Nonconvex Structural Sparsity Residual Constraint for Image Restoration

Zha, Zhiyuan; Yuan, Xin; Wen, Bihan; Zhang, Jiachao; Zhu, Ce

doi:10.1109/tcyb.2021.3084931

Cited by 14 publications

(13 citation statements)

References 76 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where 𝜆 1 > 0 and 𝜆 2 ≥ 0 are the tradeoff parameters for group sparsity prior and side prior, respectively. If 𝜆 2 = 0, problem (15) is equal to problem (8). Instead of separately executing problem (15) on each group of similar patches, it can be extended and accomplished on all patches of Y.…”

Section: Formulation Of Side Group Sparse Coding Modelmentioning

confidence: 99%

“…If 𝜆 2 = 0, problem (15) is equal to problem (8). Instead of separately executing problem (15) on each group of similar patches, it can be extended and accomplished on all patches of Y. Let Z ∈ ℝ n×N be all patches of Y, and 𝚪 be the similarity matrix for all patches.…”

Section: Formulation Of Side Group Sparse Coding Modelmentioning

confidence: 99%

“…The sparsity prior is commonly carried out through sparse coding (SC). Benefiting from dictionary learning, such as K‐SVD [11], SC based image denoising algorithms achieve the state‐of‐the‐art results at the time, such as group sparse coding (GSC) [12], multiscale sparse coding [13], centered sparse coding [14], and residual sparse coding [15]. In addition, SC has also been extended into other image restoration tasks, such as image debluring [16] and image super‐resolution [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep side group sparse coding network for image denoising

Yin

Wang

2022

IET Image Processing

View full text Add to dashboard Cite

Recently, deep learning has made significant progress in image denoising. However, most of existing deep learning based methods are purely data‐driven, without considering the knowledge of image denoising. Moreover, the parameters of deep denoising network are not explainable. According to these issues, this paper proposes a deep side group sparse coding network for image denoising, named a side group sparse coding (SGSC)‐Net. First, SGSC model for image denoising by exploiting prior information regarding the group sparse coefficients consistency is developed. Specifically, the side information is constructed as the weighted combination of intermediate estimations, and updated iteratively. Then, the optimisation solution of SGSC model is turned into a deep neural network using deep unfolding, that is, SGSC‐Net. The computational path of SGSC‐Net fully follows the iterations of optimisation solution, and consequently the network parameters are interpretable. Furthermore, the design of SGSC‐Net employs the insight of SGSC denoising model. The experimental results on well‐known datasets quantitatively and qualitatively demonstrate that SGSC‐Net is competitive to existing deep unfolding‐based and typical deep neural network‐based methods.

show abstract

Section: Formulation Of Side Group Sparse Coding Modelmentioning

confidence: 99%

Section: Formulation Of Side Group Sparse Coding Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep side group sparse coding network for image denoising

Yin

Wang

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Evidence demonstrates that image priors are the foundation for image restoration, including total variation (TV) [5][6][7], sparsity [2,8], low-rank [9][10][11], and deep image prior [12][13][14][15][16][17][18][19][20]. Particularly, sparsity prior is considered as one of the most remarkable for natural images [2,8,[21][22][23][24]. On the basis of the strategies for manipulating sparsity prior, current algorithms are roughly divided into two classes, that is, patch- [2,25,26] and group-based approaches [8,22,[27][28][29], where the former ones independently perform image restoration for each patch, and the latter ones execute restoration task for each group of patches.…”

Section: Introductionmentioning

confidence: 99%

“…To tackle this problem, the residual models [8,22] assume that the group of similar patches exist the truth representation, where the learned representation should not deviate from the truth one. In contrast to GSR, the residual model is much more difficult to train since it needs to estimate the truth representation, which is also the significant difference among various algorithms.…”

Section: Introductionmentioning

confidence: 99%

Image restoration with group sparse representation and low‐rank group residual learning

Cai,

Xie,

Deng

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Image restoration, as a fundamental research topic of image processing, is to reconstruct the original image from degraded signal using the prior knowledge of image. Group sparse representation (GSR) is powerful for image restoration; it however often leads to undesirable sparse solutions in practice. In order to improve the quality of image restoration based on GSR, the sparsity residual model expects the representation learned from degraded images to be as close as possible to the true representation. In this article, a group residual learning based on low‐rank self‐representation is proposed to automatically estimate the true group sparse representation. It makes full use of the relation among patches and explores the subgroup structures within the same group, which makes the sparse residual model have better interpretation furthermore, results in high‐quality restored images. Extensive experimental results on two typical image restoration tasks (image denoising and deblocking) demonstrate that the proposed algorithm outperforms many other popular or state‐of‐the‐art image restoration methods.

show abstract