no code implementations • 1 Aug 2022 • Antoine Dufour, Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith, Michael Lockyer, Jean-Francois Lalonde
We show, through experiments on the StarGANv2 architecture, that this generalization, albeit conceptually simple, results in significant improvements in the quality of the generated images.
no code implementations • 12 May 2022 • Yohan Poirier-Ginter, Alexandre Lessard, Ryan Smith, Jean-François Lalonde
We show that this allows us to obtain near-perfect image reconstruction without the need for encoders nor for altering the latent space after training.