Analyzing and Improving the Image Quality of StyleGAN: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

T. Karras, Samuli Laine, M. Aittala, J. Hellsten, J. Lehtinen, T. Aila

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

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 the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes 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 attribute a generated image to 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.
Original languageEnglish
Title of host publicationIEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
Pages8107-8116
Number of pages10
DOIs
Publication statusPublished - 2020
MoE publication typeA4 Article in a conference publication
EventIEEE Conference on Computer Vision and Pattern Recognition - Virtual, Online
Duration: 13 Jun 202019 Jun 2020

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE
ISSN (Print)1063-6919
ISSN (Electronic)2332-564X

Conference

ConferenceIEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR
CityVirtual, Online
Period13/06/202019/06/2020

Keywords

  • data visualisation
  • image coding
  • image resolution
  • neural net architecture
  • unsupervised learning
  • StyleGAN architecture
  • data-driven unconditional generative image modeling
  • generator normalization
  • unconditional image modeling
  • distribution quality metrics
  • perceived image quality
  • style-based GAN architecture
  • Generators
  • Training
  • Image resolution
  • Modulation
  • Convolution
  • Measurement
  • Standards

Fingerprint Dive into the research topics of 'Analyzing and Improving the Image Quality of StyleGAN: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)'. Together they form a unique fingerprint.

Cite this