Adaptive Wiener denoising using a Gaussian scale mixture model in the wavelet domain

Abstract
Standard to decompose images with multi-scale band-pass oriented filters. These representations have been shown to decouple some high-order statistical features of natural im- ages. In this paper, we describe a stochastic model for lo- cal neighborhoods of coefficients of such a representation, in which the parameters are governed by a hidden random field. Specifically, local neighborhood of coefficients are modeled as the product of a Gaussian random vector and a hidden multiplier variable. We describe an efficient de- noising method based on this model, and demonstrate the strength of the approach through numerical experiments.

This publication has 9 references indexed in Scilit: