AS³ITransUNet: Spatial-Spectral Interactive Transformer U-Net With Alternating Sampling for Hyperspectral Image Super-Resolution

Single hyperspectral image (HSI) super-resolution (SR) is an important topic in the remote-sensing field. However, existing HSI SR methods mainly use the feed-forward upsampling technique and convolutional neural network (CNN) to learn the feature representation, failing to learn the complex mapping relationship between low-resolution (LR) and high-resolution (HR) and long-range joint spectral and spatial features. To address this issue, in this article, we propose the spatial-spectral interactive transformer U-Net with alternating sampling (AS(3)ITransUNet) for the HSI SR task. In this method, to mitigate the computational burden resulting from the high spectral dimension of the HSI, a group reconstruction strategy is adopted. To effectively explore the hierarchical features of the HSI, the U-Net with alternating upsampling and downsampling is designed that allocates the task of learning the complex mapping relationship to each stage of the U-Net. To fully extract the spatial-spectral features of the HSI, we propose the spatial-spectral interactive transformer (SSIT) block and integrate it into the encoder and the decoder of U-Net. The SSIT block contains a cross-branch bidirectional interaction module, which further captures the complementary information between spatial and spectral dimensions. Moreover, multistage complementary information learning (MSCIL) is proposed to capture the complementary information in the adjacent HSI groups for recovering the absent details in the current HSI group. The experiments on the three benchmark datasets demonstrate that the proposed AS(3)ITransUNet can effectively improve the spatial resolution and preserve the spectral information at different scales. Models and codes are available at https://github.com/liushiji666/AS3-ITransUNet.