Neighbor Spectra Maintenance and Context Affinity Enhancement for Single Hyperspectral Image Super-Resolution

Single hyperspectral image super-resolution aims to improve the spatial resolution of a hyperspectral image without relying on auxiliary information. By taking advantage of the high similarity among neighbor bands, some recent methods have employed a recursive structure to super-resolve a hyperspectral image band-by-band. They are usually memory-efficient and perform well. However, they tend to introduce feedback information without distinction so as to weaken the utilization of complementary information in the context. Additionally, the spectral structure is inevitably destroyed when spatial information is extracted from neighbor bands, which hampers the effective exploration of spectral information in the subsequent process. To this end, we propose a two-stage network based on neighbor spectra maintenance and context affinity enhancement, which is composed of two sub-networks: neighbor network and context network. The former utilizes several neighbor bands to generate the neighbor spatial-spectral feature, incorporating a parallel processing scheme designed to reduce spectral distortion. Then we construct a relationship representation between the neighbor feature and feedback context information in the context network. By referring to the representation, the contents with higher complementarity will be highlighted in this stage. Experimental results on five public hyperspectral image datasets demonstrate that the proposed network not only outperforms state-of-the-art methods in terms of spatial reconstruction accuracy and spectral fidelity, but also requires less memory usage.