Beyond MMSE: Enhancing PnP Restoration with ProxiMAP

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vert, Kenta, Meanti, Giacomo, Pesme, Scott, Arbel, Michael, Mairal, Julien
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911690300325888
author Vert, Kenta
Meanti, Giacomo
Pesme, Scott
Arbel, Michael
Mairal, Julien
author_facet Vert, Kenta
Meanti, Giacomo
Pesme, Scott
Arbel, Michael
Mairal, Julien
contents Plug-and-Play (PnP) methods have become standard tools for solving imaging inverse problems by replacing the intractable maximum a posteriori (MAP) denoiser with the MMSE one. While this mismatch has been widely treated as unavoidable, recent works have sought to close this gap by targeting the MAP with diffusion-model scores. We show this is problematic in practice: learned scores do not match the true ones, so MAP-targeting iterations converge to cartoon-like images rather than realistic ones, and better results are obtained by stopping short of convergence. We turn this observation into a design principle and introduce ProxiMAP, an iterative MAP approximation whose noise schedule keeps the iterate's residual noise matched to the denoiser's training noise. This keeps the denoiser in-distribution where its score is reliable, and yields implicit early stopping that avoids the failure mode above. ProxiMAP is a modular drop-in replacement for MMSE denoisers in standard PnP algorithms and consistently sharpens reconstructions across deblurring, inpainting, super-resolution, and phase retrieval. Building on the same principle, we propose a hybrid variant that applies ProxiMAP only in the late iterations of PnP, where the denoiser is most reliable -- matching or exceeding the full-replacement variant at a fraction of the cost.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16396
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
Vert, Kenta
Meanti, Giacomo
Pesme, Scott
Arbel, Michael
Mairal, Julien
Computer Vision and Pattern Recognition
Machine Learning
Plug-and-Play (PnP) methods have become standard tools for solving imaging inverse problems by replacing the intractable maximum a posteriori (MAP) denoiser with the MMSE one. While this mismatch has been widely treated as unavoidable, recent works have sought to close this gap by targeting the MAP with diffusion-model scores. We show this is problematic in practice: learned scores do not match the true ones, so MAP-targeting iterations converge to cartoon-like images rather than realistic ones, and better results are obtained by stopping short of convergence. We turn this observation into a design principle and introduce ProxiMAP, an iterative MAP approximation whose noise schedule keeps the iterate's residual noise matched to the denoiser's training noise. This keeps the denoiser in-distribution where its score is reliable, and yields implicit early stopping that avoids the failure mode above. ProxiMAP is a modular drop-in replacement for MMSE denoisers in standard PnP algorithms and consistently sharpens reconstructions across deblurring, inpainting, super-resolution, and phase retrieval. Building on the same principle, we propose a hybrid variant that applies ProxiMAP only in the late iterations of PnP, where the denoiser is most reliable -- matching or exceeding the full-replacement variant at a fraction of the cost.
title Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.16396