The goal of this project is to upscale and improve the quality of low resolution images.
Resources used: "Image Super-Resolution Using Deep Convolutional Networks". https://arxiv.org/pdf/1809.00219v2.pdf https://arxiv.org/abs/2107.10833 https://www.youtube.com/watch?v=fxHWoDSSvSc https://paperswithcode.com/paper/esrgan-enhanced-super-resolution-generative/review/
The 91-image, Set5 dataset converted to HDF5 can be downloaded from the links below.
| Dataset | Scale | Type | Link |
|---|---|---|---|
| 91-image | 2 | Train | Download |
| 91-image | 3 | Train | Download |
| 91-image | 4 | Train | Download |
| Set5 | 2 | Eval | Download |
| Set5 | 3 | Eval | Download |
| Set5 | 4 | Eval | Download |
Otherwise, you can use prepare.py to create custom dataset.
Pre-trained weights can be downloaded from the links below.
| Model | Scale | Link |
|---|---|---|
| 9-5-5 | 2 | Download |
| 9-5-5 | 3 | Download |
| 9-5-5 | 4 | Download |
The results are stored in the same path as the query image.
We used the network settings for experiments, i.e., .
PSNR was calculated on the Y channel.
| Eval. Mat | Scale | SRCNN | SRCNN (Ours) |
|---|---|---|---|
| PSNR | 2 | 36.66 | 36.65 |
| PSNR | 3 | 32.75 | 33.29 |
| PSNR | 4 | 30.49 | 30.25 |
| Original | BICUBIC x3 | SRCNN x3 (27.53 dB) |
|
|
|
- PyTorch 1.0.0
- Numpy 1.15.4
- Pillow 5.4.1
- h5py 2.8.0
- tqdm 4.30.0