no code implementations • 2 Nov 2023 • Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis
The stepsize condition for nonconvex convergence of the proximal algorithm in use then translates to restrictive conditions on the regularization parameter of the inverse problem.
1 code implementation • 31 Jan 2023 • Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis
This paper presents a new convergent Plug-and-Play (PnP) algorithm.
no code implementations • 4 May 2022 • Coloma Ballester, Aurelie Bugeau, Samuel Hurault, Simone Parisotto, Patricia Vitoria
In this work, we focus on learning-based image completion methods for multiple and diverse inpainting which goal is to provide a set of distinct solutions for a given damaged image.
1 code implementation • 31 Jan 2022 • Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Given this new result, we exploit the convergence theory of proximal algorithms in the nonconvex setting to obtain convergence results for PnP-PGD (Proximal Gradient Descent) and PnP-ADMM (Alternating Direction Method of Multipliers).
1 code implementation • ICLR 2022 • Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Exploiting convergence results for proximal gradient descent algorithms in the non-convex setting, we show that the proposed Plug-and-Play algorithm is a convergent iterative scheme that targets stationary points of an explicit global functional.
1 code implementation • 20 Nov 2020 • Samuel Hurault, Coloma Ballester, Gloria Haro
In a soccer game, the information provided by detecting and tracking brings crucial clues to further analyze and understand some tactical aspects of the game, including individual and team actions.