Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Herbreteau, Sébastien, Kervrann, Charles
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917734766346240
author Herbreteau, Sébastien
Kervrann, Charles
author_facet Herbreteau, Sébastien
Kervrann, Charles
contents We propose a unified view of unsupervised non-local methods for image denoising that linearily combine noisy image patches. The best methods, established in different modeling and estimation frameworks, are two-step algorithms. Leveraging Stein's unbiased risk estimate (SURE) for the first step and the "internal adaptation", a concept borrowed from deep learning theory, for the second one, we show that our NL-Ridge approach enables to reconcile several patch aggregation methods for image denoising. In the second step, our closed-form aggregation weights are computed through multivariate Ridge regressions. Experiments on artificially noisy images demonstrate that NL-Ridge may outperform well established state-of-the-art unsupervised denoisers such as BM3D and NL-Bayes, as well as recent unsupervised deep learning methods, while being simpler conceptually.
format Preprint
id arxiv_https___arxiv_org_abs_2203_00570
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
Herbreteau, Sébastien
Kervrann, Charles
Image and Video Processing
Computer Vision and Pattern Recognition
We propose a unified view of unsupervised non-local methods for image denoising that linearily combine noisy image patches. The best methods, established in different modeling and estimation frameworks, are two-step algorithms. Leveraging Stein's unbiased risk estimate (SURE) for the first step and the "internal adaptation", a concept borrowed from deep learning theory, for the second one, we show that our NL-Ridge approach enables to reconcile several patch aggregation methods for image denoising. In the second step, our closed-form aggregation weights are computed through multivariate Ridge regressions. Experiments on artificially noisy images demonstrate that NL-Ridge may outperform well established state-of-the-art unsupervised denoisers such as BM3D and NL-Bayes, as well as recent unsupervised deep learning methods, while being simpler conceptually.
title Towards a unified view of unsupervised non-local methods for image denoising: the NL-Ridge approach
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2203.00570