Hyperspectral image denoising based on global and non-local low-rank factorizations

Zhuang, Lina; Bioucas-Dias, José M.

doi:10.1109/icip.2017.8296612

Cited by 32 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conduct several groups of experiments on both simulated and real images to demonstrate the performance of the proposed method compared with some existing typical algorithms. The following representative HSI denoising methods are selected as competitors, i.e., low-rank matrix recovery (LRMR) [18], TV-regularized low-rank matrix factorization (LRTV) [31], fast hyperspectral image denoising based on low-rank and sparse representations (FastHyDe) [46], global matrix factorization and to local tensor factorizations method (GLF) [41], spatial-spectral total variation regularized local low-rank matrix recovery (LLRGTV) [37], Moreau-enhanced total variation regularized local low-rank matrix recovery (LLRMTV) [43], and non-local meets global (NM-meet) denoising paradigm [42]. LRMR is one of the representative methods to recover HSI by the global low rank and sparse optimization.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…The projection-based method is first presented by Zhuang and Bioucas-Dias [40] for Gaussian and Poissonian noise removal. In [41], low-rank tensor factorization is further introduced into the subspace representation framework for HSI self-similar property enhancement. He et al [42] transfer the non-local denoising to the projected HSI instead of the original spectral dimension to reduce processing cost.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising

2020

View full text Add to dashboard Cite

Hyperspectral images (HSIs) denoising aims at recovering noise-free images from noisy counterparts to improve image visualization. Recently, various prior knowledge has attracted much attention in HSI denoising, e.g., total variation (TV), low-rank, sparse representation, and so on. However, the computational cost of most existing algorithms increases exponentially with increasing spectral bands. In this paper, we fully take advantage of the global spectral correlation of HSI and design a unified framework named subspace-based Moreau-enhanced total variation and sparse factorization (SMTVSF) for multispectral image denoising. Specifically, SMTVSF decomposes an HSI image into the product of a projection matrix and abundance maps, followed by a ‘Moreau-enhanced’ TV (MTV) denoising step, i.e., a nonconvex regularizer involving the Moreau envelope mechnisam, to reconstruct all the abundance maps. Furthermore, the schemes of subspace representation penalizing the low-rank characteristic and ℓ 2 , 1 -norm modelling the structured sparse noise are embedded into our denoising framework to refine the abundance maps and projection matrix. We use the augmented Lagrange multiplier (ALM) algorithm to solve the resulting optimization problem. Extensive results under various noise levels of simulated and real hypspectral images demonstrate our superiority against other competing HSI recovery approaches in terms of quality metrics and visual effects. In addition, our method has a huge advantage in computational efficiency over many competitors, benefiting from its removal of most spectral dimensions during iterations.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising

2020

View full text Add to dashboard Cite

show abstract

“…As images in eigen-space (i.e., linear combinations of original bands), rows of Z have the same characteristic, i.e., self-similarity, as the original image [5]. Self-similarity of rows of Z is exploited here for solving problem (12). Instead of investing efforts in tailoring regularizers promoting self-similar images, we use directly a state-of-the-art denoiser applied to Z t .…”

Section: Cost Functionmentioning

confidence: 99%

“…We can shrink the transformation coefficients to attenuate the noise and invert the transform to generate image estimates. Furthermore, it is expected that the sparser the representation is, the more Gaussian noise we can remove [11], [12] from transform domains.…”

Section: Introductionmentioning

confidence: 99%

“…We come to a conclusion that a strong and proper prior of the clean image is crucial for mixed noise removal. The priors of low rankness in spectral domain and self-similarity in spatial domain underlie the state-of-the-art HSI Gaussian denoisers, e.g., FastHyDe [5], GLF [12], and NG-meet [33]. This article exploits the characteristics of low rankness and self-similarity for mixed noise removal.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hyperspectral Mixed Noise Removal By $\ell _1$-Norm-Based Subspace Representation

Zhuang

2020

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

Self Cite

View full text Add to dashboard Cite

This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact and sparse HSI representation based on its low-rank and self-similarity characteristics. In order to deal with mixed noise having a complex statistical distribution, we propose to use the robust 1 data fidelity instead of using the 2 data fidelity, which is commonly employed for Gaussian noise removal. In a series of experiments with simulated and real datasets, the proposed method competes with state-of-the-art methods, yielding better results for mixed noise removal.

show abstract

Hyperspectral Image Denoising Based on Dual Low-Rank Structure Preservation

Tang

Leng

Cheng

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Hyperspectral image denoising based on global and non-local low-rank factorizations

Cited by 32 publications

References 13 publications

Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising

Moreau-Enhanced Total Variation and Subspace Factorization for Hyperspectral Denoising

Hyperspectral Mixed Noise Removal By $\ell _1$-Norm-Based Subspace Representation

Hyperspectral Image Denoising Based on Dual Low-Rank Structure Preservation

Contact Info

Product

Resources

About