English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  A generative model of natural images as patchworks of textures

Bethge, M., Luedtke, N., Das, D., & Theis, L. (2013). A generative model of natural images as patchworks of textures. Poster presented at Computational and Systems Neuroscience Meeting (COSYNE 2013), Salt Lake City, UT, USA.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0001-188A-9 Version Permalink: http://hdl.handle.net/21.11116/0000-0001-5783-9
Genre: Poster

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Bethge, Matthias1, 2, Author              
Luedtke, N, Author
Das, Debapriya, Author              
Theis, Lucas, Author              
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Natural images can be viewed as patchworks of different textures, where the local image statistics is roughly sta- tionary within a small neighborhood but otherwise varies from region to region. In order to model this variability, we first applied the parametric texture algorithm of Portilla and Simoncelli to image patches of 64x64 pixels in a large database of natural images such that each image patch is then described by 655 texture parameters which specify certain statistics, such as variances and covariances of wavelet coefficients or coefficient magnitudes within that patch. To model the statistics of these texture parameters, we then developed suitable nonlinear transformations of the parameters that allowed us to fit their joint statistics with a multivariate Gaussian distribution. We find that the first 200 principal components contain more than 99% of the variance and are sufficient to generate textures that are perceptually extremely close to those generated with all 655 components. We demonstrate the usefulness of the model in several ways: (1) We sample ensembles of texture patches that can be directly compared to samples of patches from the natural image database and can to a high degree reproduce their perceptual appearance. (2) We further developed an image compression algorithm which generates surprisingly accurate images at bit rates as low as 0.14 bits/pixel. Finally, (3) We demonstrate how our approach can be used for an efficient and objective evaluation of samples generated with probabilistic models of natural images.

Details

show
hide
Language(s):
 Dates: 2013-03
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Computational and Systems Neuroscience Meeting (COSYNE 2013)
Place of Event: Salt Lake City, UT, USA
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computational and Systems Neuroscience Meeting (COSYNE 2013)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: I-9 Start / End Page: 50 Identifier: -