Compressive Hyperspectral Imaging with Side Information

TL;DR

This paper introduces a blind compressive sensing method for hyperspectral imaging that leverages side information from RGB images to enhance reconstruction quality, demonstrated through a prototype camera and experiments.

Contribution

It presents a novel in situ dictionary learning algorithm for hyperspectral reconstruction that incorporates RGB side information to improve accuracy.

Findings

Successful reconstruction of hyperspectral datacubes from simulated and real measurements

Demonstrated the feasibility of a prototype hyperspectral camera using this method

Showed that side information significantly enhances reconstruction quality

Abstract

A blind compressive sensing algorithm is proposed to reconstruct hyperspectral images from spectrally-compressed measurements.The wavelength-dependent data are coded and then superposed, mapping the three-dimensional hyperspectral datacube to a two-dimensional image. The inversion algorithm learns a dictionary {\em in situ} from the measurements via global-local shrinkage priors. By using RGB images as side information of the compressive sensing system, the proposed approach is extended to learn a coupled dictionary from the joint dataset of the compressed measurements and the corresponding RGB images, to improve reconstruction quality. A prototype camera is built using a liquid-crystal-on-silicon modulator. Experimental reconstructions of hyperspectral datacubes from both simulated and real compressed measurements demonstrate the efficacy of the proposed inversion algorithm, the feasibility of the camera and the benefit of side information.