They started their model with RAW format, so the model should encoded some interactions between red / blue / green light sensors and that can help generate genuine sub-pixel details. OTOH, this is machine learning, unless you specifically has some discriminators (just an idea) to counteract, you don't really know how much these are genuine sub-pixel details and how much are hallucinations.

Turning a regular video into a super photo is different from turning a regular photo into a super photo.