Inverse problem regularization with hierarchical variational autoencoders - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Inverse problem regularization with hierarchical variational autoencoders

Résumé

In this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the advantages of i) denoiser-based Plug \& Play approaches and ii) generative model based approaches to inverse problems. First, we exploit VAE properties to design an efficient algorithm that benefits from convergence guarantees of Plug-and-Play (PnP) methods. Second, our approach is not restricted to specialized datasets and the proposed PnP-HVAE model is able to solve image restoration problems on natural images of any size. Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.

Dates et versions

hal-04038644 , version 1 (21-03-2023)

Identifiants

Citer

Jean Prost, Antoine Houdard, Andres Almansa, Nicolas Papadakis. Inverse problem regularization with hierarchical variational autoencoders. IEEE International Conference on Computer Vision (ICCV'23), Oct 2023, Paris, France. ⟨hal-04038644⟩
58 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More