Rate-optimal denoising with deep neural networks
Information and Inference: A Journal of the IMA · 2021
DOI: 10.1093/imaiai/iaaa011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information and Inference: A Journal of the IMA, 2021. Verfasst von Reinhard Heckel und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: NSF, NSF CAREER.
Abstract (Originalsprache)
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 data sets 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.
Förderung
- NSF
- NSF CAREER
Zitieren
APA
Heckel, R., Huang, W., Hand, P., & Voroninski, V. (2021). Rate-optimal denoising with deep neural networks. Information and Inference: A Journal of the IMA. https://doi.org/10.1093/imaiai/iaaa011
Vancouver
Heckel R, Huang W, Hand P, Voroninski V. Rate-optimal denoising with deep neural networks. Information and Inference: A Journal of the IMA. 2021. doi:10.1093/imaiai/iaaa011
BibTeX
@article{Heckel2021,
author = {Heckel, Reinhard and Huang, Wen and Hand, Paul and Voroninski, Vladislav},
title = {Rate-optimal denoising with deep neural networks},
journal = {Information and Inference: A Journal of the IMA},
year = {2021},
doi = {10.1093/imaiai/iaaa011}
}
EUVIMED