Karras and colleagues: progressive growing of GANs

What changed

Trained GAN generators and discriminators by progressively increasing resolution, improving training stability and high-resolution image generation.

Scientific scope

Trained GAN generators and discriminators by progressively increasing resolution, improving training stability and high-resolution image generation. Scope limitation: The ICLR 2018 method paper is distinct from later StyleGAN architectures; its benchmark and dataset refinements stay within the same package.

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 ICLR 2018 method paper is distinct from later StyleGAN architectures; its benchmark and dataset refinements stay within the same package.

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: progressive growing of GANs — original paper
• Karras and colleagues: progressive growing of GANs — official company source

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