Maskpan: Mask Prior Guided Network For Pansharpening

Pansharpening aims to generate the high spatial resolution multispectral (HRMS) images by fusing the spatial and spectral information from the low resolution multispectral (LRMS) images and high resolution panchromatic (PAN) images. Although existing pansharpening methods excel at achieving visual pleasing HRMS, they are limited in providing discriminability for visual tasks. To address this problem, this paper proposes a mask prior guided network (MaskPan) for pansharpening, which incorporates high-level semantic features with low-level detail information to improve the visual discrimination and quality of pansharpened images simultaneously. To make full use of the mask prior, the spatial and spectral features in conjunction with the semantic features are firstly fused in feature domain, and then promoted by an attention mechanism. In addition, the semantic segmentation task is introduced as a new metric to evaluate the visual discrimination of pansharpened images. Experimental results show that the proposed MaskPan can effectively enhance image quality and visual discrimination, thereby improving the pansharpening performance.