Deep Graph-Convolutional Image Denoising

Valsesia, Diego; Fracastoro, Giulia; Magli, Enrico

doi:10.1109/tip.2020.3013166

Cited by 138 publications

(57 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…N 3 Net [32] introduces the continuous deterministic relaxation of the KNN rule to neural network architectures by proposing a non-local processing layer. For the purpose of capturing self-smilar information, GCDN [33] employs graph convolution to create layers with hidden neurons having non-local receptive fields. By computing reliable feature correlations within a confined neighorbood and passing feature correlation messages between adjacent recurrent stages, NLRN [34] incorporates non-local operations into a recurrent neural network for image denosing.…”

Section: Incorporation Of Nss and Cnn Based Methodsmentioning

confidence: 99%

On Combining CNN With Non-Local Self-Similarity Based Image Denoising Methods

Yan

Guo

Xiao³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Despite the significant advances in convolutional neural network (CNN) based image denoising, the existing methods still cannot consistently outperform non-local self-similarity (NSS) based methods, especially on images with many repetitive structures. Although several studies have been given to incorporate NSS priors with CNN-based denoising,their improvement is generally insignificant when compared with the state-of-the-art CNN-based denoisers. In this paper, we suggest to combine CNN and NSS based methods for improved image denoising, resulting in an NSS-UNet architecture. Motivated by gradient descent inference of TNRD, both the current estimate and noisy observation are considered as the inputs to the CNN. To take the NSS prior into account, the result by NSS (e.g., BM3D or WNNM), is adopted as the initial estimate. And a modified UNet is presented for exploiting the multi-scale information. We evaluate the proposed method on three common testing datasets. The results clearly show that NSS-UNet outperforms the existing CNN and NSS based methods in terms of both PSNR index and visual quality.INDEX TERMS Non-local self-similarity, convolutional neural network, residual learning, image denoising.

show abstract

Section: Incorporation Of Nss and Cnn Based Methodsmentioning

confidence: 99%

On Combining CNN With Non-Local Self-Similarity Based Image Denoising Methods

Yan

Guo

Xiao³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A PG is formed by grouping the similar patches to a local patch in its neighborhoods. There has been proven that it is effective to use the patch group (PG) based NSS prior learning to denoise 16,17 . In our method, each local patch is extracted from an image with patch size.…”

Section: Blind Denoising Using Jplmentioning

confidence: 99%

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Xue

Feng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Most existing nonblind denoising approaches assumed the noise to be homogeneous white Gaussian distribution with known intensity. However, it is difficult to know beforehand or model accurately real‐world noises with complex hybrid distribution and noise intensity. In this paper, active joint prior learning (JPL) is proposed for real‐world ISAR image blind denoising. (1) To explore strong model hierarchy and components relationship automatically, a novel graphical Dirichlet mixture process (GDMP) model is developed, where the latent representations and component hyperparameters are jointly learned from each other. (2) A multiscale joint learning strategy (MJLS) is proposed to take advantage of both the optimization‐ and discriminative learning‐based capabilities. The external noiseless, internal noisy image information and their relationships are jointly explored simultaneously. (3) Low‐rank weighted sparse learning (LWSL) is proposed to learn sparse discriminative correlation components for robust prior learning, and latent low‐rank embedding for GDMP patterns self‐adaptive inference. Extensive experimental results on ISAR image datasets demonstrate the effectiveness of the proposed model for both synthesis and real‐world noisy ISAR images, and the proposed method outperforms the state‐of‐the‐art denoising methods.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Recently, the notion of deep learning has gained considerable popularity in the research realm of computer vision and pattern recognition (Badrinarayanan, Kendall, & Cipolla, 2017 ; Bao et al, 2020 ), and deep graph learning has achieved unprecedented success in numerous applications (Chang et al, 2020 ; Valsesia, Fracastoro, & Magli, 2020 ). As the brain network can be described as a graph, in which parcellated brain regions are treated as nodes and connectivity metrics between these regions as edges, deep graph learning can be naturally extended to characterizations of intrinsic features of brain functional connectivity (Jiang et al, 2020 ; Zhang, Kong, Wu, Coatrieux, & Shu, 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Spatio‐temporal graph convolutional network for diagnosis and treatment response prediction of major depressive disorder from functional connectivity

Kong

Gao

Yue

et al. 2021

Human Brain Mapping

View full text Add to dashboard Cite

The pathophysiology of major depressive disorder (MDD) has been explored to be highly associated with the dysfunctional integration of brain networks. It is therefore imperative to explore neuroimaging biomarkers to aid diagnosis and treatment. In this study, we developed a spatiotemporal graph convolutional network (STGCN) framework to learn discriminative features from functional connectivity for automatic diagnosis and treatment response prediction of MDD. Briefly, dynamic functional networks were first obtained from the resting-state fMRI with the sliding temporal window method. Secondly, a novel STGCN approach was proposed by introducing the modules of spatial graph attention convolution (SGAC) and temporal fusion. A novel SGAC was proposed to improve the feature learning ability and special anatomy prior guided pooling was developed to enable the feature dimension reduction.A temporal fusion module was proposed to capture the dynamic features of functional connectivity between adjacent sliding windows. Finally, the STGCN proposed approach was utilized to the tasks of diagnosis and antidepressant treatment response prediction for MDD. Performances of the framework were comprehensively examined with large cohorts of clinical data, which demonstrated its effectiveness in classifying MDD patients and predicting the treatment response. The sound performance suggests the potential of the STGCN for the clinical use in diagnosis and treatment prediction.

show abstract

Deep Graph-Convolutional Image Denoising

Cited by 138 publications

References 44 publications

On Combining CNN With Non-Local Self-Similarity Based Image Denoising Methods

On Combining CNN With Non-Local Self-Similarity Based Image Denoising Methods

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Spatio‐temporal graph convolutional network for diagnosis and treatment response prediction of major depressive disorder from functional connectivity

Contact Info

Product

Resources

About