Shortwave-infrared(SWIR) spectral information,ranging from 1 {\mu}m to 2.5{\mu}m, breaks the limitations of traditional color cameras in acquiring scene information and has been used in many fields. However, conventional SWIR hyperspectral imaging systems face challenges due to their bulky setups and low acquisition speed. In this work, we introduce 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 systemhas the advantages of small size and snapshot imaging. We propose a novel inter and intra prior learning unfolding framework proposed to achieve high-quality SWIR hyperspectral image reconstruction, which bridges the gap between prior learning and cross-stage information interaction. We also design an adaptive feature transfer mechanism to adaptively the transfer contextual correlation of multi-scale encoder features to prevent detailed information loss in the decoder. Experiment results demonstrate that our method can reconstruct HSI with high speed and superior performance over existing methods.

翻译：短波红外（SWIR）光谱信息（范围从1微米至2.5微米）突破了传统彩色相机获取场景信息的局限，已在众多领域得到应用。然而，传统的短波红外高光谱成像系统因其庞大的设备配置和较低的采集速度而面临挑战。本研究提出了一种基于超表面滤波器的快照式短波红外高光谱成像系统，并设计了一种相应的滤波器选择方法，以实现滤波器间最低相关系数。该系统具有体积小巧和快照成像的优势。我们提出了一种新颖的融合内部与外部先验学习的展开式重建框架，以实现高质量的短波红外高光谱图像重建，该框架弥合了先验学习与跨阶段信息交互之间的鸿沟。同时，我们设计了一种自适应特征传递机制，以自适应地传递多尺度编码器特征的上下文关联，防止解码过程中的细节信息丢失。实验结果表明，与现有方法相比，本方法能够以更快的速度重建高光谱图像，并展现出更优越的性能。