Inter and Intra Prior Learning-based Hyperspectral Image Reconstruction Using Snapshot SWIR Metasurface

TL;DR

This paper presents a compact snapshot SWIR hyperspectral imaging system using a metasurface filter and a novel prior learning framework for high-quality image reconstruction, outperforming existing methods in speed and accuracy.

Contribution

It introduces a new inter and intra prior learning unfolding framework combined with an adaptive feature transfer mechanism for improved hyperspectral image reconstruction.

Findings

Achieves high-speed hyperspectral image reconstruction.

Demonstrates superior performance over existing methods.

Provides a compact snapshot imaging system.

Abstract

Shortwave-infrared(SWIR) spectral information, ranging from 1 {\mu}m to 2.5{\mu}m, overcomes the limitations of traditional color cameras in acquiring scene information. However, conventional SWIR hyperspectral imaging systems face challenges due to their bulky setups and low acquisition speeds. This work introduces a snapshot SWIR hyperspectral imaging system based on a metasurface filter and a corresponding filter selection method to achieve the lowest correlation coefficient among these filters. This system offers the advantages of compact size and snapshot imaging. We propose a novel inter and intra prior learning unfolding framework to achieve high-quality SWIR hyperspectral image reconstruction, which bridges the gap between prior learning and cross-stage information interaction. Additionally, We design an adaptive feature transfer mechanism to adaptively transfer the contextual correlation of multi-scale encoder features to prevent detailed information loss in the decoder. Experiment results demonstrate that our method can reconstruct hyperspectral images with high speed and superior performance over existing methods.