Unified GAN for Image-to-Image translation

Re:Unified GAN for Image-to-Image translation by Cyberdog on Wednesday November 29, 2017 @06:55PM (#15812060)

Well, this is horrifying. Thank you. Now everyone that has one photo of me to match against now has several of them.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by candiodari on Wednesday November 29, 2017 @11:29PM (#15813477)

The article doesn't point this out, but in GANs, the parameters actually move on a continuous range. In other words, they don't just have several of your pictures, they've got all sorts of movies :

A movie where your face starts out "neutral" and becomes angry. A movie where you start out angry, go to surprised and end happy. And so on.

Excellent progress, I must say.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by visarga on Thursday November 30, 2017 @03:11AM (#15814163)

> they've got all sorts of movies

Here it is: one glorious hour of walk through the latent space of faces. You can "feel" the geometry of the latent space and its meanderings. https://www.youtube.com/watch?v=36lE9tV9vm0

Generated with Progressive GAN in high resolution. The quality is mind blowing, highest ever attained in any GAN. Author: NVIDIA

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by CGamesPlay on Wednesday November 29, 2017 @07:40PM (#15812304)

Well, no, you can't create information that doesn't exist. They don't have any better source to match against your blonde-hair picture than their imagination. The novelty here is that they may outsource that imagination to the machine now.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by nerdponx on Wednesday November 29, 2017 @07:42PM (#15812325)

Is this useful for simulated celebrity and fanfiction porn yet? Would be very interested in that PoC.

[ Parent | on HN ]