization
pip install requriments.txt

• Download model weights from this link to get "checkpoints_acmmm2021.zip"

mkdir -p checkpoints/imagenet/
cd checkpoints/imagenet/
unzip checkpoints_acmmm2021.zip

Testing

sh test.sh

Citation

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

@inproceedings{yin_mm2021,
  title={Yes, "Attention Is All You Need", for Exemplar based Colorization},
  author={Yin, Wang and Lu, Peng and Zhao, ZhaoRan and Peng, XuJun},
  booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
  year={2021}
}