(Author here.) Did you see the faces example on the GitHub page? It was a domain-specific network trained adversarially for that purpose, but I have yet to see any super-resolution of that quality with or without machine learning.
Most other approaches don't even try to inject high-frequency detail into the high-resolution images because the PSNR/SSIM benchmarks drop. Until those metrics/benchmarks are dropped, there'll be little more progress in super-resolution.
I ran that image through the library with the default settings and it came out with an image that is in my opinion much better than all of the approaches shown there
Most other approaches don't even try to inject high-frequency detail into the high-resolution images because the PSNR/SSIM benchmarks drop. Until those metrics/benchmarks are dropped, there'll be little more progress in super-resolution.