小波系数指导的全色锐化网络

针对现有全色锐化网络无法同时兼顾空间信息与光谱信息保留的问题，提出一种基于小波系数指导的由融合网络和指导网络组成的全色锐化网络。融合网络分别提取PAN和MS图像的多级特征，并在同一级别进行特征的选择和融合，融合后的特征分别用于指导后一级别特征的提取；指导网络用于学习HRMS与已知的输入图像的小波系数之间的映射关系，并利用学习到的映射对融合网络的输出提供额外的监督。实验结果表明，该方法能够在保留MS图像光谱信息的同时恢复尽可能多的空间信息。在模拟数据集和真实数据集上的对比实验也表明，该方法融合效果优于其他传统方法和深度学习方法，具有一定的实用价值。

Pan-sharpening network guided by wavelet coefficients

To tackle the problem that existing pan-sharpening networks cannot preserve spatial information and spectral information simultaneously, this paper proposed a pan-sharpening network guided by wavelet coefficients, which consisted of fusion network and guidance network. The fusion network extracted the multi-level features of PAN and MS images respectively, and performed feature selection and fusion at the same level. The fused features guided the extraction of features at the next level. The guidance network learned the mapping relationship between the wavelet coefficients of the input LRMS/PAN images and HRMS image, and provided extra supervision for the output of the fusion network. Experimental results show that the proposed network can recover as much spatial information as possible while preserving the spectral information of MS images. Comparison experiments on simulated datasets and real datasets also show that the fusion effect of the proposed method is better than other traditional methods and deep learning methods, which has certain value in practice.