Hyperspectral image (HSI) super-resolution (SR) technology has made remarkable progress due to the development of deep learning (DL). However, the technique still faces two challenges, i.e., the imbalance between spectral and spatial information extraction, and the parameter deviation and high computational effort associated with 3-D convolution. In this article, we propose an SR method for remote sensing HSIs based on multidomain spatial information and multiscale spectral information fusion (MSSR). Specifically, inspired by the high degree of self-similarity of remote sensing HSIs, a spatial–spectral attention module based on dilated convolution (DSSA) for capturing global spatial information is proposed. The extraction of local spatial information is then accomplished by residual blocks using small-size convolution kernels. Meanwhile, we propose the 3-D inception module to efficiently mine multiscale spectral information. The module only retains the scale of the 3-D convolution kernel in spectral dimension, which greatly reduces the high computational cost caused by 3-D convolution. Comparative experimental results on four benchmark datasets demonstrate that compared with the current cutting-edge models, our method achieves state-of-the-art (SOTA) results and the model computation is greatly reduced.

中文翻译：

---

基于多域空间信息和多尺度光谱信息融合的遥感高光谱图像超分辨率

由于深度学习（DL）的发展，高光谱图像（HSI）超分辨率（SR）技术取得了显着的进步。然而，该技术仍然面临两个挑战，即光谱和空间信息提取之间的不平衡，以及与3D卷积相关的参数偏差和高计算量。在本文中，我们提出了一种基于多域空间信息和多尺度光谱信息融合（MSSR）的遥感HSI SR方法。具体来说，受到遥感HSI高度自相似性的启发，提出了一种基于扩张卷积（DSSA）的空间光谱注意力模块，用于捕获全局空间信息。然后使用小尺寸卷积核通过残差块完成局部空间信息的提取。同时，我们提出了 3D inception 模块来有效地挖掘多尺度光谱信息。该模块仅保留了3-D卷积核在光谱维度上的尺度，大大降低了3-D卷积带来的高计算成本。四个基准数据集的对比实验结果表明，与当前的前沿模型相比，我们的方法达到了state-of-the-art（SOTA）的结果，并且模型计算量大大减少。