Fast, Frugal Image Reconstruction with a Dual Disperser Hyperspectral Imager

Recently we demonstrated the reconstruction of a hyperspectral datacube with 110 wavelength bands from 10 camera acquisitions [1] . The implementation of this scheme, similarly to compressed sensing, relies on spatial- spectral correlations within the scene. A digital micro-mirror device (DMD) provides programmable spatial- spectral filtering, and is optimized to improve both the speed and accuracy of the reconstruction. Contrary to widespread approaches based on compressed sensing with a single disperser, our dual disperser architecture, illus- trated in Figure 1a , allows straightforward access the panchromatic image and simpler reconstruction algorithms. In particular, we harnessed the panchromatic image to develop a simple edge-preserving quadratic regularization, which is faster than ℓ 1 regularization and does not assume any sparse basis.