A Style-Based Generator Architecture for Generative Adversarial Networks
Paper (PDF):
http://stylegan.xyz/paper
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, 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.
Видео A Style-Based Generator Architecture for Generative Adversarial Networks канала Tero Karras FI
http://stylegan.xyz/paper
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, 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.
Видео A Style-Based Generator Architecture for Generative Adversarial Networks канала Tero Karras FI
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Production-Level Facial Performance Capture Using Deep Convolutional Neural NetworksProgressive Growing of GANs for Improved Quality, Stability, and VariationOne hour of imaginary celebritiesAudio-Driven Facial Animation by Joint End-to-End Learning of Pose and EmotionProgressive Growing of GANs for Improved Quality, Stability, and VariationSpeech and Facial Animation at SIGGRAPH 2017 -- comparison of technical papers