Exploiting local detail in single image super-resolution via hypergraph convolution

Exploiting both local detail features and global correlation information in low-resolution (LR) images is vital for single-image super-resolution (SISR) reconstruction. Current deep CNN methods often overlook the interaction of local details while focusing on global features, rendering them incapable of accommodating both global and local features of LR images, therefore compromising the reconstruction performance. To address this, we propose a hypergraph convolution super-resolution (HCSR) network, which integrates local detail feature information and global correlation information. Hypergraph convolution is innovatively incorporated into SISR tasks, facilitating the modeling of complex spatial relationships among local features. We devise an incidence matrix for hypergraph convolution and propose a spatial feature interaction module (SFIM) for enriched local texture detail. We also use multi-hyperplane locally sensitive hash for efficient non-local hash attention (NLHA), optimally extracting correlations among global features. Based on this, a feature forward module (FFM) is developed that integrates global dependencies of multi-level features, improving the overall image detail recovery. Evaluated across five benchmark datasets, the proposed demonstrates substantial performance in both quantitative metrics and visual appeal.