目录
一、论文笔记:
图像融合
-
GDD无监督图像对融合 Guided Deep Decoder: Unsupervised Image Pair Fusion代码
- 具有结构张量表示的无监督深度图像融合Unsupervised Deep Image Fusion With Structure Tensor Representations 代码
-
高光谱多光谱图像融合
- 无监督多注意力引导网络用于高光谱和多光谱图像融合UMAG-Net: A New Unsupervised Multi-attention-guided Network for Hyperspectral and Multispectral Image Fusion
- 用于高光谱和多用于高光谱和多光谱图像融合的基于物理的具有迭代细化单元的GANPhysics-based GAN with Iterative Refinement Unit for Hyperspectral and Multispectral Image Fusion
- 用于半盲高光谱和多光谱图像融合的非局部稀疏张量分解 Nonlocal Sparse Tensor Factorization for Semiblind Hyperspectral and Multispectral Image Fusion
- 基于双流融合网络的遥感图像融合 Remote sensing image fusion based on two-stream fusion network
- 具有深度先验的高光谱泛锐化(HPDP)Hyperspectral Pansharpening With Deep Priors
- 一种新的基于对抗性的高光谱和多光谱图像融合方法 A Novel Adversarial Based Hyperspectral and Multispectral Image Fusion
- 基于自适应响应函数学习的耦合卷积神经网络在高光谱超分辨中的应用 Coupled Convolutional Neural Network With Adaptive Response Function Learning for Unsupervised Hyperspectral Super Resolution
- 频谱分治的多光谱和高光谱图像融合方法 A Band Divide-and-Conquer Multispectral and Hyperspectral Image Fusion Method
- 基于CNN的Landsat 8全色与多光谱图像融合的泛锐化方法
- 基于元分析思想的遥感图像泛锐化方法综述:实践探讨与挑战Review of the Pansharpening Methods for Remote Sensing Images Based on the Idea of Meta-analysis: Practical Discussion and Challenges
- 基于深层注意力网络的高光谱与多光谱图像融合Deep Attention Network (Change_ZH的论文笔记)
-
多聚焦图像融合
- 用于多聚焦图像融合的全局特征编码GEU网Global-feature Encoding U-Net (GEU-Net) for Multi-focus Image Fusion
-
多分辨率图像融合
- DDcGAN:一种用于多分辨率图像融合的双鉴别器条件生成对抗网络A dual Discriminator Conditional Generative Adersarial Network for Multi-Resolution Image Fusion
-
图像分类
-
高光谱分类
- 使用Transformer重新思考高光谱图像分类问题SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers代码:https://github.com/danfenghong/ IEEETGRSSpectralFormer
-
超分辨率
- 单图高光谱超分
- 高光谱图像超分辨率空间谱先验学习 Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery 代码
- 基于对抗学习的波段注意力的高光谱图像超分辨率Hyperspectral Image Super-Resolution by Band Attention Through Adversarial Learning
- 用于高光谱图像超分辨率的光谱分组和注意力驱动的残差密集网络A Spectral Grouping and Attention-Driven Residual Dense Network for Hyperspectral Image Super-Resolution
- 深度学习的图像超分辨率(综述)Deep Learning for Image Super-Resolution
- 单图像超分
- 用于轻质图像超分辨率的残差特征蒸馏网络Residual Feature Distillation Network for Lightweight Image Super-Resolution
- 具有多注意力层的超轻量级图像超分辨率Ultra Lightweight Image Super-Resolution with Multi-Attention Layers 代码
- 有参考图像超分
- MASA-SR:匹配加速和空间自适应用于有参考图像超分辨率MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution
-
网络优化
- 双多尺度注意网络:DMSANet: Dual Multi Scale Attention Network CVPR2021
-
坐标注意力以实现高效的移动网络设计Coordinate Attention for Efficient Mobile Network Design
二、数据集:
高光谱数据集网站
Harvard数据集http://Statistics of Real-World Hyperspectral Images
2018 IEEE GRSS Data Fusion Challenge – Fusion of Multispectral LiDAR and Hyperspectral Data
自然场景的高光谱图像 - 2002(David H. Foster)
自然场景的高光谱图像 - 2004(David H. Foster)
五个多光谱成像数据集
- Area of Interest 1 (AOI 1) - Location: Rio de Janeiro. 50cm imagery collected from DigitalGlobe’s WorldView-2 satellite. The dataset includes building footprints and 8-band multispectral data.
- Area of Interest 2 (AOI 2) - Location: Vegas. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
- Area of Interest 3 (AOI 3) - Location: Paris. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
- Area of Interest 4 (AOI 4) - Location: Shanghai. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
- Area of Interest 5 (AOI 5) - Location: Khartoum. 30cm imagery collected from DigitalGlobe’s WorldView-3 satellite. The dataset includes building footprints and 8-band multispectral data.
- Area of Interest 6 (AOI 6) - Location: Atlanta 27 50cm images collected from DigitalGlobes’ WorldView-2 satellite. The dataset includes building footprints and 8-band multi-spectral data
15个免费卫星遥感数据源
用于语义分割的高分辨率多光谱数据集
worldview2
ICVL
Chikusei
Pavia University和 Pavia Center数据
图像数据集网站
多聚焦图像
Multi Focus Photography Contest (19726), Pictures Page 1 - Pxleyes.com
Mansour Nejati | Lytro Multi-focus Dataset
https://github.com/sametaymaz/Multi-focus-Image-Fusion-Dataset
Standard images for multifocus image fusion - File Exchange - MATLAB Central
医学图像
www.med.harvard.edu/aanlib/home.html
真彩色图像
红外与可见光图像
(D3) target tracking in multi-sensor video
Visible-Infrared Database :: Image Fusion
https://ivrl.epfl.ch/research-2/research-downloads/supplementary_material-cvpr11-index-html/
在这位博主Daniel__Shi的文章基础上补充了一些数据集
三、代码
图像超分
1、MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution
高光谱超分
1、A spatial-spectral prior deep network for hyperspectral image super-resolution
全色锐化
1、Pansharpening via Detail Injection Based Convolutional Neural Networks
2、PSGan: A GAN-based PanSharpening model
3、Target-Adaptive CNN Based Pansharpening
图像融合
1、FusionDN (AAAI 2020): A Unified Densely Connected Network for Image Fusion
2、U2Fusion: a unified unsupervised image fusion network for multiple image fusion tasks
3、Convolutional Autoencoder-Based Multispectral Image Fusion
图像去噪
1、Deep Spatial-Spectral Global Reasoning Network for Hyperspectral Image Denoising
Py_pansharpening 具有一些经典方法的Python版本pansharpening工具箱。 到目前为止,该工具箱实现了以下算法
- Brovey
- PCA
- IHS
- SFIM
- GS
- Wavelet
- MTF-GLP
- MTF-GLP-HPM
- GSA
- CNMF
- GFPCA
- PNN
- PanNet
四、常用工具
(一)ENVI
软件与扩展包:
- ENVI5.3安装教程(含软件下载)
- ENVI扩展工具:栅格图像批处理工具包 功能包括:批量正射校正(全色/多光谱)、批量图像融合、多光谱与全色批量辐射定标、快速大气校正、栅格裁剪、投影转换、转换存储顺序、图像配准、坏点修复、指数计算、波段运算、将加载在视图中的栅格图层输出为字节型TIFF文件、格式转换、设置忽略值
教程资料: