Recurrent Back-Projection Network for Video Super-Resolution (CVPR2019)

Project page: https://alterzero.github.io/projects/RBPN.html

NEWS

• Apr 1, 2020 -> NEW paper on Space-Time Super-Resolution STARnet (to appear in CVPR2020)
• May 9, 2019 -> Added RBPN_F11 (this model was used on NTIRE2019)

Dependencies

• Python 3.5
• PyTorch >= 1.0.0
• Pyflow -> https://github.com/pathak22/pyflow

  cd pyflow/
  python setup.py build_ext -i
  cp pyflow*.so ..

Dataset

• Vimeo-90k Dataset

Pretrained Model and Testset

https://drive.google.com/drive/folders/1sI41DH5TUNBKkxRJ-_w5rUf90rN97UFn?usp=sharing

HOW TO

#Training

   python    main.py    

#Testing

   python    eval.py    

Our paper on Image Super-Resolution

Deep Back-Projection Networks for Super-Resolution (CVPR2018)

Winner (1st) of NTIRE2018 Competition (Track: x8 Bicubic Downsampling)

Winner of PIRM2018 (1st on Region 2, 3rd on Region 1, and 5th on Region 3)

Project page: https://alterzero.github.io/projects/DBPN.html

Citations

If you find this work useful, please consider citing it.

@inproceedings{RBPN2019,
  title={Recurrent Back-Projection Network for Video Super-Resolution},
  author={Haris, Muhammad and Shakhnarovich, Greg and Ukita, Norimichi},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019}
}