A Style-Based Generator Architecture for Generative Adversarial Networks

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 Paper (PDF): http://stylegan.xyz/paper

• #فناوری_و_رایانه
• #generative_adversarial_networks
• #deep_learning
• #nvidia