Generative Modelling in Latent Space
(sander.ai)
Most contemporary generative models of images, sound and video do not operate directly on pixels or waveforms. They consist of two stages: first, a compact, higher-level latent representation is extracted, and then an iterative generative process operates on this representation instead. How does this work, and why is this approach so popular?
Most contemporary generative models of images, sound and video do not operate directly on pixels or waveforms. They consist of two stages: first, a compact, higher-level latent representation is extracted, and then an iterative generative process operates on this representation instead. How does this work, and why is this approach so popular?