A Style-Based Generator Architecture for Generative Adversarial Networks

@article{Karras2018ASG,
  title={A Style-Based Generator Architecture for Generative Adversarial Networks},
  author={Tero Karras and Samuli Laine and Timo Aila},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2018},
  pages={4396-4405}
}
Highlight Information
We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. [...] Key Method To quantify interpolation quality and disentanglement, we propose two new, automated methods that are applicable to any generator architecture. Finally, we introduce a new, highly varied and high-quality dataset of human faces.Expand Abstract

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 429 CITATIONS

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Real or Not Real, that is the Question

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning Feature Extraction for Transfer from Simulation to Reality

  • 2019
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multiple-Identity Image Attacks Against Face-based Identity Verification

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

On the "steerability" of generative adversarial networks

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Prescribed Generative Adversarial Networks

VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2020

CITATION STATISTICS

  • 98 Highly Influenced Citations

  • Averaged 126 Citations per year from 2017 through 2019

  • 3,580% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 57 REFERENCES

Generative Adversarial Networks

VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Large Scale GAN Training for High Fidelity Natural Image Synthesis

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Improved Training of Wasserstein GANs

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Rectifier Nonlinearities Improve Neural Network Acoustic Models

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Disentangling by Factorising

VIEW 2 EXCERPTS