Progressive Growing of GANs for Improved Quality, Stability, and Variation

10/27/2017
by   Tero Karras, et al.
0

We describe a new training methodology for generative adversarial networks. The key idea 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 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.

READ FULL TEXT

page 18

page 19

page 20

page 21

page 22

page 23

page 24

page 25

research
01/29/2019

PA-GAN: Improving GAN Training by Progressive Augmentation

Training of Generative Adversarial Networks (GANs) is notoriously fragil...
research
05/08/2018

High-resolution medical image synthesis using progressively grown generative adversarial networks

Generative adversarial networks (GANs) are a class of unsupervised machi...
research
10/04/2018

Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs

The extension of image generation to video generation turns out to be a ...
research
12/03/2019

Analyzing and Improving the Image Quality of StyleGAN

The style-based GAN architecture (StyleGAN) yields state-of-the-art resu...
research
06/16/2021

Dynamically Grown Generative Adversarial Networks

Recent work introduced progressive network growing as a promising way to...
research
07/23/2021

Unrealistic Feature Suppression for Generative Adversarial Networks

Due to the unstable nature of minimax game between generator and discrim...
research
09/28/2022

Cyclegan Network for Sheet Metal Welding Drawing Translation

In intelligent manufacturing, the quality of machine translation enginee...

Please sign up or login with your details

Forgot password? Click here to reset