Image Synthesis Applications

Thumbnail Image
Ntavelis, Evangelos
Shahbazi, Mohamad
Luongo, Francesca
Kastanis, Iason
Timofte, Radu
Danelljan, Martin
Van Gool, Luc
Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales. However, these approaches are either limited to a set of discrete scales or struggle to maintain good perceptual quality at the scales for which the model is not trained explicitly. We propose the design of scale-consistent positional encodings invariant to our generator's layers transformations. This enables the generation of arbitrary-scale images even at scales unseen during training. Moreover, we incorporate novel inter-scale augmentations into our pipeline and partial generation training to facilitate the synthesis of consistent images at arbitrary scales. Lastly, we show competitive results for a continuum of scales on various commonly used datasets for image synthesis
Publication Reference
Ntavelis et al, Image Synthesis Applications, DataDays 2022, Zurich