PixelCNN models with auxiliary variables for natural image modeling Conference Paper

Author(s): Kolesnikov, Alexander; Lampert, Christoph H
Title: PixelCNN models with auxiliary variables for natural image modeling
Title Series: PMLR
Affiliation IST Austria
Abstract: We study probabilistic models of natural images and extend the autoregressive family of PixelCNN models by incorporating latent variables. Subsequently, we describe two new generative image models that exploit different image transformations as latent 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 LatentPixelCNN models, in particular showing that they produce much more realistically looking image samples than previous state-of-the-art probabilistic models.
Keywords: Computer vision and pattern recognition
Conference Title: ICML: International Conference on Machine Learning
Volume: 70
Conference Dates: August 6 - August 11, 2017
Conference Location: Sydney, Australia
Publisher: Omnipress  
Date Published: 2017-01-01
Start Page: 1905
End Page: 1914
Notes: We thank Tim Salimans for spotting a mistake in our preliminary arXiv manuscript. This work was funded by the European Research Council under the European Unions Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036.
Open access: yes (repository)
IST Austria Authors
  1. Christoph Lampert
    87 Lampert
Related IST Austria Work