Cross-Guided Pyramid Attention-Based Residual Hyperdense Network for Hyperspectral Image Pansharpening

Hyperspectral (HS) image pansharpening is of great importance in improving the spatial resolution for many commercial platforms and remote sensing tasks. Convolutional neural network (CNN) has recently been applied in pansharpening. However, most existing CNN-based pansharpening models followed an early-fusion/late-fusion strategy, which integrates the low-level/high-level features of panchromatic (PAN) and HS streams at the input-output of the network. It is difficult to learn more complex combinations between PAN and HS streams. This article proposes a novel end-to-end residual hyperdense pansharpening network with a cross-guided pyramid attention (called RHDcgpaNet). The overall architecture of the proposed method is a residual hyperdense network, which extends the definition of dense connections to two-stream pansharpening problem. The proposed RHDcgpaNet allows guidance from the state of the preceding layers to all the layers in- between PAN and HS streams in a feed-forward manner, significantly increasing the learning representation. A cross-guided pyramid attention is designed and embedded to the proposed residual hyperdense network to yield more useful spatial–spectral feature transfer in network. Extensive experiments on widely used datasets demonstrate that the proposed RHDcgpaNet achieves favorable performance in comparison to the state-of-the-art methods.