Heterogeneous two-Stream Network with Hierarchical Feature Prefusion for Multispectral Pan-Sharpening
Dong Wang, Yunpeng Bai, Bendu Bai, Chanyue Wu, Ying Li
Abstract
Multispectral (MS) pan-sharpening aims at producing a high spatial resolution (HR) MS image by fusing a single-band HR panchromatic (PAN) image and a corresponding MS image with low spatial resolution. In this paper, we propose a heterogeneous two-stream network (HTSNet) with hierarchical feature prefusion for MS pan-sharpening. The HTSNet employs a heterogeneous group of spatial and spectral streams for spatial and spectral information extraction, respectively. The spatial stream utilizes a 2D CNN for spatial information extraction from the PAN images, and the spectral stream obtains spectral feature cubes from the MS images by a 3D CNN. At the same time, a prefusion module is introduced to prefuse the spatial details with spectral information and transfer information between different streams, which can enhance later processing. In the experiment, the Gaofen-2 satellite dataset is utilized to compare the proposed method with the state-of-the-art MS pan-sharpening methods. Experimental results demonstrate the superiority of our HTSNet in terms of visual effect and quantitative qualities.
BibTeX
@inproceedings{icassp2021_heterogeneoustwo,
title = {Heterogeneous two-Stream Network with Hierarchical Feature Prefusion for Multispectral Pan-Sharpening},
author = {Dong Wang and Yunpeng Bai and Bendu Bai and Chanyue Wu and Ying Li},
booktitle = {ICASSP 2021},
year = {2021}
}