Home

Awesome

Face and Image Super-resolution

Paper

Adrian Bulat*, Jing Yang*, Georgios Tzimiropoulos ''To learn image super-resolution, use a GAN to learn how to do image degradation first'' in ECCV2018

Method

<div align="center"> <img src="overview.png" width="600px"</img> </div>

Requirements

Pytorch 0.4.1

Data

Running testing

CUDA_VISIBLE_DEVICES=0, python model_evaluation.py 

Fid Calculation

CUDA_VISIBLE_DEVICES=0, python fid_score.py /Dataset/HIGH/SRtrainset_2/ test_res/

This code is from https://github.com/mseitzer/pytorch-fid

Citation

@inproceedings{bulat2018learn, 
  title={To learn image super-resolution, use a GAN to learn how to do image degradation first},
  author={Bulat, Adrian and Yang, Jing and Tzimiropoulos, Georgios},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  pages={185--200},
  year={2018}  
}

License

This project is licensed under the MIT License

Third-party Re-implementation

Thanks for yoon28 providing training: https://github.com/yoon28/unpaired_face_sr