Computer Generated Faces Using GANs
Events
Subscribe:  iCal  |  Google Calendar
Milwaukee US   17, Jun — 22, Jun
New York US   17, Jun — 20, Jun
St. Petersburg RU   19, Jun — 21, Jun
TBA BR   22, Jun — 24, Jun
Amsterdam NL   25, Jun — 28, Jun
Latest comments

We're using Unity (Quarter Circle Games). I'm happy to give an interview and some of my lighting/PP techniques. You can view out game here: https://store.steampowered.com/app/907500/The_Peterson_Case/

by ZHENG ZENG
2 hours ago

NICE!!!

This is a fan project, like the Lord Inquisitor was. GW has absolutely nothing to do with it!

Computer Generated Faces Using GANs
13 November, 2018
News

Have a look at a rather new training methodology for generative adversarial networks by a team of researchers from Nvidia.

The key idea here is to grow both the generator and discriminator progressively: “starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024²,” states the team.

The team also proposes a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, they described several implementation details that are important for discouraging unhealthy competition between the generator and discriminator.

Finally, they suggest a new metric for evaluating GAN results, both in terms of image quality and variation. 

You can learn more and find the full paper here

Comments

1
Leave a Reply

avatar
1 Comment threads
0 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
1 Comment authors
Ell Recent comment authors
Ell
Guest
Ell

Very old paper

Related articles
Education
Character Art Program
Education
Character Art Program