Institut de Mathématiques de Bordeaux (IMB), Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), Modélisation Mathématique pour l'Oncologie (MONC), Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS)-Institut Bergonié Bordeaux, UNICANCER-UNICANCER-Centre Inria de l'Université de Bordeaux, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), ANR-23-PEIA-0004,PDE-AI,Numerical analysis, optimal control and optimal transport for AI(2023)
Source:
International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'25) ; https://hal.science/hal-04833501 ; International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'25), May 2025, Totnes, Devon, United Kingdom
International audience ; Plug-and-Play methods for image restoration are iterative algorithms that solve a variational problem to restore an image. These algorithms are known to be flexible to changes of degradation and to perform state-of-the-art restoration. Recently, a lot of efforts have been made to explore new algorithms to solve this variational problem based on the Plug-and-Play or REgularization by Denoising (RED) frameworks, such as SNORE that is a converging stochastic gradient descent algorithm. A variant of this algorithm, named SNORE Prox, reaches state-of-the-art performances, especially for inpainting tasks. However, the convergence of SNORE Prox, that can be seen as a stochastic proximal gradient descent, has not been analyzed so far. In this paper, we prove the convergence of SNORE Prox under reasonable non-convex assumptions.
