Hyperspectral Image Reconstruction Using Multi-scale Fusion Learning

Abstract

Hyperspectral imaging is a promising imaging modality that simultaneously captures several images for the same scene on narrow spectral bands, and it has made considerable progress in different fields, such as agriculture, astronomy, and surveillance. However, the existing hyperspectral (HS) cameras sacrifice the spatial resolution for providing the detail spectral distribution of the imaged scene, which leads to low-resolution (LR) HS images compared with the common red-green-blue (RGB) images. Generating a high-resolution HS (HR-HS) image via fusing an observed LR-HS image with the corresponding HR-RGB image has been actively studied. Existing methods for this fusing task generally investigate hand-crafted priors to model the inherent structure of the latent HR-HS image, and they employ optimization approaches for solving it. However, proper priors for different scenes can possibly be diverse, and to figure it out for a specific scene is difficult. This study investigates a deep convolutional neural network (DCNN)-based method for automatic prior learning, and it proposes a novel fusion DCNN model with multi-scale spatial and spectral learning for effectively merging an HR-RGB and LR-HS images. Specifically, we construct an U-shape network architecture for gradually reducing the feature sizes of the HR-RGB image (Encoder-side) and increasing the feature sizes of the LR-HS image (Decoder-side), and we fuse the HR spatial structure and the detail spectral attribute in multiple scales for tackling the large resolution difference in spatial domain of the observed HR-RGB and LR-HS images. Then, we employ multi-level cost functions for the proposed multi-scale learning network to alleviate the gradient vanish problem in long-propagation procedure. In addition, for further improving the reconstruction performance of the HR-HS image, we refine the predicted HR-HS image using an alternating back-projection method for minimizing the reconstruction errors of the observed LR-HS and HR-RGB images. Experiments on three benchmark HS image datasets demonstrate the superiority of the proposed method in both quantitative values and visual qualities.