jarrentwu1031 / ccpl

Contrastive Coherence Preserving Loss for Versatile Style Transfer

  • Public
  • 1.9K runs
  • GitHub
  • Paper
  • License
Run with an API
Playground API Examples README Versions

Input

Output

Examples

View more examples

Run time and cost

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 5 seconds.

Readme

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},
}

animated

Inspirations for CCPL

animated

Details of CCPL

animated

Artistic Style Transfer

<div align=center> </div>

Photo-realistic Style Transfer

<div align=center> </div>

Super-resolution PST

<div align=center> </div>

Short-term Temporal Consistency

<div align=center> </div>

Long-term Temporal Consistency

<div align=center> </div>

Image-to-image translation

animated

Acknowledgments

The code is based on project AdaIN and CUT. We sincerely thank them for their great work.