Skip to content

Latest commit

 

History

History
45 lines (32 loc) · 2.96 KB

README.md

File metadata and controls

45 lines (32 loc) · 2.96 KB

StyleGANv1 (CVPR'2019)

A Style-Based Generator Architecture for Generative Adversarial Networks

Task: Unconditional GANs

Abstract

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature. The new architecture leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images (e.g., freckles, hair), and it enables intuitive, scale-specific control of the synthesis. The new generator improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. 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.

Results and Models

Results (compressed) from StyleGANv1 trained by mmediting
Model Dataset FID50k P&R50k_full Download
styleganv1_ffhq_256 FFHQ 6.090 70.228/27.050 model
styleganv1_ffhq_1024 FFHQ 4.056 70.302/36.869 model

Citation

@inproceedings{karras2019style,
  title={A style-based generator architecture for generative adversarial networks},
  author={Karras, Tero and Laine, Samuli and Aila, Timo},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4401--4410},
  year={2019},
  url={https://openaccess.thecvf.com/content_CVPR_2019/html/Karras_A_Style-Based_Generator_Architecture_for_Generative_Adversarial_Networks_CVPR_2019_paper.html},
}