Image denoising with multi-layer perceptrons, part 1: comparison with existing algorithms and with bounds

TL;DR

This paper demonstrates that multi-layer perceptrons trained on large image datasets can outperform existing denoising algorithms and approach theoretical bounds, effectively handling various noise types.

Contribution

It introduces a novel application of MLPs for image denoising, surpassing current methods and approaching theoretical performance limits.

Findings

MLPs outperform state-of-the-art denoising algorithms.

MLPs achieve results close to theoretical bounds.

Effective on various noise types including mixed Poisson-Gaussian and JPEG artifacts.

Abstract

Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with cleverly engineered algorithms. In this work we attempt to learn this mapping directly with plain multi layer perceptrons (MLP) applied to image patches. We will show that by training on large image databases we are able to outperform the current state-of-the-art image denoising methods. In addition, our method achieves results that are superior to one type of theoretical bound and goes a large way toward closing the gap with a second type of theoretical bound. Our approach is easily adapted to less extensively studied types of noise, such as mixed Poisson-Gaussian noise, JPEG artifacts, salt-and-pepper noise and noise resembling stripes, for which we achieve excellent results as well. We will show that combining a block-matching procedure with MLPs can further improve the results on certain images. In a second paper, we detail the training trade-offs and the inner mechanisms of our MLPs.