CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer (ECCV 2022 Oral)
@inproceedings{wu2022ccpl,
title={CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer},
author={Wu, Zijie and Zhu, Zhen and Du, Junping and Bai, Xiang},
year={2022},
booktitle={ECCV},
}
Inspirations for CCPL
Details of CCPL
Artistic Style Transfer
<div align=center>![](https://github.com/JarrentWu1031/CCPL/blob/main/images/Fig.%206.jpg?raw=true)
Photo-realistic Style Transfer
<div align=center>![](https://github.com/JarrentWu1031/CCPL/blob/main/images/Fig.%207.jpg?raw=true)
Super-resolution PST
<div align=center>![](https://github.com/JarrentWu1031/CCPL/blob/main/images/pho1.jpg?raw=true)
Short-term Temporal Consistency
<div align=center>![](https://github.com/JarrentWu1031/CCPL/blob/main/images/Fig.%205.jpg?raw=true)
Long-term Temporal Consistency
<div align=center>![](https://github.com/JarrentWu1031/CCPL/blob/main/images/lterm.jpg?raw=true)
Image-to-image translation
Acknowledgments
The code is based on project AdaIN and CUT. We sincerely thank them for their great work.