Structured Uncertainty in the Observation Space of Variational Autoencoders. (arXiv:2205.12533v2 [cs.LG] UPDATED)

Variational autoencoders (VAEs) are a popular class of deep generative models
with many variants and a wide range of applications. Improvements upon the
standard VAE mostly focus on the modelling of the posterior distribution over
the latent space and the properties of the neural network decoder. In contrast,
improving the model for the observational distribution is rarely considered and
typically defaults to a pixel-wise independent categorical or normal
distribution. In image synthesis, sampling from such distributions produces
spatially-incoherent results with …

arxiv observation space uncertainty variational autoencoders