DeepAI AI Chat
Log In Sign Up

Analyzing and Improving the Image Quality of StyleGAN

12/03/2019
by   Tero Karras, et al.
37

The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent vectors to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably detect if an image is generated by a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

READ FULL TEXT

page 4

page 8

page 11

page 12

page 13

page 14

page 15

page 19

12/06/2021

Tunable Image Quality Control of 3-D Ultrasound using Switchable CycleGAN

In contrast to 2-D ultrasound (US) for uniaxial plane imaging, a 3-D US ...
10/27/2017

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

We describe a new training methodology for generative adversarial networ...
02/01/2022

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Computer graphics has experienced a recent surge of data-centric approac...
06/13/2021

Styleformer: Transformer based Generative Adversarial Networks with Style Vector

We propose Styleformer, which is a style-based generator for GAN archite...
09/04/2021

Fast Image-Anomaly Mitigation for Autonomous Mobile Robots

Camera anomalies like rain or dust can severelydegrade image quality and...
04/02/2022

StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

In this paper we introduce StyleWaveGAN, a style-based drum sound genera...
08/12/2019

Deep Tone Mapping Operator for High Dynamic Range Images

A computationally fast tone mapping operator (TMO) that can quickly adap...

Code Repositories

stylegan2-pytorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement


view repo

stylegan2-pytorch

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch


view repo

StyleGAN2-Tensorflow-2.0

StyleGAN 2 in Tensorflow 2.0


view repo

StyleGAN2-TensorFlow-2.x

Unofficial implementation of StyleGAN2 using TensorFlow 2.x.


view repo