Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Khelifa, Naïl, Sherry, Ferdia, Schönlieb, Carola-Bibiane
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913725481484288
author Khelifa, Naïl
Sherry, Ferdia
Schönlieb, Carola-Bibiane
author_facet Khelifa, Naïl
Sherry, Ferdia
Schönlieb, Carola-Bibiane
contents The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term that incorporates prior knowledge about the underlying image. The iterative framework of Plug-and-Play methods, specifically designed for tackling such inverse problems, achieves state-of-the-art performance by replacing the regularisation with a generic denoiser, which may be parametrised by a neural network architecture. However, these deep learning approaches suffer from a critical limitation: the absence of a control parameter to modulate the regularisation strength, which complicates the design of a convergent regularisation. To address this issue, this work introduces a novel scaling method that explicitly integrates and adjusts the strength of regularisation. The scaling parameter enhances interpretability by reflecting the quality of the denoiser's learning process, and also systematically improves its optimisation. Furthermore, the proposed approach ensures that the resulting family of regularisations is provably stable and convergent.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
Khelifa, Naïl
Sherry, Ferdia
Schönlieb, Carola-Bibiane
Image and Video Processing
Machine Learning
The inherent ill-posed nature of image reconstruction problems, due to limitations in the physical acquisition process, is typically addressed by introducing a regularisation term that incorporates prior knowledge about the underlying image. The iterative framework of Plug-and-Play methods, specifically designed for tackling such inverse problems, achieves state-of-the-art performance by replacing the regularisation with a generic denoiser, which may be parametrised by a neural network architecture. However, these deep learning approaches suffer from a critical limitation: the absence of a control parameter to modulate the regularisation strength, which complicates the design of a convergent regularisation. To address this issue, this work introduces a novel scaling method that explicitly integrates and adjusts the strength of regularisation. The scaling parameter enhances interpretability by reflecting the quality of the denoiser's learning process, and also systematically improves its optimisation. Furthermore, the proposed approach ensures that the resulting family of regularisations is provably stable and convergent.
title Enhanced Denoising and Convergent Regularisation Using Tweedie Scaling
topic Image and Video Processing
Machine Learning
url https://arxiv.org/abs/2503.05956