Pan-sharpening aims to seek high-resolution multi-spectral(HRMS)images from paired multispectral images of low resolution(LRMS)and panchromatic(PAN)images,the key to which is how to maximally integrate spatial and spectral infor-mation from PAN and LRMS images.Following the principle of gradual advance,this paper designs a novel network that con-tains two main logical functions,i.e.,detail enhancement and pro-gressive fusion,to solve the problem.More specifically,the detail enhancement module attempts to produce enhanced MS results with the same spatial sizes as corresponding PAN images,which are of higher quality than directly up-sampling LRMS images.Having a better MS base(enhanced MS)and its PAN,we pro-gressively extract information from the PAN and enhanced MS images,expecting to capture pivotal and complementary infor-mation of the two modalities for the purpose of constructing the desired HRMS.Extensive experiments together with ablation studies on widely-used datasets are provided to verify the efficacy of our design,and demonstrate its superiority over other state-of-the-art methods both quantitatively and qualitatively.Our code has been released at https://github.com/JiaYN1/PAPS.
万方数据
