Rate-Optimal Denoising with Deep Neural Networks

DOI10.1093/IMAIAI/IAAA011arXiv1805.08855MaRDI QIDQ6301959FDOQ6301959

Authors: Reinhard Heckel, Wen Huang, Paul E. Hand, Vladislav Voroninski 

Publication date: 22 May 2018

Abstract: Deep neural networks provide state-of-the-art performance for image denoising, where the goal is to recover a near noise-free image from a noisy observation. The underlying principle is that neural networks trained on large datasets have empirically been shown to be able to generate natural images well from a low-dimensional latent representation of the image. Given such a generator network, a noisy image can be denoised by i) finding the closest image in the range of the generator or by ii) passing it through an encoder-generator architecture (known as an autoencoder). However, there is little theory to justify this success, let alone to predict the denoising performance as a function of the network parameters. In this paper we consider the problem of denoising an image from additive Gaussian noise using the two generator based approaches. In both cases, we assume the image is well described by a deep neural network with ReLU activations functions, mapping a $k$-dimensional code to an $n$-dimensional image. In the case of the autoencoder, we show that the feedforward network reduces noise energy by a factor of $O(k/n)$. In the case of optimizing over the range of a generative model, we state and analyze a simple gradient algorithm that minimizes a non-convex loss function, and provably reduces noise energy by a factor of $O(k/n)$. We also demonstrate in numerical experiments that this denoising performance is, indeed, achieved by generative priors learned from data.

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

This page was built for publication: Rate-Optimal Denoising with Deep Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6301959)