Cool as hell. Is this flexible enough that it could realistically be applied to generic selfies and not just these very uniform photos? Make this into an app and you could have the next Prisma!
You mean FaceApp?
Unified GAN for Image-to-Image translation
11–20 of 22 posts
Re: Unified GAN for Image-to-Image translation
#12racial bias in computer vision strikes again!
Re: Unified GAN for Image-to-Image translation
#13In 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.
Re: Unified GAN for Image-to-Image translation
#14Well, this is horrifying. Thank you. Now everyone that has one photo of me to match against now has several of them.
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.
> 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
Re: Unified GAN for Image-to-Image translation
#15In 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.
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?
Re: Unified GAN for Image-to-Image translation
#16I think this (or something like this) can be used as a way to transmit a video chat on a very low bandwidth (think tens of bytes/second) level.
Re: Unified GAN for Image-to-Image translation
#17I think this (or something like this) can be used as a way to transmit a video chat on a very low bandwidth (think tens of bytes/second) level.
You're talking about an animated avatar that just happens to be of an actual person? And only in 2D?
Re: Unified GAN for Image-to-Image translation
#18Re: Unified GAN for Image-to-Image translation
#19In 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.
I wish researchers showed a random mix of results, not just their best results ...
Re: Unified GAN for Image-to-Image translation
#20I think this (or something like this) can be used as a way to transmit a video chat on a very low bandwidth (think tens of bytes/second) level.
You're talking about an animated avatar that just happens to be of an actual person? And only in 2D?
For a start, yes. A proof of pricinple would be nice. Would probably look very shitty, but would use very little bandwidth.
I read about a fictional system like this in "A fire upon the deep" by Vernor Vinge a long time ago but never thought it would be feasible. There a scene of an entire room of people interacting was being deconstructed/reconstructed for a video chat using low bandwidth.