# Metasurface-empowered snapshot hyperspectral imaging with convex/deep (CODE) small-data learning theory

## TL;DR

This paper introduces a compact hyperspectral imager using metasurfaces and small-data deep learning to enable high-fidelity imaging with minimal training data.

## Contribution

The novel integration of multi-resonant metasurfaces with the CODE small-data learning theory for compact hyperspectral imaging.

## Key findings

- A single multi-wavelength metasurface chip reduces the device area significantly.
- The CODE-driven system generates an 18-band hyperspectral data cube using only 18 training data points.
- The system achieves high fidelity in hyperspectral imaging within the visible window (500-650 nm).

## Abstract

Hyperspectral imaging is vital for material identification but traditional systems are bulky, hindering the development of compact systems. While previous metasurfaces address volume issues, the requirements of complicated fabrication processes and significant footprint still limit their applications. This work reports a compact snapshot hyperspectral imager by incorporating the meta-optics with a small-data convex/deep (CODE) deep learning theory. Our snapshot hyperspectral imager comprises only one single multi-wavelength metasurface chip working in the visible window (500-650 nm), significantly reducing the device area. To demonstrate the high performance of our hyperspectral imager, a 4-band multispectral imaging dataset is used as the input. Through the CODE-driven imaging system, it efficiently generates an 18-band hyperspectral data cube with high fidelity using only 18 training data points. We expect the elegant integration of multi-resonant metasurfaces with small-data learning theory will enable low-profile advanced instruments for fundamental science studies and real-world applications.

Hyperspectral imagers play a vital role in material identification, but traditionally, they have been bulky. Here, the authors introduce a compact hyperspectral imaging system that combines metasurface optics with small-data deep learning.