Transcription of A Style-Based Generator Architecture for Generative ...
{{id}} {{{paragraph}}}
Example: confidence
A Style-Based Generator Architecture for Generative ...
A Style-Based Generator Architecture for Generative Adversarial NetworksTero propose an alternative Generator Architecture for gen-erative adversarial networks, borrowing from style transferliterature. The new Architecture leads to an automaticallylearned, unsupervised separation of high-level attributes( , pose and identity when trained on human faces) andstochastic variation in the generated images ( , freckles,hair), and it enables intuitive, scale-specific control of thesynthesis. The new Generator improves the state-of-the-artin terms of traditional distribution quality metrics, leads todemonstrably better interpolation properties, and also bet-ter disentangles the latent factors of variation. To quantifyinterpolation quality and disentanglement, we propose twonew, automated methods that are applicable to any genera-tor Architecture . Finally, we introduce a new, highly variedand high-quality dataset of human IntroductionThe resolution and quality of images produced by gener-ative methods especially Generative adversarial networks(GAN) [21] have seen rapid improvement recently [28,41,4].
Method Pathlength Separa-full end bility b Traditionalgenerator Z 412.0 415.3 10.78 d Style-basedgeneratorW 446.2 376.6 3.61 e +Addnoiseinputs W 200.5 160.6 3.54
Loading..
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: