# Efficient and Accurate Hyperspectral Image Demosaicing with Neural Network Architectures

arXiv: https://arxiv.org/abs/2403.12050 · HTML: https://mlsanity.com/paper/2403.12050/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 43 references that are in the map.
- First posted on arXiv 21 Dec 2023.

## Builds on (most cited first, 8 of 8)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Single Image Super-Resolution via a Holistic Attention Network](https://mlsanity.com/paper/2008.08767/) (2020)
- [NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image](https://mlsanity.com/paper/2005.03412/) (2020)
- [Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network](https://mlsanity.com/paper/1707.05425/) (2017)
- [Hyperspectral Image Segmentation: A Preliminary Study on the Oral and Dental Spectral Image Database (ODSI-DB)](https://mlsanity.com/paper/2303.08252/) (2023)
- [Deep demosaicking for multispectral filter arrays](https://mlsanity.com/paper/1808.08021/) (2018)
- [Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning](https://mlsanity.com/paper/2211.15435/) (2022)

## Abstract (arXiv)

Neural network architectures for image demosaicing have been become more and more complex. This results in long training periods of such deep networks and the size of the networks is huge. These two factors prevent practical implementation and usage of the networks in real-time platforms, which generally only have limited resources. This study investigates the effectiveness of neural network architectures in hyperspectral image demosaicing. We introduce a range of network models and modifications, and compare them with classical interpolation methods and existing reference network approaches. The aim is to identify robust and efficient performing network architectures. Our evaluation is conducted on two datasets, "SimpleData" and "SimRealData," representing different degrees of realism in multispectral filter array (MSFA) data. The results indicate that our networks outperform or match reference models in both datasets demonstrating exceptional performance. Notably, our approach focuses on achieving correct spectral reconstruction rather than just visual appeal, and this emphasis is supported by quantitative and qualitative assessments. Furthermore, our findings suggest that efficient demosaicing solutions, which require fewer parameters, are essential for practical applications. This research contributes valuable insights into hyperspectral imaging and its potential applications in various fields, including medical imaging.