Hang Renlong, Liu Qingshan, Li Zhu
IEEE Trans Image Process. 2021;30:7256-7265. doi: 10.1109/TIP.2021.3104177. Epub 2021 Aug 20.
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.
高光谱图像（HSI）包含丰富的光谱信息，这对许多任务都有益处。然而，由于当前成像技术的限制，获取HSI很困难。作为一种替代方法，光谱超分辨率旨在从其对应的RGB图像重建HSI。最近，深度学习已在这项任务中展现出其强大能力，但大多数使用的网络都是从其他领域迁移过来的，比如空间超分辨率。在本文中，我们尝试利用HSI的两个固有特性来设计一个光谱超分辨率网络。第一个是光谱相关性。基于此特性，设计了一个分解子网来重建HSI。另一个是投影特性，即RGB图像可被视为HSI的三维投影。受此启发，构建了一个自监督子网作为对分解子网的约束。这两个子网构成了我们的端到端超分辨率网络。为了测试其有效性，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，与几个当前最先进的网络相比，我们提出的网络能够实现具有竞争力的重建性能。
