Progressive Spatial-Spectral Joint Network for Hyperspectral Image Reconstruction

Hyperspectral (HS) images are widely used to identify and characterize objects in a scene of interest with high acquisition costs and low spatial resolution. It is an inexpensive way to obtain high-spatial-resolution HS images (HSIs) by spectral reconstruction from high-spatial-resolution multispectral (MS) images. In this article, we proposed a progressive spatial-spectral joint network (PSJN) to reconstruct HSIs from MS images. PSJN is composed of a 2-D spatial feature extraction module, a 3-D progressive spatial-spectral feature construction module, and a spectral postprocessing module. PSJN makes full use of the shallow spatial features extracted by the 2-D spatial feature extraction module with the spatial-spectral features extracted by the 3-D progressive spatial-spectral feature construction module. The 3-D progressive spatial-spectral feature construction module is designed to extract spatial-spectral information from local spectra in local space and construct spectral information from a few bands to a lot of bands in a pyramidal structure. Besides, a network updating mechanism is proposed to improve the spectral reconstruction effect of the images with poor original spectral reconstruction effect. The experimental results on three HS-MS datasets and one MS dataset demonstrate the efficacy of the proposed methods. Compared with the most advanced spectral reconstruction methods based on dictionary learning and deep learning, our method achieves the best performance of the latest methods in similarity evaluation and classification performance evaluation.