Dual camera snapshot hyperspectral imaging system via physics informed learning

TL;DR

This paper introduces a self-supervised, physics-informed CNN framework for dual-camera hyperspectral imaging that adapts to real-world conditions without training, enabling robust reconstruction of 3D hyperspectral images.

Contribution

It proposes a novel untrained, physics-informed CNN approach for hyperspectral imaging, overcoming limitations of supervised methods that require ground truth data.

Findings

Method performs well in diverse imaging environments.

System can be fine-tuned and self-improved in real-time.

Achieves accurate hyperspectral reconstruction without training data.

Abstract

We consider using the system's optical imaging process with convolutional neural networks (CNNs) to solve the snapshot hyperspectral imaging reconstruction problem, which uses a dual-camera system to capture the three-dimensional hyperspectral images (HSIs) in a compressed way. Various methods using CNNs have been developed in recent years to reconstruct HSIs, but most of the supervised deep learning methods aimed to fit a brute-force mapping relationship between the captured compressed image and standard HSIs. Thus, the learned mapping would be invalid when the observation data deviate from the training data. Especially, we usually don't have ground truth in real-life scenarios. In this paper, we present a self-supervised dual-camera equipment with an untrained physics-informed CNNs framework. Extensive simulation and experimental results show that our method without training can be adapted to a wide imaging environment with good performance. Furthermore, compared with the training-based methods, our system can be constantly fine-tuned and self-improved in real-life scenarios.