Noise and lack of resolution are different beasts. That paper has nothing to do with "zoom & enhance", which will never reach the level we see in movies, since the information is just not there.
Especially in certain domains such as written letters (e.g. license plates) or faces that have a well-known structure with variations in known dimensions, I wouldn't be surprised to see algorithms that can probabilistically infer what information would have originally been there. Of course you'd never reconstruct an entire face from a single pixel, but how far can we go? I dunno - but my hunch is pretty far