Sharpening Hyperspectral Images Using Plug-and-Play Priors

详细信息    查看全文

• 关键词：Data fusion ; Hyperspectral imaging ; Multispectral imaging ; Latent variables ; Plug ; and ; play ; Gaussian mixtures
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10169
• 期：1
• 页码：392-402
• 丛书名：Latent Variable Analysis and Signal Separation
• ISBN：978-3-319-53547-0
• 卷排序：10169

文摘

This paper addresses the problem of fusing hyperspectral (HS) images of low spatial resolution and multispectral (MS) images of high spatial resolution into images of high spatial and spectral resolution. By assuming that the target image lives in a low dimensional subspace, the problem is formulated with respect to the latent representation coefficients. Our major contributions are: (i) using patch-based spatial priors, learned from the MS image, for the latent images of coefficients; (ii) exploiting the so-called plug-and-play approach, wherein a state-of-the-art denoiser is plugged into the iterations of a variable splitting algorithm.