We propose a self-supervised method tailored for coded aperture snapshot spectral imaging (CASSI).
We show that significant limitations exist arising from the lack of diversity in the prevailing hyperspectral image datasets.
We present a thorough investigation of more than 25 state-of-the-art spectral reconstruction methods.
We propose a snapshot hyperspectral imaging system that employs a diffractive optical element and an end-to-end network.
We describe how scene depth can be extracted using a hyperspectral light field capture (H-LF) system.