lizhangray/edge-srn

Generating realistic texture for super-resolution by designing a lightweight network

🌌 Edge Guided Learning for Image Super-resolution with Realistic Textures

Code for our IEEE WCCI 2022 paper Edge Guided Learning for Image Super-resolution with Realistic Textures

🍅   Run

The pretrained models and test codes are uploaded, now you can run test.py to get results in the challenge. Just like:

    #python test.py pathToModel datasetsName

    python test.py checkpoints/EdgeSRN_x4.pth Set14

You can also get the result images in "page_results" folder we provided.

🍅   Requirement

The code was tested on python3.9, linux.

🍅   Citing

The code is free for academic/research purpose. Please kindly cite our work in your publications if it helps your research.

@article{
  title={Edge Guided Learning for Image Super-resolution with Realistic Textures},
  author={Z. Li, Z. Zhong, Z. Chen, G. Yao, X. Chen, W. Huang},
  conference={The 2022 International Joint Conference on Neural Networks (IJCNN). IEEE, Padua, Italy. 2022, 18-23 July},
  year={2022}
}

🍅   Example (Left is LR, Right is Ours)