Poster
PixelCNN Models with Auxiliary Variables for Natural Image Modeling
Alexander Kolesnikov · Christoph H. Lampert

Mon Aug 7th 06:30 -- 10:00 PM @ Gallery #2

We study probabilistic models of natural images and extend the autoregressive family of PixelCNN models by incorporating auxiliary variables. Subsequently, we describe two new generative image models that exploit different image transformations as auxiliary variables: a quantized grayscale view of the image or a multi-resolution image pyramid. The proposed models tackle two known shortcomings of existing PixelCNN models: 1) their tendency to focus on low-level image details, while largely ignoring high-level image information, such as object shapes, and 2) their computationally costly procedure for image sampling. We experimentally demonstrate benefits of our models, in particular showing that they produce much more realistically looking image samples than previous state-of-the-art probabilistic models.

Author Information

Alexander Kolesnikov (IST Austria)
Christoph H. Lampert (IST Austria)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors