AWhat changed
Introduced a style-based GAN generator architecture with scale-specific synthesis control and measured improvements in interpolation and disentanglement on face-image generation.
Scientific scope
Introduced a style-based GAN generator architecture with scale-specific synthesis control and measured improvements in interpolation and disentanglement on face-image generation. Scope limitation: The arXiv preprint appeared in December 2018; this record uses the CVPR 2019 publication year. Findings are tied to the paper's models, data and metrics, not all image synthesis.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. The arXiv preprint appeared in December 2018; this record uses the CVPR 2019 publication year. Findings are tied to the paper's models, data and metrics, not all image synthesis.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Karras and colleagues: StyleGAN style-based generator architecture — original paper
- Karras and colleagues: StyleGAN style-based generator architecture — company research page
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction