Skip to content
PyTorch code for our paper "Gated Multiple Feedback Network for Image Super-Resolution" (BMVC2019)
Branch: master
Clone or download
Latest commit 2343acf Jul 10, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
figs Initial commit Jul 5, 2019
networks Update and Jul 9, 2019
options Update Jul 7, 2019
.gitignore Initial commit Jul 5, 2019 Update arXiv link Jul 10, 2019

Gated Multiple Feedback Network for Image Super-Resolution

This repository contains the PyTorch implementation for the proposed GMFN [arXiv].

The framework of our proposed GMFN. The colored arrows among different time steps denote the multiple feedback connections. The high-level information carried by them helps low-level features become more representative.


Clone SRFBN as the backbone and satisfy its requirements.


  1. Copy ./networks/ into SRFBN_CVPR19/networks/

  2. Download the pre-trained models from Google driver or Baidu Netdisk, unzip and place them into SRFBN_CVPR19/models.

  3. Copy ./options/test/ to SRFBN_CVPR19/options/test/.

  4. Run commands cd SRFBN_CVPR19 and one of followings for evaluation on Set5:

python -opt options/test/test_GMFN_x2.json
python -opt options/test/test_GMFN_x3.json
python -opt options/test/test_GMFN_x4.json
  1. Finally, PSNR/SSIM values for Set5 are shown on your screen, you can find the reconstruction images in ./results.

To test GMFN on other standard SR benchmarks or your own images, please refer to the instruction in SRFBN.


  1. Prepare the training set according to this (1-3).
  2. Modify ./options/train/train_GMFN.json by following the instructions in ./options/train/
  3. Run commands:
python -opt options/train/train_GNFN.json
  1. You can monitor the training process in ./experiments.

  2. Finally, you can follow the test pipeline to evaluate the model trained by yourself.


Quantitative Results

Quantitative evaluation under scale factors x2, x3 and x4. The best performance is shown in bold and the second best performance is underlined.

More Qualitative Results (x4)


If you find our work useful in your research or publications, please consider citing:

    author = {Li, Qilei and Li, Zhen and Lu, Lu and Jeon, Gwanggil and Liu, Kai and Yang, Xiaomin},
    title = {Gated Multiple Feedback Network for Image Super-Resolution},
    booktitle = {The British Machine Vision Conference (BMVC)},
    year = {2019}

    author = {Li, Zhen and Yang, Jinglei and Liu, Zheng and Yang, Xiaomin and Jeon, Gwanggil and Wu, Wei},
    title = {Feedback Network for Image Super-Resolution},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year= {2019}
You can’t perform that action at this time.