A Style-Based Generator Architecture for Generative Adversarial Networks
No Thumbnail Available
Date
2018-12-05
Journal Title
Journal ISSN
Volume Title
Publisher
arXiv
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.
Description
StyleGAN은 고해상도 얼굴 이미지 생성을 위한 스타일 기반 GAN 구조를 제시하여 디테일 제어와 잠재 공간 분리성에서 우수한 성능을 보여줍니다 ©2018 NVIDIA
Keywords
StyleGAN, GAN, Image Generation, Computer Vision, Neural Networks