An Attention-Based Approach for Single Image Super Resolution but with reduced number of channels and changes in network achitecture. It enhances the resolution of the input image by a factor of 3.
Low resolution:
Bicubic interpolation:
Super resolution:
| Metric | Value |
|---|---|
| PSNR | 30.46 dB |
| GFlops | 16.062 |
| MParams | 0.030 |
| Source framework | Pytorch* |
For reference, PSNR for bicubic upsampling on test dataset is 28.48 dB.
-
name: "0" , shape: [1x3x360x640] - An input image in the format [BxCxHxW], where:
- B - batch size
- C - number of channels
- H - image height
- W - image width.
-
name: "1" , shape: [1x3x1080x1920] - Bicubic interpolation of the input image in the format [BxCxHxW], where:
- B - batch size
- C - number of channels
- H - image height
- W - image width.
Expected color order is BGR.
- The net outputs one blobs with shapes [1, 3, 1080, 1920] that contains image after super resolution.
[*] Other names and brands may be claimed as the property of others.