Deep Self-Supervised Hyperspectral Image Reconstruction

Abstract

Reconstructing a high-resolution hyperspectral (HR-HS) image via merging a low-resolution hyperspectral (LR-HS) image and a high-resolution RGB (HR-RGB) image has become a hot research topic, and can greatly benefit for different subsequent high-level vision tasks. Recently, deep learning–based approaches have evolved for HS image reconstruction and validated impressive performance. However, to learn a good reconstruction model in the deep learning–based methods, it is mandatory to previously collect large-scale training triplets consisting of the LR-HS, HR-RGB, and HR-HS images, which is difficult to be collected in real applications. This study proposes a deep self-supervised HS image reconstruction framework (DSSH), which does not have to depend on any handcrafted prior and previously collected training triplets at all. The proposed DSSH method leverages the designed network architecture itself for capturing the prior of the underlying structure in the latent HR-HS image and employs the observed LR-HS and HR-RGB images only for network parameter learning. Experiments on two benchmark HS image datasets validated that the proposed DSSH method manifests very impressive reconstruction performance, and is even better than some state-of-the-art supervised learning approaches.