Dual camera snapshot hyperspectral imaging system via physics informed learning
This addresses the challenge of snapshot hyperspectral imaging for applications like remote sensing or medical imaging by enabling adaptation to real-life scenarios without ground truth, though it is incremental as it builds on existing CNN methods.
The paper tackles the problem of reconstructing hyperspectral images from compressed dual-camera snapshots by proposing a self-supervised, physics-informed CNN framework that avoids reliance on ground truth data, achieving good performance across varied imaging environments without training.
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.