Abstract
Low-Rank Tensor Optimization With Nonlocal Plug-and-Play Regularizers for Snapshot Compressive Imaging
Highlights
H YPERSPECTRAL images (HSIs) are naturally thirdorder tensors consisting of 1D spectral and 2D spatial information
The parameters involved in generalized alternating projection based total variation (GapTV) and NGMeet are tuned to the best performance, and the parameters involved in the decompressed SCI (DeSCI) are set following the suggestion of the source codes
We use the mean of peak signal-to-noise ratio (PSNR) (MPSNR) values of all bands, the mean of structural similarity index measure (SSIM) (MSSIM) values of all bands, and spectral angle mapper (SAM) to objectively evaluate the reconstructed results of simulated experiments
Summary
H YPERSPECTRAL images (HSIs) are naturally thirdorder tensors consisting of 1D spectral and 2D spatial information. For the high-resolution spectral information of HSIs, they have been widely employed in many fields, such as resource detection [1], target recognition [2], and environmental monitoring [3]. With promising applications is snapshot compressive imaging (SCI) [15]–[18]. The SCI system samples a set of contiguous channels (e.g., coded aperture compressive spectral imaging (CASSI) [19]) to obtain 2D compressed measurements, greatly reducing the computational workload. To reconstruct HSIs from 2D measurements, various methods have been proposed. These methods can be divided into two categories: (1) deep learning-based methods; (2) model-based methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
