Loading [MathJax]/extensions/MathMenu.js
Dynamical Fusion Model With Joint Variational and Deep Priors for Hyperspectral Image Super-Resolution | IEEE Journals & Magazine | IEEE Xplore

Dynamical Fusion Model With Joint Variational and Deep Priors for Hyperspectral Image Super-Resolution


Abstract:

In this letter, we propose a novel dynamic fusion model (DFM) with joint variational and deep priors for the task of hyperspectral image super-resolution (HISR). The give...Show More

Abstract:

In this letter, we propose a novel dynamic fusion model (DFM) with joint variational and deep priors for the task of hyperspectral image super-resolution (HISR). The given model can benefit from both the advantages of traditional modeling and deep learning (DL) methods, thus achieving significant improvements based on existing deep pretrained models. Specifically, the given model mainly contains two newly designed terms, i.e., the weighted spatial fidelity (WSF) term and the deep fusion (DF) term. The WSF term focuses on the spatial recovery of the low-resolution hyperspectral image (LR-HSI) through the high-resolution multispectral image (HR-MSI) without the knowledge of the spectral response matrix, thus the proposed DFM can be viewed as a semi-blind model for HISR. Moreover, the DF term relied upon DF with a designed adaptive weight matrix, which can effectively inject the deep priors into the traditional minimization model. Besides, the proposed DFM can be quickly and effectively solved using the alternating direction method of multipliers (ADMM). Experimental results on widely used datasets demonstrate the superiority of our approach compared with state-of-the-art HISR methods.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)
Article Sequence Number: 5506205
Date of Publication: 20 June 2023

ISSN Information:

Funding Agency:


References

References is not available for this document.