A Style-Based Generator Architecture for Generative Adversarial Networks

@article{Karras2019ASG,
  title={A Style-Based Generator Architecture for Generative Adversarial Networks},
  author={Tero Karras and S. Laine and Timo Aila},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={4396-4405}
}
  • Tero Karras, S. Laine, Timo Aila
  • Published 2019
  • Computer Science, Mathematics
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 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
    1,323 Citations

    Figures, Tables, and Topics from this paper.

    Unsupervised K-modal styled content generation
    • 1
    • Highly Influenced
    • PDF
    Unsupervised multi-modal Styled Content Generation
    • 2
    • Highly Influenced
    Unsupervised Controllable Generation with Self-Training
    Self-Attention Generative Adversarial Networks
    • 1,006
    • PDF
    Autoencoding Generative Adversarial Networks
    LoGANv2: Conditional Style-Based Logo Generation with Generative Adversarial Networks
    SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
    • 1
    • Highly Influenced
    • PDF
    One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
    Style Generator Inversion for Image Enhancement and Animation
    • 9
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 68 REFERENCES
    Self-Attention Generative Adversarial Networks
    • 1,006
    • PDF
    Generative Multi-Adversarial Networks
    • 180
    • PDF
    On Self Modulation for Generative Adversarial Networks
    • 40
    • PDF
    Online Adaptative Curriculum Learning for GANs
    • 14
    • PDF
    Progressive Growing of GANs for Improved Quality, Stability, and Variation
    • 2,246
    • PDF
    Improved Training of Wasserstein GANs
    • 3,560
    • Highly Influential
    • PDF
    Adversarial Feature Learning
    • 956
    • PDF
    Improved Techniques for Training GANs
    • 3,768
    • PDF