当前位置: X-MOL 学术IEEE Trans. Image Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Posterior Distribution-Based Embedding for Hyperspectral Image Super-Resolution
IEEE Transactions on Image Processing ( IF 10.6 ) Pub Date : 2022-08-30 , DOI: 10.1109/tip.2022.3201478
Jinhui Hou 1 , Zhiyu Zhu 1 , Junhui Hou 1 , Huanqiang Zeng 2 , Jinjian Wu 3 , Jiantao Zhou 4
Affiliation  

In this paper, we investigate the problem of hyperspectral (HS) image spatial super-resolution via deep learning. Particularly, we focus on how to embed the high-dimensional spatial-spectral information of HS images efficiently and effectively. Specifically, in contrast to existing methods adopting empirically-designed network modules, we formulate HS embedding as an approximation of the posterior distribution of a set of carefully-defined HS embedding events, including layer-wise spatial-spectral feature extraction and network-level feature aggregation. Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable, producing PDE-Net, in which high-resolution (HR) HS images are iteratively refined from the residuals between input low-resolution (LR) HS images and pseudo-LR-HS images degenerated from reconstructed HR-HS images via probability-inspired HS embedding. Extensive experiments over three common benchmark datasets demonstrate that PDE-Net achieves superior performance over state-of-the-art methods. Besides, the probabilistic characteristic of this kind of networks can provide the epistemic uncertainty of the network outputs, which may bring additional benefits when used for other HS image-based applications. The code will be publicly available at https://github.com/jinnh/PDE-Net .

中文翻译:

基于深度后验分布的高光谱图像超分辨率嵌入

在本文中,我们通过深度学习研究了高光谱 (HS) 图像空间超分辨率问题。特别是,我们专注于如何有效地嵌入 HS 图像的高维空间光谱信息。具体来说,与采用经验设计的网络模块的现有方法相比,我们将 HS 嵌入表示为一组精心定义的 HS 嵌入事件的后验分布的近似值,包括逐层空间光谱特征提取和网络级特征聚合。然后,我们将提出的特征嵌入方案合并到一个物理可解释的源一致的超分辨率框架中,生成 PDE-Net,其中高分辨率 (HR) HS 图像是从输入低分辨率 (LR) HS 图像和通过概率启发的 HS 嵌入从重建的 HR-HS 图像退化的伪 LR-HS 图像之间的残差中迭代提炼的。对三个常见基准数据集的大量实验表明,PDE-Net 的性能优于最先进的方法。此外,这种网络的概率特性可以提供网络输出的认知不确定性,这在用于其他基于 HS 图像的应用时可能会带来额外的好处。该代码将在以下位置公开提供 对三个常见基准数据集的大量实验表明,PDE-Net 的性能优于最先进的方法。此外,这种网络的概率特性可以提供网络输出的认知不确定性,这在用于其他基于 HS 图像的应用时可能会带来额外的好处。该代码将在以下位置公开提供 对三个常见基准数据集的大量实验表明,PDE-Net 的性能优于最先进的方法。此外,这种网络的概率特性可以提供网络输出的认知不确定性,这在用于其他基于 HS 图像的应用时可能会带来额外的好处。该代码将在以下位置公开提供https://github.com/jinnh/PDE-Net .
更新日期:2022-09-03
down
wechat
bug