Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery

Abstract

Recently, single gray/RGB image super-resolution reconstruction task has been extensively studied and made significant progress by leveraging the advanced machine learning techniques based on deep convolutional neural networks (DCNNs). However, there has been limited technical development focusing on single hyperspectral image super-resolution due to the high-dimensional and complex spectral patterns in hyperspectral image. In this paper, we make a step forward by investigating how to adapt state-of-the-art residual learning based single gray/RGB image super-resolution approaches for computationally efficient single hyperspectral image super-resolution, referred as SSPSR. Specifically, we introduce a spatial-spectral prior network (SSPN) to fully exploit the spatial information and the correlation between the spectra of the hyperspectral data. Considering that the hyperspectral training samples are scarce and the spectral dimension of hyperspectral image data is very high, it is nontrivial to train a stable and effective deep network. Therefore, a group convolution (with shared network parameters) and progressive upsampling framework is proposed. This will not only alleviate the difficulty in feature extraction due to high-dimension of the hyperspectral data, but also make the training process more stable. To exploit the spatial and spectral prior, we design a spatial-spectral block (SSB), which consists of a spatial residual module and a spectral attention residual module. Experimental results on some hyperspectral images demonstrate that the proposed SSPSR method enhances the details of the recovered high-resolution hyperspectral images, and outperforms state-of-the-arts. The source code is available at \url{https://github.com/junjun-jiang/SSPSR

arXiv commentAccepted for publication at IEEE Transactions on Computational Imaging

References in corpus (2)

• Deep Image Prior
• SIRF: Simultaneous Image Registration and Fusion in A Unified Framework

Cited by in corpus (7)

• Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
• Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution
• Deep Plug-and-Play Prior for Hyperspectral Image Restoration
• A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution
• Deep Posterior Distribution-based Embedding for Hyperspectral Image Super-resolution
• Unaligned RGB Guided Hyperspectral Image Super-Resolution with Spatial-Spectral Concordance
• SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising