A Fast Alternating Minimization Algorithm for Coded Aperture Snapshot Spectral Imaging Based on Sparsity and Deep Image Priors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Qile, Zhao, Xianhong, Ma, Xu, Chen, Xudong, Arce, Gonzalo R.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916455148158976
author Zhao, Qile
Zhao, Xianhong
Ma, Xu
Chen, Xudong
Arce, Gonzalo R.
author_facet Zhao, Qile
Zhao, Xianhong
Ma, Xu
Chen, Xudong
Arce, Gonzalo R.
contents Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) from one or several two-dimensional projection measurements. However, fewer projection measurements or more spectral channels leads to a severly ill-posed problem, in which case regularization methods have to be applied. In order to significantly improve the accuracy of reconstruction, this paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors (Fama-SDIP) of natural images. By integrating deep image prior (DIP) into the principle of compressive sensing (CS) reconstruction, the proposed algorithm can achieve state-of-the-art results without any training dataset. Extensive experiments show that Fama-SDIP method significantly outperforms prevailing leading methods on simulation and real HSI datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2206_05647
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle A Fast Alternating Minimization Algorithm for Coded Aperture Snapshot Spectral Imaging Based on Sparsity and Deep Image Priors
Zhao, Qile
Zhao, Xianhong
Ma, Xu
Chen, Xudong
Arce, Gonzalo R.
Image and Video Processing
Computer Vision and Pattern Recognition
Optics
Coded aperture snapshot spectral imaging (CASSI) is a technique used to reconstruct three-dimensional hyperspectral images (HSIs) from one or several two-dimensional projection measurements. However, fewer projection measurements or more spectral channels leads to a severly ill-posed problem, in which case regularization methods have to be applied. In order to significantly improve the accuracy of reconstruction, this paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors (Fama-SDIP) of natural images. By integrating deep image prior (DIP) into the principle of compressive sensing (CS) reconstruction, the proposed algorithm can achieve state-of-the-art results without any training dataset. Extensive experiments show that Fama-SDIP method significantly outperforms prevailing leading methods on simulation and real HSI datasets.
title A Fast Alternating Minimization Algorithm for Coded Aperture Snapshot Spectral Imaging Based on Sparsity and Deep Image Priors
topic Image and Video Processing
Computer Vision and Pattern Recognition
Optics
url https://arxiv.org/abs/2206.05647