HD snapshot diffractive spectral imaging and inferencing

TL;DR

This paper introduces a high-definition snapshot diffractive spectral imaging system that captures and reconstructs spectral data from a single image, enabling high-resolution spectral imaging across various applications with advantages like optical compression and flexible spectral basis selection.

Contribution

The paper presents a novel diffractive filter array-based spectral imaging system capable of snapshot capture and computational reconstruction, offering high spectral resolution and versatility over traditional methods.

Findings

Achieves 25 spectral channels at 30-50 nm resolution

Demonstrates accurate spectral reconstruction compared to ground truth

Validates applications in biological, food, and astronomical imaging

Abstract

We present a novel high-definition (HD) snapshot diffractive spectral imaging system utilizing a diffractive filter array (DFA) to capture a single image that encodes both spatial and spectral information. This single diffractogram can be computationally reconstructed into a spectral image cube, providing a high-resolution representation of the scene across 25 spectral channels in the 440-800 nm range at 1304x744 spatial pixels (~1 MP). This unique approach offers numerous advantages including snapshot capture, a form of optical compression, flexible offline reconstruction, the ability to select the spectral basis after capture, and high light throughput due to the absence of lossy filters. We demonstrate a 30-50 nm spectral resolution and compared our reconstructed spectra against ground truth obtained by conventional spectrometers. Proof-of-concept experiments in diverse applications including biological tissue classification, food quality assessment, and simulated stellar photometry validate our system's capability to perform robust and accurate inference. These results establish the DFA-based imaging system as a versatile and powerful tool for advancing scientific and industrial imaging applications.