single-image-super-resolution-1033¶

Use Case and High-Level Description¶

An Attention-Based Approach for Single Image Super Resolution but with reduced number of channels and changes in network architecture. It enhances the resolution of the input image by a factor of 3.

Low resolution:

Bicubic interpolation:

Super resolution:

For reference, PSNR for bicubic upsampling on test dataset is 28.48 dB.

Image, name: 0, shape: 1, 3, 360, 640 in the format B, C, H, W, where:
- B - batch size
- C - number of channels
- H - image height
- W - image width
Bicubic interpolation of the input image, name: 1, shape: 1, 3, 1080, 1920 in the format B, C, H, W, where:
- B - batch size
- C - number of channels
- H - image height
- W - image width
Expected color order is BGR.

The net output is a blob with shapes 1, 3, 1080, 1920 that contains image after super resolution.

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities:

[*] Other names and brands may be claimed as the property of others.