A survey on hyperspectral image restoration: from the view of low-rank tensor approximation

Liu, Na; Li, Wei; Wang, Yinjian; Tao, Ran; Du, Qian; Chanussot, Jocelyn

doi:10.1007/s11432-022-3609-4

Cited by 24 publications

(8 citation statements)

References 196 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, i Z is fed into the spatial and spectral down-projection modules in the next stage. Finally, 1 Z , 2 Z , and 3 Z are concatenated to reconstruct the fused image.…”

Section: Reconstruction and Optimizationmentioning

confidence: 99%

“…More and more remote sensing images are obtained and applied to various fields. However, optical and multi/hyperspectral images often suffer from the limitations of spatial and spectral resolutions [1]- [2]. The physical tradeoff in imaging sensors limits the concurrent increase of spatial and spectral resolutions of remote sensing images [3]- [4].…”

Section: Introductionmentioning

confidence: 99%

“…d is the sampling ratio. Because spatial up-and down-sampling are involved, the spatial dimensions of images are changed in (1). Thus, we superscripts, l and h, to represent LR and HR, respectively.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, a spatial-aware block (SpaAB) is designed to further enhance the spatial information in the HR feature. In SpaAB, the spatial information in features is highlighted by 128 filters with the size of 1…”

mentioning

confidence: 99%

See 3 more Smart Citations

Spatial-Spectral Dual Back-Projection Network for Pansharpening

Zhang

Wang

Zhang

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep unfolding networks have obtained satisfactory performance in the pansharpening task owing to their sufficient interpretability. Inspired by the back-projection (BP) mechanism, we propose a BP-driven model, spatial-spectral dual back-project network (S 2 DBPN), to fuse the low spatial resolution multispectral (LR MS) and the high spatial resolution panchromatic (PAN) images by exploiting the BP in spatial and spectral domains. Specifically, the proposed S 2 DBPN is made up of a spatial BP network, a spectral BP network, and a reconstruction network. In the spatial BP network, spatial down-and up-projection modules are derived from BP, which is responsible for the projection of the LR MS image into the spatial domain. By analogy with the spatial BP, we reformulate the degradation between high spatial resolution multispectral (HR MS) and PAN images as spectral down-and up-projections. Then, the spectral BP network is constructed for the projection of the PAN image along the channel dimension. Finally, the features from spatial and spectral BP networks are integrated to produce the desired HR MS image through the reconstruction network. Compared to the state-of-the-art methods, extensive experiments on QuickBird, GeoEye-1, and WorldView-2 datasets demonstrate that our S 2 DBPN produces better HR MS images in terms of qualitative and quantitative evaluation metrics. The code of S 2 DBPN is released at: https://github.com/RSMagneto/S2DBPN.

show abstract

“…Then, i Z is fed into the spatial and spectral down-projection modules in the next stage. Finally, 1 Z , 2 Z , and 3 Z are concatenated to reconstruct the fused image.…”

Section: Reconstruction and Optimizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Spatial-Spectral Dual Back-Projection Network for Pansharpening

Zhang

Wang

Zhang

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Noise can blur the images, complicating disease detection and potentially leading to severe consequences, including fatalities. Therefore, it is crucial to remove noise from medical images before further analysis [2]. A primary hurdle in medical imaging is capturing images without omitting important details.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Medical Image Denoising with Innovative Teacher–Student Model-Based Approaches for Precision Diagnostics

Muksimova,

Umirzakova,

Mardieva

et al. 2023

Sensors

View full text Add to dashboard Cite

The realm of medical imaging is a critical frontier in precision diagnostics, where the clarity of the image is paramount. Despite advancements in imaging technology, noise remains a pervasive challenge that can obscure crucial details and impede accurate diagnoses. Addressing this, we introduce a novel teacher–student network model that leverages the potency of our bespoke NoiseContextNet Block to discern and mitigate noise with unprecedented precision. This innovation is coupled with an iterative pruning technique aimed at refining the model for heightened computational efficiency without compromising the fidelity of denoising. We substantiate the superiority and effectiveness of our approach through a comprehensive suite of experiments, showcasing significant qualitative enhancements across a multitude of medical imaging modalities. The visual results from a vast array of tests firmly establish our method’s dominance in producing clearer, more reliable images for diagnostic purposes, thereby setting a new benchmark in medical image denoising.

show abstract

Multi-sensor multispectral reconstruction framework based on projection and reconstruction

Li,

Liu,

et al. 2024

Sci. China Inf. Sci.

View full text Add to dashboard Cite

A survey on hyperspectral image restoration: from the view of low-rank tensor approximation

Cited by 24 publications

References 196 publications

Spatial-Spectral Dual Back-Projection Network for Pansharpening

Spatial-Spectral Dual Back-Projection Network for Pansharpening

Enhancing Medical Image Denoising with Innovative Teacher–Student Model-Based Approaches for Precision Diagnostics

Multi-sensor multispectral reconstruction framework based on projection and reconstruction

Contact Info

Product

Resources

About