[emrah]

It is pretty impressive/crazy how well CDM and SR3 work together to go from 32x32 to 256x256 e.g. the Irish Setter. How could the algos possibly know the lighter coloring (due to breed or lighting) between the dog's eyes?! It's basically inventing pixels

[shakna]

Even basic upscaling algorithms can guess a surprising amount of detail.

When I was putting together a simple and fast method, a while back, I compared my own to the very, very, basic and ended up with this [0].

The far left is the original, the others are just shifting the scale percentage. There's a surprising amount of detail kept, even though all of the algorithms were pushed way beyond what should be considered their limits. (Purposefully - to expose bias that was easier to analyse.)

[0] https://raw.githubusercontent.com/shakna-israel/upscaler_ana...

[emrah]

Thank you for sharing. Honestly I don't see any "pixel divining" in your examples. The algos take existing pixels and build on top of that.

Irish Setter example seems to introduce detail that is not part of the original small image, like the lighter/whitish area between the dog's eyes.

[sorokod]

How confident can you be that the initial 32x32 was an Irish Setter?