MRDA-Net: Multiscale Residual Dense Attention Network for Image Denoising

Zhu, Jianhu; Yao, Cheng; Tang, Yibin; Gao, Yuan; Lin, Zhenzhi; Hu, Hongmei

doi:10.1007/978-3-031-06767-9_18

Cited by 3 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two types of attention mechanisms are commonly used: (1) attention from different networks and (2) attention within the same network. The former emphasizes the extraction of complex background features from different scales, as in [33], which designs a feature aggregation module with dual attention blocks to effectively generate multiscale feature maps that are then aggregated through concatenation. The latter, on the other hand, emphasizes the influence between different branches of the same network and guides the feature fusion of the previous stage.…”

Section: Attention Mechanism For Image Denoisingmentioning

confidence: 99%

Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising

Bian,

He,

et al. 2023

Electronics

View full text Add to dashboard Cite

In the field of image denoising, convolutional neural networks (CNNs) have become increasingly popular due to their ability to learn effective feature representations from large amounts of data. In the field of image denoising, CNNs are widely used to improve performance. However, increasing network depth can weaken the influence of shallow layers on deep layers, especially for complex denoising tasks such as real denoising and blind denoising, where conventional networks fail to achieve high-quality results. To address this issue, this paper proposes a hybrid dilated convolution-based denoising network (AMDNet) that incorporates attention mechanisms. In specific, AMDNet consists of four modules: the sparse module (SM), the feature fusion module (FFM), the attention guidance module (AGM), and the image residual module (IRM). The SM employs hybrid dilated convolution to extract local features, while the FFM is used to integrate global and local features. The AGM accurately extracts noise information hidden in complex backgrounds. Finally, the IRM reconstructs images in a residual manner to obtain high-quality results after denoising. AMDNet has the following features: (1) The sparse mechanism in hybrid dilated convolution enables better extraction of local features, enhancing the network’s ability to capture noise information. (2) The feature fusion module, through long-range connections, fully integrates global and local features, improving the performance of the model; (3) the attention module is ingeniously designed to precisely extract features in complex backgrounds. The experimental results demonstrate that AMDNet achieves outstanding performance on three tasks (Gaussian noise, real noise, and blind denoising).

show abstract

Section: Attention Mechanism For Image Denoisingmentioning

confidence: 99%