Pixel Recursive Super Resolution

Re:Pixel Recursive Super Resolution by throwaway287391 on Monday February 06, 2017 @04:38PM (#13584363)

I hate to be a debbie downer but the results don't look particularly great to me. For comparison, see "AffGAN" [1] and "LAPGAN" [2] for better (IMO) super-resolution results using GAN-like techniques. Granted, all three papers are applied in somewhat different settings (different input/output resolutions, different datasets), so direct comparison is difficult.

[1] https://openreview.net/pdf?id=S1RP6GLle

[2] https://arxiv.org/abs/1506.05751

[ Parent | on HN ]

Re:Pixel Recursive Super Resolution by pmoriarty on Monday February 06, 2017 @07:35PM (#13585827)

Are there any turnkey, easy to use software packages that use LAPGAN or AffGAN for image enhancement? Or are these techniques purely in the research realm at this point?

[ Parent | on HN ]

Re:Pixel Recursive Super Resolution by ygra on Tuesday February 07, 2017 @03:18AM (#13587932)

Does research always have to yield a result that's better than any other approach? In my understanding it's worthwhile to pursue different ways of approaching a problem even if some of them don't work as well as others (but you don't know that beforehand).

[ Parent | on HN ]

Re:Pixel Recursive Super Resolution by aHeng on Tuesday February 07, 2017 @05:36AM (#13588464)

Basically, this is a survial law in the academic jungle even if depressing.

[ Parent | on HN ]

Re:Pixel Recursive Super Resolution by dnautics on Tuesday February 07, 2017 @02:24AM (#13587756)

You're not the only one who feels this way; I wasn't very impressed by the adversarial-network synthesized moving GIFs, that everyone went crazy over a few months ago, either.

[ Parent | on HN ]