PixelVAE: A Latent Variable Model for Natural Images

Understand

Natural image modeling is a landmark challenge of unsupervised learning.

• Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty capturing small details.
• PixelCNN models details very well, but lacks a latent code and is difficult to scale for capturing large structures.
• We present PixelVAE, a VAE model with an autoregressive decoder based on PixelCNN.