Graph Attention in Attention Network for Image Denoising
- 21 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 53 (11) , 7077-7088
Abstract
Image denoising aims to remove the noise from noisy images. With the increasing complexity of the noise within the noisy images, current denoising methods cannot satisfactorily address this issue. This article proposes a graph attention in attention network (GAiA-Net) for image denoising. First, we introduce a novel approach to graph construction for the GAiA-Net. In the process of such graph construction, the noisy images are divided into patches to formulate the nodes in a graph. The edges are initialized using $ k $ -nearest neighbors. Hence, through iterative transformation and learning, both the pixel-level and structure-level features can be captured by different information exchanges and aggregation within (pixel-level) and outside (structure-level) of the nodes, respectively. Second, we propose the graph attention in attention (GAiA) in the GAiA-Net. The proposed GAiA produces the pixel-level attention within nodes to be further induced to the nodes with various distances to generate the final attention. Therefore, our GAiA-Net can capture the long dependencies on both the pixel-level and structure-level features, which can effectively reduce the complex noise in the denoising process. Comprehensive experiments demonstrate that the proposed GAiA-Net produces state-of-the-art performances on both synthetic noise image and real noise image datasets. Especially, when experimenting on complex noisy Nam datasets, our GAiA-Net achieves a PSNR of 40.40 dB and SSIM of 0.989. These results prove the satisfactory potential and effectiveness of our GAiA-Net.Keywords
Funding Information
- NSFC Fund (62176077, 62206073)
- Shenzhen Key Technical Project (2022N001, 2020N046, 2022N063)
- Shenzhen Fundamental Research and Discipline Layout project (JCYJ20210324132210025)
- Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies (2022B1212010005)
- Guangdong Shenzhen joint Youth Fund (2021A151511074)
- Natural Science Foundation of Guangdong Province (2023A1515010893)
- Shenzhen Doctoral Initiation Technology Plan (RCBS20221008093222010)
This publication has 39 references indexed in Scilit:
- Collaborative Representation Cascade for Single-Image Super-ResolutionIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- Loss Functions for Image Restoration With Neural NetworksIEEE Transactions on Computational Imaging, 2016
- A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising2016
- Single-Image Super-Resolution by Subdictionary Coding and Kernel RegressionIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2016
- Single image super-resolution from transformed self-exemplars2015
- Image demosaicking by nonlocal adaptive thresholding2013
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- Fields of Experts: A Framework for Learning Image Priors2005
- A Non-Local Algorithm for Image Denoising2005