Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network

Hyperspectral and multispectral remote sensing image fusion is an optimal approach for generating hyperspectral–spatial-resolution images, effectively overcoming the physical limitations of sensors. In transformer-based image fusion methods constrained by the local window self-attention mechanism, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Yilin He, Heng Li, Miaosen Zhang, Shuangqi Liu, Chunyu Zhu, Bingxia Xin, Jun Wang, Qiong Wu
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/12/1973
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849425332359135232
author Yilin He
Heng Li
Miaosen Zhang
Shuangqi Liu
Chunyu Zhu
Bingxia Xin
Jun Wang
Qiong Wu
author_facet Yilin He
Heng Li
Miaosen Zhang
Shuangqi Liu
Chunyu Zhu
Bingxia Xin
Jun Wang
Qiong Wu
author_sort Yilin He
collection DOAJ
description Hyperspectral and multispectral remote sensing image fusion is an optimal approach for generating hyperspectral–spatial-resolution images, effectively overcoming the physical limitations of sensors. In transformer-based image fusion methods constrained by the local window self-attention mechanism, the extraction of global information and coordinated contextual features is often insufficient. Fusion that aims to emphasize spatial–spectral heterogeneous characteristics may significantly enhance the robustness of joint representation for multi-source data. To address these issues, this study proposes a hyperspectral and multispectral remote sensing image fusion method based on a retractable spatial–spectral transformer network (RSST) and introduces the attention retractable mechanism into the field of remote sensing image fusion. Furthermore, a gradient spatial–spectral recovery block is incorporated to effectively mitigate the limitations of token interactions and the loss of spatial–spectral edge information. A series of experiments across multiple scales demonstrate that RSST exhibits significant advantages over existing mainstream image fusion algorithms.
format Article
id doaj-art-ad0f7804f9bb4ac792eff9c4bc993d22
institution Kabale University
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-ad0f7804f9bb4ac792eff9c4bc993d222025-08-20T03:29:48ZengMDPI AGRemote Sensing2072-42922025-06-011712197310.3390/rs17121973Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer NetworkYilin He0Heng Li1Miaosen Zhang2Shuangqi Liu3Chunyu Zhu4Bingxia Xin5Jun Wang6Qiong Wu7College of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaCollege of Software, Jilin University, No. 2699 Qianjin Street, Changchun 130012, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaHangzhou Institute of Technology, Xidian University, No. 177 Lvxue Road, Hangzhou 311231, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, No. 938 Ximinzhu Street, Changchun 130026, ChinaHyperspectral and multispectral remote sensing image fusion is an optimal approach for generating hyperspectral–spatial-resolution images, effectively overcoming the physical limitations of sensors. In transformer-based image fusion methods constrained by the local window self-attention mechanism, the extraction of global information and coordinated contextual features is often insufficient. Fusion that aims to emphasize spatial–spectral heterogeneous characteristics may significantly enhance the robustness of joint representation for multi-source data. To address these issues, this study proposes a hyperspectral and multispectral remote sensing image fusion method based on a retractable spatial–spectral transformer network (RSST) and introduces the attention retractable mechanism into the field of remote sensing image fusion. Furthermore, a gradient spatial–spectral recovery block is incorporated to effectively mitigate the limitations of token interactions and the loss of spatial–spectral edge information. A series of experiments across multiple scales demonstrate that RSST exhibits significant advantages over existing mainstream image fusion algorithms.https://www.mdpi.com/2072-4292/17/12/1973image fusionhyperspectral imagemultispectral imagetransformerretractable attentiongradient spatial–spectral recovery
spellingShingle Yilin He
Heng Li
Miaosen Zhang
Shuangqi Liu
Chunyu Zhu
Bingxia Xin
Jun Wang
Qiong Wu
Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
Remote Sensing
image fusion
hyperspectral image
multispectral image
transformer
retractable attention
gradient spatial–spectral recovery
title Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
title_full Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
title_fullStr Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
title_full_unstemmed Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
title_short Hyperspectral and Multispectral Remote Sensing Image Fusion Based on a Retractable Spatial–Spectral Transformer Network
title_sort hyperspectral and multispectral remote sensing image fusion based on a retractable spatial spectral transformer network
topic image fusion
hyperspectral image
multispectral image
transformer
retractable attention
gradient spatial–spectral recovery
url https://www.mdpi.com/2072-4292/17/12/1973
work_keys_str_mv AT yilinhe hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT hengli hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT miaosenzhang hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT shuangqiliu hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT chunyuzhu hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT bingxiaxin hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT junwang hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork
AT qiongwu hyperspectralandmultispectralremotesensingimagefusionbasedonaretractablespatialspectraltransformernetwork