Existing spectral super-resolution (SSR) methods have achieved satisfactory performance by designing complicated deep convolution neural networks (DCNNs) to extract spectral and spatial features. However, these methods ignore the fact that the significance of spatial and spectral information in each hyperspectral image (HSI) is different, and most of them directly fuse two kinds of information with concatenation and convolution operation, which resulting in generating redundant information and have negative effects on reconstruction. To address such inadequacies, this paper proposes a novel adaptive spatial–spectral modulation network (ASSM-Net). Specifically, we propose a new adaptive feature fusion module (AFFM) to replace traditional convolutional fusion schemes. Through explicitly measuring the weights of spatial information and spectral features of HSI, AFFM can select dominant features for each pixel to modulate spatial and spectral information. Additionally, we develop a pixel-weighted aware attention (PAA) mechanism to enhance the feature interdependences for recovering finer structure information. Finally, a large number of quantitative and qualitative experiments reveal that the proposed network achieves competitive reconstruction results on three benchmark datasets (NTIRE 2022, CAVE and Harvard).

中文翻译：

---

一种新颖的光谱超分辨率网络，具有空间域和光谱域之间的主导信息


现有的光谱超分辨率（SSR）方法通过设计复杂的深度卷积神经网络（DCNN）来提取光谱和空间特征，取得了令人满意的性能。然而，这些方法忽略了每张高光谱图像（HSI）中空间和光谱信息的重要性不同的事实，并且大多数直接通过串联和卷积运算融合两种信息，从而导致生成冗余信息，并且具有负面影响。对重建的影响。为了解决这些不足，本文提出了一种新颖的自适应空间频谱调制网络（ASSM-Net）。具体来说，我们提出了一种新的自适应特征融合模块（AFFM）来取代传统的卷积融合方案。通过显式测量 HSI 的空间信息和光谱特征的权重，AFFM 可以为每个像素选择主导特征来调制空间和光谱信息。此外，我们开发了一种像素加权感知注意（PAA）机制来增强特征相互依赖性，以恢复更精细的结构信息。最后，大量定量和定性实验表明，所提出的网络在三个基准数据集（NTIRE 2022、CAVE 和Harvard）上取得了有竞争力的重建结果。