Deep Exemplar-based Video Colorization (Pytorch Implementation)
Paper | Pretrained Model | Youtube video
Deep Exemplar-based Video Colorization, CVPR2019
Bo Zhang1,3,
Mingming He1,5,
Jing Liao2,
Pedro V. Sander1,
Lu Yuan4,
Amine Bermak1,
Dong Chen3
1Hong Kong University of Science and Technology,2City University of Hong Kong,
3Microsoft Research Asia, 4Microsoft Cloud&AI, 5USC Institute for Creative Technologies
Prerequisites
- Python 3.6+
- Nvidia GPU + CUDA, CuDNN
Installation
conda create -n ColorVid python=3.6
source activate ColorVid
pip install -r requirements.txt
Data preparation
checkpoint, pre-trained vgg
- input video frames
- reference image
- output
Test
python test.py
TODO
- Release the training code
- Prepare the Colab Demo
- Output the video
- GIF teaser
Citation
If you use this code for your research, please cite our paper.
@inproceedings{zhang2019deep, title={Deep exemplar-based video colorization}, author={Zhang, Bo and He, Mingming and Liao, Jing and Sander, Pedro V and Yuan, Lu and Bermak, Amine and Chen, Dong}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={8052--8061}, year={2019} }
License
This project is licensed under the MIT license.