Skip to content

Latest commit

 

History

History
51 lines (27 loc) · 945 Bytes

File metadata and controls

51 lines (27 loc) · 945 Bytes

Dynamic-CSD

This is the official implementation of Dynamic Image Super-Resolution via Progressively Contrastive Self-Distillation. A preliminary version of this work has been presented as a conference paper. You could find the code of CSD here.

Coming soon...

Abstract

Results

Dependencies

PyTorch

matplotlib

imageio

tensorboardX

opencv-python

scipy

scikit-image

Train

Prepare data

We use DIV2K training set as our training data.

About how to download data, you could refer to EDSR(PyTorch)

Begin to train

Test

Citation

If you find the code helpful in you research or work, please cite as:


}

Acknowledgements

This code is built on EDSR(PyTorch). We thank the authors for sharing their codes.