Tuning-Free Plug-and-Play Hyperspectral Image Deconvolution With Deep Priors - Archive ouverte HAL
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2023

Tuning-Free Plug-and-Play Hyperspectral Image Deconvolution With Deep Priors

Xiuheng Wang
Jie Chen
Cédric Richard

Résumé

Deconvolution is a widely used strategy to mitigate the blurring and noisy degradation of hyperspectral images (HSIs) generated by the acquisition devices. This issue is usually addressed by solving an ill-posed inverse problem. While investigating proper image priors can enhance the deconvolution performance, it is not trivial to handcraft a powerful regularizer and to set the regularization parameters. To address these issues, in this article, we introduce a tuning-free plug-and-play (PnP) algorithm for HSI deconvolution. Specifically, we use the alternating direction method of multipliers (ADMM) to decompose the optimization problem into two iterative subproblems. A flexible blind 3-D denoising network (B3DDN) is designed to learn deep priors and to solve the denoising subproblem with different noise levels. A measure of 3-D residual whiteness is then investigated to adjust the penalty parameters when solving the quadratic subproblems, as well as a stopping criterion. Experimental results on both simulated and real-world data with ground truth demonstrate the superiority of the proposed method.
Fichier principal
Vignette du fichier
wang2022tuning.pdf (8 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04242318 , version 1 (14-10-2023)

Identifiants

Citer

Xiuheng Wang, Jie Chen, Cédric Richard. Tuning-Free Plug-and-Play Hyperspectral Image Deconvolution With Deep Priors. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61, pp.1-13. ⟨10.1109/TGRS.2023.3253549⟩. ⟨hal-04242318⟩
30 Consultations
27 Téléchargements

Altmetric

Partager

More