Hyperspectral imaging

Limitations of hyperspectral imaging from RGB images: An optics-aware analysis

We systematically analyze data-driven spectral reconstruction from RGB images and show that fundamental limitations exist arising from the lack of metamerism and diversity in the existing hyperspectral image datasets.

Large-area fabrication-aware computational diffractive optics computational diffractive optics

We propose a fabrication-aware design pipeline for diffractive optics fabricated by direct-write grayscale lithography followed by nano-imprinting replication

Progressive self-supervised learning for CASSI computational spectral cameras

We propose a self-supervised method tailored for coded aperture snapshot spectral imaging (CASSI).

Limitations of hyperspectral imaging from RGB images: A data perspective

We show that significant limitations exist arising from the lack of diversity in the prevailing hyperspectral image datasets.

A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging

We present a thorough investigation of more than 25 state-of-the-art spectral reconstruction methods.

Compact Snapshot Hyperspectral Imaging with Diffracted Rotation

We propose a snapshot hyperspectral imaging system that employs a diffractive optical element and an end-to-end network.

Hyperspectral light field stereo matching

We describe how scene depth can be extracted using a hyperspectral light field capture (H-LF) system.