APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 3

ESAFormer: Multi-resolution Fusion Network for Pansharpening

Xiangzeng Liu, Xi'dian University, China, xzliu@xidian.edu.cn , Rutao Li, Xi'dian University, China, Ziyao Wang, Xi'dian University, China, Ronghan Li, Xi'dian University, China, Qi Cheng, China University of Mining and Technology, China, Qiguang Miao, Xi'dian University, China
 
Suggested Citation
Xiangzeng Liu, Rutao Li, Ziyao Wang, Ronghan Li, Qi Cheng and Qiguang Miao (2024), "ESAFormer: Multi-resolution Fusion Network for Pansharpening", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 3, e204. http://dx.doi.org/10.1561/116.00000174

Publication Date: 22 Apr 2024
© 2024 X. Liu, R. Li, Z. Wang, R. Li, Q. Cheng and Q. Miao
 
Subjects
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 158 times

In this article:
Introduction 
Multi-resolution Fusion Network for Pansharpening 
Experimental Results and Analysis 
Conclusions 
References 

Abstract

The pansharpening task is to fuse low-resolution multispectral (LRMS) images and high-resolution panchromatic (PAN) images to generate high-resolution multispectral images. Most of the existing methods do not preserve spatial and spectral details well, which is due to ignoring the difference in resolution between the two images. To address this issue, we propose a novel fusion network (ESAFormer) that effectively enhances the spatial and spectral information representation. In the proposed model, a hybrid multiresolution structure of CNN and Transformer is deployed to allow the features of LRMS images and PAN images to fuse progressively. Subsequently, the enhanced spatial attention module is adopted to preserve spatial details and long-range information. Extensive experimental results indicate that the proposed method is superior to existing SOTA methods on World-View2 and IKONOS datasets.

DOI:10.1561/116.00000174

Companion

APSIPA Transactions on Signal and Information Processing Special Issue - Advanced Machine Learning Techniques for Remote Sensing: Algorithms and Applications
See the other articles that are part of this special issue.