Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising
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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/18/3770 |
| _version_ | 1797580427374886912 |
|---|---|
| author | Shengqin Bian Xinyu He Zhengguang Xu Lixin Zhang |
| author_facet | Shengqin Bian Xinyu He Zhengguang Xu Lixin Zhang |
| author_sort | Shengqin Bian |
| collection | DOAJ |
| description | 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). |
| first_indexed | 2024-03-10T22:50:49Z |
| format | Article |
| id | doaj.art-06a407d300cc4a8f9d75db28f1751c4c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T22:50:49Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-06a407d300cc4a8f9d75db28f1751c4c2023-11-19T10:21:06ZengMDPI AGElectronics2079-92922023-09-011218377010.3390/electronics12183770Hybrid Dilated Convolution with Attention Mechanisms for Image DenoisingShengqin Bian0Xinyu He1Zhengguang Xu2Lixin Zhang3School of Automation, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation, University of Science and Technology Beijing, Beijing 100083, ChinaSchool of Automation, University of Science and Technology Beijing, Beijing 100083, ChinaIn 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).https://www.mdpi.com/2079-9292/12/18/3770image denoisinghybrid dilated convolutionattention mechanismblind denoising |
| spellingShingle | Shengqin Bian Xinyu He Zhengguang Xu Lixin Zhang Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising Electronics image denoising hybrid dilated convolution attention mechanism blind denoising |
| title | Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising |
| title_full | Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising |
| title_fullStr | Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising |
| title_full_unstemmed | Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising |
| title_short | Hybrid Dilated Convolution with Attention Mechanisms for Image Denoising |
| title_sort | hybrid dilated convolution with attention mechanisms for image denoising |
| topic | image denoising hybrid dilated convolution attention mechanism blind denoising |
| url | https://www.mdpi.com/2079-9292/12/18/3770 |
| work_keys_str_mv | AT shengqinbian hybriddilatedconvolutionwithattentionmechanismsforimagedenoising AT xinyuhe hybriddilatedconvolutionwithattentionmechanismsforimagedenoising AT zhengguangxu hybriddilatedconvolutionwithattentionmechanismsforimagedenoising AT lixinzhang hybriddilatedconvolutionwithattentionmechanismsforimagedenoising |