DeepAI AI Chat
Log In Sign Up

Analyzing and Improving the Image Quality of StyleGAN

by   Tero Karras, et al.

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.


page 4

page 8

page 11

page 12

page 13

page 14

page 15

page 19


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 ...

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

We describe a new training methodology for generative adversarial networ...

StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets

Computer graphics has experienced a recent surge of data-centric approac...

Styleformer: Transformer based Generative Adversarial Networks with Style Vector

We propose Styleformer, which is a style-based generator for GAN archite...

Fast Image-Anomaly Mitigation for Autonomous Mobile Robots

Camera anomalies like rain or dust can severelydegrade image quality and...

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...

Deep Tone Mapping Operator for High Dynamic Range Images

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

Code Repositories


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

view repo


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

view repo


StyleGAN 2 in Tensorflow 2.0

view repo


Unofficial implementation of StyleGAN2 using TensorFlow 2.x.

view repo