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

TL;DR

This paper introduces NL-Ridge, a unified, unsupervised non-local image denoising method that combines patch aggregation with Ridge regression, outperforming several state-of-the-art methods in experiments.

Contribution

It presents a unified framework for non-local denoising methods using Ridge regression and SURE, simplifying and improving upon existing approaches.

Findings

NL-Ridge outperforms BM3D and NL-Bayes in experiments.

The method is conceptually simpler than recent deep learning approaches.

It effectively unifies various patch aggregation techniques.

Abstract

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.