IVCVMay 29, 2020

Hyperspectral Image Super-resolution via Deep Spatio-spectral Convolutional Neural Networks

arXiv:2005.14400v12 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a domain-specific issue for hyperspectral imaging applications, offering incremental improvements in super-resolution.

The authors tackled the problem of low spatial resolution in hyperspectral images by proposing a deep convolutional neural network architecture that fuses low-resolution hyperspectral and high-resolution multispectral images to produce high-resolution hyperspectral images, achieving state-of-the-art performance in experiments.

Hyperspectral images are of crucial importance in order to better understand features of different materials. To reach this goal, they leverage on a high number of spectral bands. However, this interesting characteristic is often paid by a reduced spatial resolution compared with traditional multispectral image systems. In order to alleviate this issue, in this work, we propose a simple and efficient architecture for deep convolutional neural networks to fuse a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI), yielding a high-resolution hyperspectral image (HR-HSI). The network is designed to preserve both spatial and spectral information thanks to an architecture from two folds: one is to utilize the HR-HSI at a different scale to get an output with a satisfied spectral preservation; another one is to apply concepts of multi-resolution analysis to extract high-frequency information, aiming to output high quality spatial details. Finally, a plain mean squared error loss function is used to measure the performance during the training. Extensive experiments demonstrate that the proposed network architecture achieves best performance (both qualitatively and quantitatively) compared with recent state-of-the-art hyperspectral image super-resolution approaches. Moreover, other significant advantages can be pointed out by the use of the proposed approach, such as, a better network generalization ability, a limited computational burden, and a robustness with respect to the number of training samples.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes