A Style-Based Generator Architecture for Generative Adversarial Networks
Tero Karras, Samuli Laine, Timo Aila
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 12,595 citationsOpen access
No retraction on record in OpenAlex.Check Crossref now
Cite this paper
Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(12), 4217–4228. https://doi.org/10.1109/tpami.2020.2970919
In text: (Karras et al., 2019)
Ask a question about this research
One question, free, no account. Anchorcite finds the papers, checks each against Crossref and links every sentence of the answer to the passage it comes from.
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.
Related papers
Metadata from OpenAlex (CC0). Citations are generated from the published record.