Hyperspectral imagery (HSI) contains rich spectral information, which is beneficial to many tasks. However, acquiring HSI is difficult because of the limitations of current imaging technology. As an alternative method, spectral super-resolution aims at reconstructing HSI from its corresponding RGB image. Recently, deep learning has shown its power to this task, but most of the used networks are transferred from other domains, such as spatial super-resolution. In this paper, we attempt to design a spectral super-resolution network by taking advantage of two intrinsic properties of HSI. The first one is the spectral correlation. Based on this property, a decomposition subnetwork is designed to reconstruct HSI. The other one is the projection property, i.e., RGB image can be regarded as a three-dimensional projection of HSI. Inspired from it, a self-supervised subnetwork is constructed as a constraint to the decomposition subnetwork. These two subnetworks constitute our end-to-end super-resolution network. In order to test the effectiveness of it, we conduct experiments on three widely used HSI datasets (i.e., CAVE, NUS, and NTIRE2018). Experimental results show that our proposed network can achieve competitive reconstruction performance in comparison with several state-of-the-art networks.

中文翻译：

---

由高光谱图像的内在特性引导的光谱超分辨率网络

高光谱图像（HSI）包含丰富的光谱信息，这对许多任务都有好处。然而，由于当前成像技术的限制，获取 HSI 很困难。作为替代方法，光谱超分辨率旨在从其相应的 RGB 图像重建 HSI。最近，深度学习已经显示出它在这项任务中的威力，但大多数使用的网络都是从其他领域转移过来的，例如空间超分辨率。在本文中，我们尝试利用 HSI 的两个内在特性来设计光谱超分辨率网络。第一个是频谱相关性。基于这个特性，设计了一个分解子网络来重构 HSI。另一个是投影属性，即RGB图像可以看作是HSI的三维投影。受其启发，构建自监督子网络作为对分解子网络的约束。这两个子网构成了我们端到端的超分辨率网络。为了测试它的有效性，我们在三个广泛使用的 HSI 数据集（即 CAVE、NUS 和 NTIRE2018）上进行了实验。实验结果表明，与几种最先进的网络相比，我们提出的网络可以实现有竞争力的重建性能。