Self-distilled StyleGAN: Towards Generation From Internet Photos
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
This session WILL NOT be recorded.
TimeThursday, 11 August 20229:42am - 9:47am PDT
LocationEast Building, Room 1-3
DescriptionWe adapt StyleGAN to work on raw, uncurated internet photos, resulting in high-quality image synthesis. Our self-distillation approach consists of two components: a generative-based, self-filtering of the dataset to eliminate outlier images and perceptual clustering of the generated images to detect inherent data modalities used to improve StyleGAN's "truncation trick".