DLRP: Learning Deep Low-Rank Prior for Remotely Sensed Image Denoising

Huang, Zhenghua; Wang, Zhicheng; Zhu, Zifan; Zhang, Yaozong; Hao, Fang

doi:10.1109/lgrs.2022.3167401

Cited by 15 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sun et al [74] used low-rank representation and a CNN denoiser (LRR-CNN) to form a hyperspectral image denoising model. Huang et al [75] proposed a nonlocal self-similar (NSS) block-based deep image denoising scheme, designated the deep low-rank prior (DLRP), to achieve efficient performance. Xu et al [76] developed an end-to-end deep architecture to follow the process of sparse-representation-based image restoration.…”

Section: Deep Unfoldingmentioning

confidence: 99%

“…where E(•) is a function to compute the mean value of a matrix. Generally, this constructed data matrix X i is sparse and can be characterized by a coding coefficient vector α i with a given or learned dictionary D [75]. That is, X i = R i x = Dα i .…”

Section: Model Generationmentioning

confidence: 99%

“…Comparison approaches' selection: To check the effectiveness of the proposed MD 3 scheme and its advantages, three types of methods described in Section 2, model-based (NCSR [43] and WSSR [6]), DNN-based ( [18]), and deep-unfolding-based (DKSVD [68], DCDicL [73], LRR-CNN [74], and DLRP [75]), were selected to be utilized, and their results were compared regarding quantization and qualification.…”

Section: Experimental Preparationmentioning

confidence: 99%

See 2 more Smart Citations

MD3: Model-Driven Deep Remotely Sensed Image Denoising

et al. 2023

View full text Add to dashboard Cite

Remotely sensed images degraded by additive white Gaussian noise (AWGN) have low-level vision, resulting in a poor analysis of their contents. To reduce AWGN, two types of denoising strategies, sparse-coding-model-based and deep-neural-network-based (DNN), are commonly utilized, which have their respective merits and drawbacks. For example, the former pursue enjoyable performance with a high computational burden, while the latter have powerful capacity in completing a specified task efficiently, but this limits their application range. To combine their merits for improving performance efficiently, this paper proposes a model-driven deep denoising (MD3) scheme. To solve the MD3 model, we first decomposed it into several subproblems by the alternating direction method of multipliers (ADMM). Then, the denoising subproblems are replaced by different learnable denoisers, which are plugged into the unfolded MD3 model to efficiently produce a stable solution. Both quantitative and qualitative results validate that the proposed MD3 approach is effective and efficient, while it has a more powerful ability in generating enjoyable denoising performance and preserving rich textures than other advanced methods.

show abstract

Section: Deep Unfoldingmentioning

confidence: 99%

Section: Model Generationmentioning

confidence: 99%

Section: Experimental Preparationmentioning

confidence: 99%

See 1 more Smart Citation

MD3: Model-Driven Deep Remotely Sensed Image Denoising

et al. 2023

View full text Add to dashboard Cite

show abstract

“… Patch-based methods: In these methods, a noisy image is initially decomposed into a group of patches. Then, the homogeneous patches are selected via various statistical techniques for noise level estimation [ 25 , 26 , 27 ]. For example, Pyatykh et al [ 28 ] proposed a method based on principal component analysis (PCA), which viewed the smallest eigenvalue of the image patch covariance matrix as the noise level.…”

Section: Literature Reviewmentioning

confidence: 99%

Blind Additive Gaussian White Noise Level Estimation from a Single Image by Employing Chi-Square Distribution

Wang

Zhu

et al. 2022

Entropy

Self Cite

View full text Add to dashboard Cite

The additive Gaussian white noise (AGWN) level in real-life images is usually unknown, for which the empirical setting will make the denoising methods over-smooth fine structures or remove noise incompletely. The previous noise level estimation methods are easily lost in accurately estimating them from images with complicated structures. To cope with this issue, we propose a novel noise level estimation scheme based on Chi-square distribution, including the following key points: First, a degraded image is divided into many image patches through a sliding window. Then, flat patches are selected by using a patch selection strategy on the gradient maps of those image patches. Next, the initial noise level is calculated by employing Chi-square distribution on the selected flat patches. Finally, the stable noise level is optimized by an iterative strategy. Quantitative, with association, to qualitative results of experiments on synthetic real-life images validate that the proposed noise level estimation method is effective and even superior to the state-of-the-art methods. Extensive experiments on noise removal using BM3D further illustrate that the proposed noise level estimation method is more beneficial for achieving favorable denoising performance with detail preservation.

show abstract

“…Remote sensing images can capture rich geographic information with high resolution and rich spectral information 1 – 4 They have been widely used in many applications, such as monitoring and forecasting meteorological climate, land resource exploration, and military operations 5 – 9 However, stripe noise is a common degradation in remote sensing images, which not only affects the visual effect but also limits further high-level applications based on remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

Remote sensing image destriping based on variable weight and group sparse regularization

Jiang

Huang

Bai³

et al. 2023

J. Appl. Rem. Sens.

Self Cite

View full text Add to dashboard Cite

.Striping effects are common phenomena in remote sensing images, and they significantly limit subsequent applications. Although many destriping approaches have been developed, there aren’t many that can completely eliminate complex stripes with varying levels of strength. To address this issue, we propose a stripe removal model based on a variable weight coefficient and group sparse regularization. Specifically, rather than a single scalar for the stripes in most approaches, different weights are set for different stripe rows to estimate the stripes with varying intensities. An adaptive method to estimate the weight matrix is proposed. On the other hand, group sparsity regularization is employed to constrain the entire stripe. In addition, region weights are designed for regions with different stripe characteristics. The alternating direction multiplier method is employed to solve the proposed model by alternating minimization. Experimental results based on simulation and real data demonstrate that the proposed model outperforms other advanced methods in terms of stripe noise removal and image detail preservation.

show abstract

DLRP: Learning Deep Low-Rank Prior for Remotely Sensed Image Denoising

Cited by 15 publications

References 36 publications

MD3: Model-Driven Deep Remotely Sensed Image Denoising

MD3: Model-Driven Deep Remotely Sensed Image Denoising

Blind Additive Gaussian White Noise Level Estimation from a Single Image by Employing Chi-Square Distribution

Remote sensing image destriping based on variable weight and group sparse regularization

Contact Info

Product

Resources

About