GEOMETRIC LOW-RANK TENSOR APPROXIMATION FOR REMOTELY SENSED HYPERSPECTRAL AND MULTISPECTRAL IMAGERY FUSION

Improving the spatial resolution of a hyperspectral image (HSI) is of great significance in the remotely sensed field. By fusing a high-spatial-resolution multispectral image (MSI) with an HSI collected from the same scene, hyperspectral and multispectral (HS-MS) fusion has been an emerging technique to address the issue. Extracting complex spatial information from MSIs while maintaining abundant spectral information of HSIs is essential to generate the fused high-spatial-resolution HSI (HS²I). A common way is to learn low-rank/sparse representations from HSI and MSI, then reconstruct the fused HS²I based on tensor/matrix decomposition or unmixing paradigms, which ignore the intrinsic geometry proximity inherited by the low-rank property of the fused HS²I. This study proposes to estimate the high-resolution HS²I via low-rank tensor approximation with geometry proximity as side information learned from MSI and HSI by defined graph signals, which we name GLRTA. Row graph G_r and column graph G_c are defined on the horizontal slice and lateral slice of MSI tensor M respectively, while spectral band graph G_b is defined on a frontal slice of HSI tensor H. Experimental results demonstrate that the proposed GLRTA can effectively improve the reconstruction results compared to other competitive works.