RDASNet: Image Denoising via a Residual Dense Attention Similarity Network
In recent years, thanks to the performance advantages of convolutional neural networks (CNNs), CNNs have been widely used in image denoising. However, most of the CNN-based image-denoising models cannot make full use of the redundancy of image data, which limits the expressiveness of the model. We p...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/3/1486 |
| _version_ | 1797623168506003456 |
|---|---|
| author | Haowu Tao Wenhua Guo Rui Han Qi Yang Jiyuan Zhao |
| author_facet | Haowu Tao Wenhua Guo Rui Han Qi Yang Jiyuan Zhao |
| author_sort | Haowu Tao |
| collection | DOAJ |
| description | In recent years, thanks to the performance advantages of convolutional neural networks (CNNs), CNNs have been widely used in image denoising. However, most of the CNN-based image-denoising models cannot make full use of the redundancy of image data, which limits the expressiveness of the model. We propose a new image-denoising model that aims to extract the local features of the image through CNN and focus on the global information of the image through the attention similarity module (ASM), especially the global similarity details of the image. Furthermore, dilation convolution is used to enlarge the receptive field to better focus on the global features. Moreover, avg-pooling is used to smooth and suppress noise in the ASM to further improve model performance. In addition, through global residual learning, the effect is enhanced from shallow to deep layers. A large number of experiments show that our proposed model has a better image-denoising effect, including quantitative and visual results. It is more suitable for complex blind noise and real images. |
| first_indexed | 2024-03-11T09:24:50Z |
| format | Article |
| id | doaj.art-1bbaf79f01584a6e84853d67cffc7383 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T09:24:50Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1bbaf79f01584a6e84853d67cffc73832023-11-16T18:01:55ZengMDPI AGSensors1424-82202023-01-01233148610.3390/s23031486RDASNet: Image Denoising via a Residual Dense Attention Similarity NetworkHaowu Tao0Wenhua Guo1Rui Han2Qi Yang3Jiyuan Zhao4School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaIn recent years, thanks to the performance advantages of convolutional neural networks (CNNs), CNNs have been widely used in image denoising. However, most of the CNN-based image-denoising models cannot make full use of the redundancy of image data, which limits the expressiveness of the model. We propose a new image-denoising model that aims to extract the local features of the image through CNN and focus on the global information of the image through the attention similarity module (ASM), especially the global similarity details of the image. Furthermore, dilation convolution is used to enlarge the receptive field to better focus on the global features. Moreover, avg-pooling is used to smooth and suppress noise in the ASM to further improve model performance. In addition, through global residual learning, the effect is enhanced from shallow to deep layers. A large number of experiments show that our proposed model has a better image-denoising effect, including quantitative and visual results. It is more suitable for complex blind noise and real images.https://www.mdpi.com/1424-8220/23/3/1486image denoisingCNNattention similarity moduleresidual dense block |
| spellingShingle | Haowu Tao Wenhua Guo Rui Han Qi Yang Jiyuan Zhao RDASNet: Image Denoising via a Residual Dense Attention Similarity Network Sensors image denoising CNN attention similarity module residual dense block |
| title | RDASNet: Image Denoising via a Residual Dense Attention Similarity Network |
| title_full | RDASNet: Image Denoising via a Residual Dense Attention Similarity Network |
| title_fullStr | RDASNet: Image Denoising via a Residual Dense Attention Similarity Network |
| title_full_unstemmed | RDASNet: Image Denoising via a Residual Dense Attention Similarity Network |
| title_short | RDASNet: Image Denoising via a Residual Dense Attention Similarity Network |
| title_sort | rdasnet image denoising via a residual dense attention similarity network |
| topic | image denoising CNN attention similarity module residual dense block |
| url | https://www.mdpi.com/1424-8220/23/3/1486 |
| work_keys_str_mv | AT haowutao rdasnetimagedenoisingviaaresidualdenseattentionsimilaritynetwork AT wenhuaguo rdasnetimagedenoisingviaaresidualdenseattentionsimilaritynetwork AT ruihan rdasnetimagedenoisingviaaresidualdenseattentionsimilaritynetwork AT qiyang rdasnetimagedenoisingviaaresidualdenseattentionsimilaritynetwork AT jiyuanzhao rdasnetimagedenoisingviaaresidualdenseattentionsimilaritynetwork |