Re:DensePose: Dense Human Pose Estimation in the Wild
by macawfish on Friday February 02, 2018 @04:51PM
(#16294490)
Question: how far away is this from a "person swapping" GAN video synthesis kind of application?
[ Parent
| on HN ]
Re:DensePose: Dense Human Pose Estimation in the Wild
by tziki on Friday February 02, 2018 @11:38PM
(#16296211)
I think that's a really good question. IMO this is an essential part of any pipeline aiming to do that, but there's a bunch of hurdles with neural networks that's haven't been crossed yet. The first one that comes to mind is that I'm not aware of any work which would try to teach neural networks to imagine what someone would look like from different angles (aside from relatively restricted settings like facial frontalization). Second, you talk of videos. That means the person needs to look 'consistent' from frame to frame. This isn't a solved problem either, especially when it comes to GANs. I'm sure there are a few other areas that need to be solved.
Re:DensePose: Dense Human Pose Estimation in the Wild
by TaylorAlexander on Friday February 02, 2018 @07:30PM
(#16295375)
I’m not sure if you’ve seen the face swapping that was making the rounds recently, but I was thinking this makes whole body swapping look closer.
Re:DensePose: Dense Human Pose Estimation in the Wild
by mattbierner on Friday February 02, 2018 @10:17PM
(#16295944)
If you thought face swapping was bad, just wait until someone uses this tech to create AR goggles that let the wearer see everyone “naked”, like having Superman X-ray vision
Re:DensePose: Dense Human Pose Estimation in the Wild
by gumby on Friday February 02, 2018 @10:39PM
(#16296020)
If the software is at all accurate, using that kind of AR google on me should result in retinal scarring.
Re:DensePose: Dense Human Pose Estimation in the Wild
by rakenrainbow on Friday February 02, 2018 @11:08PM
(#16296110)
Why would that be 'bad'? If someone finds joy in seeing all people naked, go for it.
Re:DensePose: Dense Human Pose Estimation in the Wild
by macawfish on Friday February 02, 2018 @08:13PM
(#16295535)
That's exactly what I had in mind, but I'm no expert. And just wait until they've got basic, fluid object recognition down. I've already seen some impressive, old work on coherent in-painting of images.
It seems like all these deep learning discoveries are relatively composable too.