Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Deliang, Chen, Peng, Xu, Haobo, Yao, Jiale, Li, Fang, Zeng, Tieyong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911218050007040
author Wei, Deliang
Chen, Peng
Xu, Haobo
Yao, Jiale
Li, Fang
Zeng, Tieyong
author_facet Wei, Deliang
Chen, Peng
Xu, Haobo
Yao, Jiale
Li, Fang
Zeng, Tieyong
contents Plug-and-play (PnP) methods with deep denoisers have shown impressive results in imaging problems. They typically require strong convexity or smoothness of the fidelity term and a (residual) non-expansive denoiser for convergence. These assumptions, however, are violated in Poisson inverse problems, and non-expansiveness can hinder denoising performance. To address these challenges, we propose a cocoercive conservative (CoCo) denoiser, which may be (residual) expansive, leading to improved denoising. By leveraging the generalized Helmholtz decomposition, we introduce a novel training strategy that combines Hamiltonian regularization to promote conservativeness and spectral regularization to ensure cocoerciveness. We prove that CoCo denoiser is a proximal operator of a weakly convex function, enabling a restoration model with an implicit weakly convex prior. The global convergence of PnP methods to a stationary point of this restoration model is established. Extensive experimental results demonstrate that our approach outperforms closely related methods in both visual quality and quantitative metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08909
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problems
Wei, Deliang
Chen, Peng
Xu, Haobo
Yao, Jiale
Li, Fang
Zeng, Tieyong
Computer Vision and Pattern Recognition
Machine Learning
Functional Analysis
Optimization and Control
94A08, 47H10, 47J26, 46N10, 47N10
Plug-and-play (PnP) methods with deep denoisers have shown impressive results in imaging problems. They typically require strong convexity or smoothness of the fidelity term and a (residual) non-expansive denoiser for convergence. These assumptions, however, are violated in Poisson inverse problems, and non-expansiveness can hinder denoising performance. To address these challenges, we propose a cocoercive conservative (CoCo) denoiser, which may be (residual) expansive, leading to improved denoising. By leveraging the generalized Helmholtz decomposition, we introduce a novel training strategy that combines Hamiltonian regularization to promote conservativeness and spectral regularization to ensure cocoerciveness. We prove that CoCo denoiser is a proximal operator of a weakly convex function, enabling a restoration model with an implicit weakly convex prior. The global convergence of PnP methods to a stationary point of this restoration model is established. Extensive experimental results demonstrate that our approach outperforms closely related methods in both visual quality and quantitative metrics.
title Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problems
topic Computer Vision and Pattern Recognition
Machine Learning
Functional Analysis
Optimization and Control
94A08, 47H10, 47J26, 46N10, 47N10
url https://arxiv.org/abs/2505.08909