Random cascades of Gaussian scale mixtures and their use in modeling natural images with application to denoising

M. J. Wainwright, E. P. Simoncelli, A. S. Willsky

Research output: Contribution to conferencePaperpeer-review


A semi-parametric class of non-Gaussian multiscale statistical processes defined by random cascades on wavelet trees were developed. It was shown that the models accurately fit both the marginal and joint histograms of wavelet coefficients from natural images. In addition, applications of such models to denoising both 1D signals and natural images were highlighted.

Original languageEnglish (US)
Number of pages4
StatePublished - 2000
EventInternational Conference on Image Processing (ICIP 2000) - Vancouver, BC, Canada
Duration: Sep 10 2000Sep 13 2000


OtherInternational Conference on Image Processing (ICIP 2000)
CityVancouver, BC

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this