Unsupervised Hybrid Network of Transformer and CNN for Blind Hyperspectral and Multispectral Image Fusion

多光谱图像 高光谱成像 计算机科学 人工智能 图像融合 遥感 融合 多光谱模式识别 传感器融合 模式识别(心理学) 计算机视觉 图像(数学) 地质学 语言学 哲学
作者
Xuheng Cao,Yusheng Lian,Kaixuan Wang,Chao Ma,Xianqing Xu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-15 被引量:69
标识
DOI:10.1109/tgrs.2024.3359232
摘要

Fusing a low spatial resolution hyperspectral image with a high spatial resolution multispectral image has become popular for generating a high spatial resolution hyperspectral image (HR-HSI). Most methods assume that the degradation information from high resolution to low resolution is known in spatial and spectral domains. Conversely, this information is often limited or unavailable in practice, restricting their performance. Furthermore, existing fusion methods still face the problem of insufficient exploration of the cross-interaction between the spatial and spectral domains in the HR-HSI, leaving scope for further improvement. This paper proposes an unsupervised Hybrid Network of Transformer and CNN (uHNTC) for blind HSI-MSI fusion. The uHNTC comprises three subnetworks: a transformer-based feature fusion subnetwork (FeafusFomer) and two CNN-based degradation subnetworks (SpaDNet and SpeDNet). Considering the strong multi-level spatio-spectral correlation between the desired HR-HSI and the observed images, we design a Multi-level Cross-feature Attention (MCA) mechanism in FeafusFormer. By incorporating the hierarchical spatio-spectral feature fusion into the attention mechanism in the transformer, the MCA globally keeps a high spatio-spectral cross-similarity between the recovered HR-HSI and observed images, thereby ensuring the high cross-interaction of the recovered HR-HSI. Subsequently, the characteristics of degradation information are utilized to guide the design of the SpaDNet and SpeDNet, which helps FeafusFormer accurately recover the desired HR-HSI in complex real-world environments. Through an unsupervised joint training of the three subnetworks, uHNTC recovers the desired HR-HSI without pre-known degradation information. Experimental results on three public datasets and a WorldView-2 images show that the uHNTC outperforms ten state-of-the-art fusion methods. Code available: https://github.com/Caoxuheng/HIFtool.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
yh完成签到,获得积分10
1秒前
万能图书馆的应助被Jason采纳,获得30
2秒前
陆豪杰完成签到,获得积分10
3秒前
充电宝的应助被星辰采纳,获得20
3秒前
4秒前
5秒前
5秒前
勤奋梨愁完成签到,获得积分10
5秒前
xixi关注了科研通微信公众号
6秒前
无花果的应助被guoguozhijia158采纳,获得10
6秒前
7秒前
863发布了新的文献求助10
7秒前
slsdianzi完成签到,获得积分10
8秒前
脱羰甲酸发布了新的文献求助10
9秒前
9秒前
9秒前
852的应助被小冰块采纳,获得10
9秒前
zhaoliancheng完成签到,获得积分20
12秒前
大模型的应助被执着的钢笔采纳,获得10
12秒前
Z_xy完成签到,获得积分10
12秒前
13秒前
细心鲂发布了新的文献求助10
14秒前
zhaoliancheng发布了新的文献求助10
14秒前
霞霞子完成签到 ,获得积分10
15秒前
16秒前
万能图书馆的应助被久怨采纳,获得10
17秒前
SONG完成签到,获得积分10
18秒前
Yy完成签到 ,获得积分10
19秒前
博士完成签到 ,获得积分10
20秒前
20秒前
Ava的应助被863采纳,获得10
21秒前
斯文败类的应助被百川采纳,获得10
21秒前
21秒前
21秒前
22秒前
wwqc完成签到,获得积分0
24秒前
顾矜的应助被dit采纳,获得10
24秒前
26秒前
YI123456发布了新的文献求助10
26秒前
kowster完成签到 ,获得积分10
26秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188353
求助须知:如何正确求助?哪些是违规求助? 9576169
关于积分的说明 21845860
捐赠科研通 7786410
什么是DOI,文献DOI怎么找? 3435292
关于科研通互助平台的介绍 2559588
邀请新用户注册赠送积分活动 2482235