Hacker News Reader

How do you recover information that is not there? Best you can do is guess what’s supposed to be there.

That’s why I hate watching 4K AI “enhanced” historical films, it is akin to rewriting history.

Long story short, these algorithms aren't recovering information that was lost. They reconstruct the images by guessing what should've been there. So, you're not violating any information theoretic concept.

But this means the guesses can be incorrect, although the likelihood of that happening can be greatly reduced with good training data.

I never heard of this before. What kind of enhancing does the AI do?

It tries to predict patterns from blurry shots. It might introduce artifacts that were never there: some drawings I upscaled turned distant woods into houses. You can see why this might be bad when viewing something for historical accuracy.

See e.g., https://www.topazlabs.com and https://github.com/nagadomi/waifu2x

Sorry, I think I was unclear. What I meant is that I am familiar with these techniques, I just never heard them applied in the context of history movies.

Reply on news.ycombinator.com