This repository is implementation of the "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network".
- PyTorch 1.1.0
- Numpy 1.15.4
- Pillow 6.0.0
- h5py 2.8.0
- tqdm 4.30.0
The 91-image, Set5 dataset converted to HDF5 can be downloaded from the links below.
Dataset | Scale | Type | Link |
---|---|---|---|
91-image | 3 | Train | Link code: r3u7 |
Set5 | 3 | Eval | Link |
Otherwise, you can use prepare.py
to create custom dataset.
bash run.sh
Pre-trained weights can be downloaded from the links below.
Model | Scale | Link |
---|---|---|
ESPCN (91) | 3 | Link |
The results are stored in the same path as the query image.
bash run.sh
PSNR was calculated on the Y channel.
Eval. Mat | Scale | Paper (91) | Ours (91) |
---|---|---|---|
PSNR | 3 | 32.55 | 32.88 |
Original | BICUBIC x3 | ESPCN x3 (23.84 dB) |
![]() |
![]() |
![]() |
Original | BICUBIC x3 | ESPCN x3 (25.32 dB) |
![]() |
![]() |
![]() |