2022
DOI: 10.1109/tsp.2022.3223552
|View full text |Cite
|
Sign up to set email alerts
|

Untrained Graph Neural Networks for Denoising

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
2
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 14 publications
(7 citation statements)
references
References 43 publications
0
7
0
Order By: Relevance
“…Through deep learning techniques, neural networks can automatically learn features and patterns in images to achieve more accurate noise reduction. Among them, Convolutional Neural Network (CNN) is the most widely used type of neural network, which performs well in image processing tasks [12,13]. The core idea of neural network is to learn and extract image features at various scales through a series of convolutional, pooling and fully connected layers, so as to achieve image noise reduction.…”
Section: Methods Based On Machine Learningmentioning
confidence: 99%
“…Through deep learning techniques, neural networks can automatically learn features and patterns in images to achieve more accurate noise reduction. Among them, Convolutional Neural Network (CNN) is the most widely used type of neural network, which performs well in image processing tasks [12,13]. The core idea of neural network is to learn and extract image features at various scales through a series of convolutional, pooling and fully connected layers, so as to achieve image noise reduction.…”
Section: Methods Based On Machine Learningmentioning
confidence: 99%
“…Nevertheless, not only is DeepL usually training-data hungry and computationally heavy, but concerns were also raised in [23] about instabilities in medical-image reconstruction. Deep image priors (DIP) [24] and untrained neural networks offer user-defined priors to alleviate the need for massive training data, and have been used in signal recovery [25], [26] and accelerated medical imaging [27], [28].…”
Section: Introductionmentioning
confidence: 99%
“…Complex signal denoising has been demonstrated in automotive applications based on spectrograms being fed as complex-valued images into a CNN [39], but this is simulated additive white Gaussian noise which is not correlated. In [40], untrained graph neural networks directly estimate the raw signal parameters faster than noise alike one-shot learning showing promise as it has been validated over simulated and real data. This area, however, for complex signals is still undergoing development.…”
Section: Introductionmentioning
confidence: 99%