# Dual camera snapshot hyperspectral imaging system via physics informed learning

arXiv: https://arxiv.org/abs/2109.02643 · HTML: https://mlsanity.com/paper/2109.02643/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 36 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 2 of 2)

- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging](https://mlsanity.com/paper/2108.12654/) (2021)

## Built on by (most cited first, 3 of 3)

- [mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics](https://mlsanity.com/paper/2303.16205/) (2023)
- [PCMamba: Physics-Informed Cross-Modal State Space Model for Dual-Camera Compressive Hyperspectral Imaging](https://mlsanity.com/paper/2505.16373/) (2025)
- [DMDC: Dynamic-mask-based dual camera design for snapshot Hyperspectral Imaging](https://mlsanity.com/paper/2308.01541/) (2023)

## Abstract (arXiv)

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.