Hyperspectral Superresolution Reconstruction via Decomposition of Low-Rank and Sparse Tensor

Hyperspectral superresolution reconstruction technique obtains a high-resolution hyperspectral image (HR-HSI) by fusing both a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image. Existing methods of hyperspectral superresolution reconstruction are mostly concentrated on the global low-rank property while spatial and spectral information in individual regions is not considered. To address this issue, the decomposition of low-rank and sparse tensor is proposed in this study. First, HR-HSI was decomposed into low-rank and sparse components. The former was further separated into spatial and spectral domains according to the spectral low-rank property, and the latter was used to compensate for information loss caused by the low-rank property. Then, a nonlocal constraint of adaptive manifold extracting structural details by the manifold structure was designed to enforce nonlocal self-similarity of the spatial domain. In order to ensure the same spatial structure of different bands and reduce the false individual regions in the sparse component, a surface-aware regularization combined with group sparsity was utilized. Finally, HR-HSI was constructed by the alternating direction method of multipliers. Experiment results on three datasets show that the proposed method outperforms five common existing methods by means of both visual and quantitative evaluations. It is concluded that the new method by taking into account the low-rank and sparse properties can improve the result of the reconstruction.