Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

Résumé

Plug-and-Play (PnP) methods are efficient iterative algorithms for solving ill-posed image inverse problems. PnP methods are obtained by using deep Gaussian denoisers instead of the proximal operator or the gradient-descent step within proximal algorithms. Current PnP schemes rely on data-fidelity terms that have either Lipschitz gradients or closed-form proximal operators, which is not applicable to Poisson inverse problems. Based on the observation that the Gaussian noise is not the adequate noise model in this setting, we propose to generalize PnP using theBregman Proximal Gradient (BPG) method. BPG replaces the Euclidean distance with a Bregman divergence that can better capture the smoothness properties of the problem. We introduce the Bregman Score Denoiser specifically parametrized and trained for the new Bregman geometry and prove that it corresponds to the proximal operator of a nonconvex potential. We propose two PnP algorithms based on the Bregman Score Denoiser for solving Poisson inverse problems. Extending the convergence results of BPG in the nonconvex settings, we show that the proposed methods converge, targeting stationary points of an explicit global functional. Experimental evaluations conducted on various Poisson inverse problems validate the convergence results and showcase effective restoration performance.

Dates et versions

hal-04121529 , version 1 (07-06-2023)

Identifiants

Citer

Samuel Hurault, Ulugbek Kamilov, Arthur Leclaire, Nicolas Papadakis. Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems. Neural Information Processing Systems (NeurIPS'23), Dec 2023, New Orleans, United States. ⟨hal-04121529⟩
57 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More