For scientifically correct scaling (think forensics) you will of course need to interpolate the source data instead of generating synthetic data which is done by AI upscaling.
Both use priors, the former a large and complex one, the latter a simplistic one, but both "invent data based on assumptions".
For scientifically correct scaling (think forensics) you will of course need to interpolate the source data instead of generating synthetic data which is done by AI upscaling.