Spectral-Fidelity Convolutional Neural Networks for Hyperspectral Pansharpening

He, Lin; Zhu, Jiawei; Li, Jun; Meng, Deyu; Chanussot, Jocelyn; Plaza, Antonio

doi:10.1109/jstars.2020.3025040

Cited by 38 publications

(28 citation statements)

References 41 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the explosive development of deep learning, many CNN-based fusion networks have been designed to inject the pan details into the LR-HSI. For example, He et al [30] generated the PAN details and HSI features through convolution operations and fused these features by cascade CNN blocks to get the HR-HSI. Li et al [34] combined the CNN and guided filter to inject the PAN details into the LR-HSI.…”

Section: B Pan Detail Inject Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Unmixing based PAN guided fusion network for hyperspectral imagery

Li,

Tian,

Xia

et al. 2022

Preprint

View full text Add to dashboard Cite

Section: B Pan Detail Inject Methodsmentioning

confidence: 99%

“…In addition, to avoid the blurring effect induced by this loss function, we add the SAM loss to improve the spectral fidelity of the fused HR-HSI as SAM ( X, X) = 1 N m j arccos x j x j xj 2 x j 2 (30) where x j x j represents the inner product of these two vectors, and the other notations in this equation are the same as Eq. ( 29).…”

Section: F Loss Functionmentioning

confidence: 99%

Unmixing based PAN guided fusion network for hyperspectral imagery

Li,

Tian,

Xia

et al. 2022

Preprint

View full text Add to dashboard Cite

“…Over recent years, deep learning (DL) based methods, particularly convolutional neural network (CNN) based DL techniques, have achieved significant advances in image processing fields, e.g., image resolution reconstruction [42]- [50], image classification [51]- [53], image denoising [54], image fusion [55]- [61], etc. Therefore, many methods [1], [2], [62]- [75] based on deep learning have also been applied to solve the pansharpening problem. Dong et al [42] originally introduce a shallow three-layer CNN (SRCNN) to learn the mapping between LR and HR patches for single image super-resolution.…”

Section: Introductionmentioning

confidence: 99%

A Deep-Shallow Fusion Network With Multidetail Extractor and Spectral Attention for Hyperspectral Pansharpening

Zhuo

Zhang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral (HS) pansharpening aims at fusing a low-resolution HS (LRHS) image with a high-resolution panchromatic (PAN) image to obtain a hyperspectral image with both higher spectral and spatial resolutions. However, existing HS pansharpening algorithms are mainly based on multispectral (MS) pansharpening approaches, which cannot perfectly restore much spectral information and more high-frequency spatial details in the continuous spectral bands and much broader spectral range, leading to spectral distortion and spatial blur. In this paper, we develop a new hyperspectral pansharpening network architecture (called Hyper-DSNet) to fully preserve latent spatial details and spectral fidelity via a deep-shallow fusion structure with multi-detail extractor and spectral attention. Specifically, the proposed architecture mainly consists of three parts. First, to solve the problem of spatial ambiguity and exploit the potential information, five types of high-pass filter templates are used to fully extract the spatial details of the PAN image, constructing a so-called multi-detail extractor (MDE). Then, after passing a multi-scale convolution module, a deep-shallow fusion (DSF) structure, which reduces parameters by decreasing the number of output channels as the network goes deeper, is utilized sequentially. In final, a spectral attention (SA) module is conducted to preserve the spectrum for a wealth of spectral information of HS images. Visual and quantitative experiments on three commonly used simulated datasets and one full-resolution dataset demonstrate the effectiveness and robustness of the proposed Hyper-DSNet against the recent state-ofthe-art hyperspectral pansharpening techniques. Ablation studies and discussions further verify our contributions, e.g., better spectral preservation and spatial detail recovery. The source code is available at https://github.com/liangjiandeng/Hyper-DSNet, and the related datasets can be found from https://github.com/liangjiandeng/HyperPanCollection.

show abstract

“…Due to the high spectral resolution of the HSI, HSI can be widely used in environmental surveillance, military surveillance, medical detection, and agricultural planning, etc. [1]- [10]. However, higher spectral resolution means larger volume, which will greatly increase the burden of transmission and storage.…”

Section: Introductionmentioning

confidence: 99%

T-Hy-Demosaicing: Hyperspectral Reconstruction Via Tensor Subspace Representation Under Orthogonal Transformation

Huang

Lin

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

This paper aims to solve the problem of the hyperspectral imagery (HSI) demosaicing under a novel subsampling hyperspectral sensing strategy. The existing method utilizes the periodic structure of sub-sampling to estimate a fixed subspace in matrix form from the measurement result, which reduces the representation ability of the subspace in iterations and destroys the intrinsic structure of the tensor. To overcome these drawbacks, we propose a tensor-based HSI demosaicing (T-Hydemosaicing) model with tensor subspace representation, which takes the low-tubal-rankness and the nonlocal self-similarity into account. In particular, we suggest a tensor singular value decomposition based on orthogonal transformation (Tran-based t-SVD) to learn the tensor subspace that possesses a more powerful representation ability. In addition, we develop an effective algorithm to solve the proposed non-convex model under the framework of the proximal alternating minimization (PAM) algorithm. Experiments conducted on simulated datasets illustrate that the proposed method outperforms other comparative methods in both visual and quantitative terms.

show abstract

Spectral-Fidelity Convolutional Neural Networks for Hyperspectral Pansharpening

Cited by 38 publications

References 41 publications

Unmixing based PAN guided fusion network for hyperspectral imagery

Unmixing based PAN guided fusion network for hyperspectral imagery

A Deep-Shallow Fusion Network With Multidetail Extractor and Spectral Attention for Hyperspectral Pansharpening

T-Hy-Demosaicing: Hyperspectral Reconstruction Via Tensor Subspace Representation Under Orthogonal Transformation

Contact Info

Product

Resources

About