A Style-Based Generator Architecture for Generative Adversarial Networks

Paper (PDF): Authors: Tero Karras (NVIDIA) Samuli Laine (NVIDIA) Timo Aila (NVIDIA) 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, scal