Image denoising using scale mixtures of Gaussians in the wavelet domain

J Portilla, V Strela, M J Wainwright, and E P Simoncelli

Published in IEEE Trans Image Processing, vol.12(11), pp. 1338--1351, Nov 2003.
© IEEE Signal Processing Society

Recipient of a 2008 IEEE Signal Processing Society Best Paper Award.

DOI: 10.1109/TIP.2003.818640

Download:

  • Reprint (pdf)
  • Description, software & test images
    • We describe a method for removing noise from digital images, based on a statistical model of the coefficients of an overcomplete multi-scale oriented basis. Neighborhoods of coefficients at adjacent positions and scales are modeled as the product of two independent random variables: a Gaussian vector and a hidden positive scalar multiplier. The latter modulates the local variance of the coefficients in the neighborhood, and is thus able to account for the empirically observed correlation between the coefficient amplitudes. Under this model, the Bayesian least squares estimate of each coefficient reduces to a weighted average of the local linear estimate over all possible values of the hidden multiplier variable. We demonstrate through simulations with images contaminated by additive white Gaussian noise that the performance of this method substantially surpasses that of previously published methods, both visually and in terms of mean squared error.
    Related:
  • Image modeling and denoising with random fields of GSMs: PAMI-08Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures
    by S Lyu and E P Simoncelli
  • Image restoration using GSMs: icip-03Image restoration using Gaussian scale mixtures in the wavelet domain
    by J Portilla and E P Simoncelli
  • Original technical report version (Sep 2002): TR-02Image Denoising using Gaussian Scale Mixtures in the Wavelet Domain
    by J Portilla, V Strela, M J Wainwright, and E P Simoncelli
  • Initial conference publication of denoising using GSMs: icip-01Adaptive Wiener Denoising Using a Gaussian Scale Mixture Model in the Wavelet Domain
    by J Portilla, V Strela, M J Wainwright, and E P Simoncelli
  • Initial publication of GSMs as a model for images: nips-99Scale Mixtures of Gaussians and the Statistics of Natural Images
    by M J Wainwright and E P Simoncelli
  • Earlier publication on contextual denoising using local variance prediction: Vidakovic-chapter-99Bayesian Denoising of Visual Images in the Wavelet Domain
    by E P Simoncelli
  • Smooth shrinkage as Bayesian least squares estimation: icip-96Noise Removal via Bayesian Wavelet Coring
    by E P Simoncelli and E H Adelson
  • Online Publications