# Class-specific image denoising using importance sampling

## TL;DR

This paper introduces a class-specific image denoising method based on importance sampling, which effectively approximates Bayesian MMSE estimates and outperforms existing methods on face and text images.

## Contribution

It presents a novel importance sampling framework for class-specific denoising, allowing flexible priors and noise models, with convergence guarantees to true MMSE estimates.

## Key findings

- Outperforms state-of-the-art denoisers on face images
- Effective for text image denoising
- Converges to true MMSE estimates with increasing samples

## Abstract

In this paper, we propose a new image denoising method, tailored to specific classes of images, assuming that a dataset of clean images of the same class is available. Similarly to the non-local means (NLM) algorithm, the proposed method computes a weighted average of non-local patches, which we interpret under the importance sampling framework. This viewpoint introduces flexibility regarding the adopted priors, the noise statistics, and the computation of Bayesian estimates. The importance sampling viewpoint is exploited to approximate the minimum mean squared error (MMSE) patch estimates, using the true underlying prior on image patches. The estimates thus obtained converge to the true MMSE estimates, as the number of samples approaches infinity. Experimental results provide evidence that the proposed denoiser outperforms the state-of-the-art in the specific classes of face and text images.