Unified GAN for Image-to-Image translation

Re:Unified GAN for Image-to-Image translation by bambax on Thursday November 30, 2017 @02:56AM (#15814112)

In the examples, the source images are very very uniform (Caucasian, young, healthy).

Does this work with other images? Can it age photos of people who are already over 50 for example? Or non-whites? Or children? Etc.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by bitL on Thursday November 30, 2017 @06:56AM (#15815052)

I frankly don't see why it couldn't add more years to 50y. Moreover, it could likely "unage" over 50y to 20y, just by inverse of their aging method. GANs are unbelievably powerful.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by amelius on Thursday November 30, 2017 @04:44AM (#15814581)

I wish researchers showed a random mix of results, not just their best results ...

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by IshKebab on Thursday November 30, 2017 @06:04AM (#15814885)

Some do - they show failure modes.

[ Parent | on HN ]

Re:Unified GAN for Image-to-Image translation by IanCal on Thursday November 30, 2017 @03:18AM (#15814200)

I'd like to see it applied to completely different things, what does it do to animals, a grid, a brick wall, a car, etc.

Is a trained model available anywhere?

[ Parent | on HN ]