Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations

Zhuang, Lina; Bioucas-Dias, José M.

doi:10.1109/jstars.2018.2796570

Cited by 278 publications

(211 citation statements)

References 48 publications

(86 reference statements)

Supporting

Mentioning

178

Contrasting

Order By: Relevance

“…Results (Fig. 4, Table 1) are compared to Mumford-Shah [14] and fourth-order total variation (TV-H −1 ) [5] 2D methods, as well as the state-of-the-art HSI inpainting method FastHyIn [40].…”

Section: Methodsmentioning

confidence: 99%

Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution

Sidorov

Hardeberg

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

148

130

View full text Add to dashboard Cite

Deep learning algorithms have demonstrated state-ofthe-art performance in various tasks of image restoration. This was made possible through the ability of CNNs to learn from large exemplar sets. However, the latter becomes an issue for hyperspectral image processing where datasets commonly consist of just a few images. In this work, we propose a new approach to denoising, inpainting, and superresolution of hyperspectral image data using intrinsic properties of a CNN without any training. The performance of the given algorithm is shown to be comparable to the performance of trained networks, while its application is not restricted by the availability of training data. This work is an extension of original "deep prior" algorithm to hyperspectral imaging domain and 3D-convolutional networks.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution

Sidorov

Hardeberg

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

148

130

View full text Add to dashboard Cite

show abstract

“…A remedy is a two-stage method combining the spatial regularizer and spectral low-rank property together. This is done by firstly mapping the original HSI into the low-dimensional spectral subspace, and then denoise the mapped image via existing spatial denoising methods, e.g., wavelets [11,32], BM3D [52] and HOSVD [51]. These two-stage methods provide a new sight to denoise the HSI in the transferred spectral space, which is very fast.…”

Section: Spectral: Global Low-rank Propertymentioning

confidence: 99%

Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

Wei

Yao

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

133

View full text Add to dashboard Cite

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, while their denoising performance benefits little from more spectral bands, the running time of these methods significantly increases. In this paper, we claim that the HSI lies in a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should lie in this global low-rank subspace. This motivates us to propose a unified spatialspectral paradigm for HSI denoising. As the new model is hard to optimize, An efficient algorithm motivated by alternating minimization is developed. This is done by first learning a low-dimensional orthogonal basis and the related reduced image from the noisy HSI. Then, the non-local low-rank denoising and iterative regularization are developed to refine the reduced image and orthogonal basis, respectively. Finally, the experiments on synthetic and both real datasets demonstrate the superiority against the stateof-the-art HSI denoising methods.

show abstract

“…where HySime stays for Hyperspectral signal Subspace Identification by Minimum Error [18], p is a length of the eigenspace.…”

Section: Joint Slice Denoisingmentioning

confidence: 99%

“…Overall, the presented CCF algorithm follows the structure of the fast hyperspectral denoising (FastHyDe) algorithm presented for real-valued data in [18]. A generalization to the complex domain required modification of the codes as well as revision of the theoretical background.…”

Section: Joint Slice Denoisingmentioning

confidence: 99%

Hyperspectral phase imaging based on denoising in complex-valued eigensubspace

Shevkunov

Katkovnik

Claus

et al. 2020

Optics and Lasers in Engineering

View full text Add to dashboard Cite

A new denoising algorithm for hyperspectral complex domain data has been developed and studied. This algorithm is based on the complex domain block-matching 3D filter including the 3D Wiener arXiv:1907.03104v1 [eess.IV] 6 Jul 2019 A PREPRINT -JULY 9, 2019 filtering stage. The developed algorithm is applied and tuned to work in the singular value decomposition (SVD) eigenspace of reduced dimension. The accuracy and quantitative advantage of the new algorithm are demonstrated in simulation tests and in processing of the experimental data. It is shown that the algorithm is effective and provides reliable results even for highly noisy data.

show abstract

Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations

Cited by 278 publications

References 48 publications

Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution

Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution

Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

Hyperspectral phase imaging based on denoising in complex-valued eigensubspace

Contact Info

Product

Resources

About