A Model for Super-Resolution
This net uses an architecture inspired by VGG in order to create super-resolution images. It takes an interpolated low-resolution image and refines the details to create a sharp upsampling.
Get this network from the Wolfram Neural Net Repository. See details about this specific network here.
This network performs the refinement on the Y channel in the YCbCr color space. Here is an evaluation function that must be used to pre- and post-process the input.
Evaluate the network on a small image to double its size.
Compare with the unrefined resampling using the same cubic kernel used to produce the net input and a high-quality OMOMS kernel.
show complete Wolfram Language input