16-bit buffer SuperResolution Scaling

I am trying to change the sample code to work on 16 bit images, as it is currently set to 8bit. Is that a limitation of the super resolution feature, or can it work on a 16 or 32 bit float buffer as well?

Seems these forums are not really that active, so hoping someone else who has played with it knows a bit more.

The docs are non-existent, makes it hard to know what is available and what is not.

Cheers,
Clint Hanson