Pré-Publication, Document De Travail Année : 2025

From the Gradient-Step Denoiser to the Proximal Denoiser and their associated convergent Plug-and-Play algorithms

Résumé

In this paper we analyze the Gradient-Step Denoiser and its usage in Plug-and-Play algorithms. The Plug-and-Play paradigm of optimization algorithms uses off the shelf denoisers to replace a proximity operator or a gradient descent operator of an image prior. Usually this image prior is implicit and cannot be expressed, but the Gradient-Step Denoiser is trained to be exactly the gradient descent operator or the proximity operator of an explicit functional while preserving state-of-the-art denoising capabilities.

Dates et versions

hal-05261818 , version 1 (15-09-2025)

Identifiants

Citer

Vincent Herfeld, Baudouin Denis de Senneville, Arthur Leclaire, Nicolas Papadakis. From the Gradient-Step Denoiser to the Proximal Denoiser and their associated convergent Plug-and-Play algorithms. 2025. ⟨hal-05261818⟩
83 Consultations
0 Téléchargements

Altmetric

Partager

  • More