An Iterative Regularization Method Based on Tensor Subspace Representation for Hyperspectral Image Super-Resolution

Xu, Ting; Huang, Ting‐Zhu; Deng, Liang-Jian; Yokoya, Naoto

doi:10.1109/tgrs.2022.3176266

Cited by 34 publications

(15 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Factorizationbased methods mainly decompose the target image and then build an optimization model to solve. The factorization-based methods include matrix factorization-based methods [31]- [34] and tensor decomposition-based methods [35]- [43]. Matrix factorization-based methods primarily transform the fusion task into an estimation of the spectral basis and corresponding coefficients.…”

Section: A Model-based Methodsmentioning

confidence: 99%

“…Based on tensor ring decomposition, He et al [40] designed a model that iteratively obtain corresponding core tensors from LRHS and HRMS images. A regularization method was proposed by Xu et al [43], which integrated two priors simultaneously to estimate tensor subspace and tensor coefficients and obtained excellent super-resolution results.…”

Section: A Model-based Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Crossed Dual-Branch U-Net for Hyperspectral Image Super-Resolution

Zhang,

Liu,

Yang

et al. 2024

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

View full text Add to dashboard Cite

Hyperspectral images have gained great achievements in many fields, but their low-spatial resolution limits the effectiveness in applications. Hyperspectral image superresolution has emerged as a popular research trend, where high-resolution hyperspectral images are obtained via combing low-resolution hyperspectral images with high-resolution multispectral images. In this process of multi-modality data fusion, it is crucial to ensure effective cross-modality information interaction. To generate higher quality fusion results, a crossed dual-branch U-Net is proposed in this paper. In specific, we adopt U-Net architecture and introduce a spectral-spatial feature interaction module to capture cross-modality interaction information between two input images. To narrow the gap between downsampling and upsampling processes, a spectralspatial parallel Transformer is designed as skip connection. This novel design simultaneously learns the long-range dependencies both on spatial and spectral information and provides detailed information for final fusion. In the fusion stage, We adopt a progressive upsampling strategy to refine the generated images. Extensive experiments on several public datasets are conducted to prove the performance of the proposed network. The code can be accessed at https://github.com/liuofficial/CD-UNet.

show abstract

Section: A Model-based Methodsmentioning

confidence: 99%

Section: A Model-based Methodsmentioning

confidence: 99%

Crossed Dual-Branch U-Net for Hyperspectral Image Super-Resolution

Zhang,

Liu,

Yang

et al. 2024

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

View full text Add to dashboard Cite

show abstract

“…Secondly, the difficulty in obtaining MTF-filter parameters during the degradation process is a potential influencing factor. Alternatively, some researchers use uniform filtering [31,32] and Gaussian filtering [29,30,36] to implement the spatial degradation. The size and the variance of Gaussian kernels used are different, making the accuracy of spatial degradation unreliable.…”

Section: Fr Quality Assessmentmentioning

confidence: 99%

“…Tucker decomposition and Canonical polyadic (CP) decomposition are widely used. The representative TR-based fusion methods include coupled sparse tensor factorization [27], nonlocal coupled tensor CP [28], low tensor multi-rank regularization (LTMR) [29], low tensor-train rank representation [30], unidirectional total variation with tucker decomposition (UTV) [31], tensor subspace representation-based regularization model (IR-TenSR) [32]. The deep CNN-based methods often train a network between ground-truth images (i.e., original HS images) and input images (i.e., low spatial resolution HS and high spatial resolution MS images).…”

Section: Introductionmentioning

confidence: 99%

A No-Reference Quality Assessment Method for Hyperspectral Sharpened Images via Benford’s Law

Hao,

Li,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In recent years, hyperspectral (HS) sharpening technology has received high attention and HS sharpened images have been widely applied. However, the quality assessment of HS sharpened images has not been well addressed and is still limited to the use of full-reference quality evaluation. In this paper, a novel no-reference quality assessment method based on Benford’s law for HS sharpened images is proposed. Without a reference image, the proposed method detects fusion distortion by performing first digit distribution on three quality perception features in HS sharpened images, using the standard Benford’s law as a benchmark. The experiment evaluates 10 HS fusion methods on three HS datasets and selects four full-reference metrics and four no-reference metrics to compare with the proposed method. The experimental results demonstrate the superior performance of the proposed method.

show abstract

“…The experimental results demonstrate that this strategy can effectively preserve spatial detail information in the recovered image. Xu et al [31] utilized an iterative regularization technique based on tensor sub-space representation to amalgamate paired multispectral and hyperspectral images, thereby reconstructing high-resolution hyperspectral images with distinct texture and sharp edges. Hong et al [32] proposed a decoupled and coupled high-spectral-resolution image super-resolution algorithm that progressively aggregates high-spectral and multi-spectral information.…”

Section: B Remote Sensing Image Super-resolutionmentioning

confidence: 99%

Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution

Wang¹,

Zhao²,

Chen

2023

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

View full text Add to dashboard Cite

Recently, with the rise and progress of convolutional neural networks (CNNs), CNN-based remote sensing image super-resolution (RSSR) methods have gained considerable advancement and showed great power for image reconstruction tasks. However, most of these methods cannot handle well the enormous number of objects with different scales contained in remote sensing images and thus limits super-resolution performance. To address these issues, we propose a Multi-Scale Fast Fourier Transform (FFT) based Attention Network (MSFFTAN) which employs a multi-input U-shape structure as backbone for accurate remote sensing image super-resolution. Specifically, we carefully design an FFT-based residual block consisting of an image domain branch and a Fourier domain branch to extract local details and global structures simultaneously. In addition, a Local-Global Channel Attention Block (LGCAB) is developed to further enhance the reconstruction ability of small targets. Finally, we present a Branch Gated Selective Block (BGSB) to adaptively explore and aggregate features from multiple scales and depths. Extensive experiments on two publicly datasets have demonstrated the superiority of MSFFTAN over the state-of-theart (SOAT) approaches in aspects of both quantitative metrics and visual quality. The peak signal-to-noise ratio of our network is 1.5 dB higher than the SOAT method on the UCMerced LandUse with downscaling factor 2.

show abstract

An Iterative Regularization Method Based on Tensor Subspace Representation for Hyperspectral Image Super-Resolution

Cited by 34 publications

References 73 publications

Crossed Dual-Branch U-Net for Hyperspectral Image Super-Resolution

Crossed Dual-Branch U-Net for Hyperspectral Image Super-Resolution

A No-Reference Quality Assessment Method for Hyperspectral Sharpened Images via Benford’s Law

Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution

Contact Info

Product

Resources

About