1 citations · 1 across the 9 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CV2023
PrivacyGAN: robust generative image privacy
Mariia Zameshina, Marlene Careil, Olivier Teytaud +1
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to…
cs.CV2023★ 1 cited
Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation
Mariia Zameshina, Olivier Teytaud, Laurent Najman
Latent diffusion models excel at producing high-quality images from text. Yet, concerns appear about the lack of diversity in the generated imagery. To tackle this, we introduce Di…