Denseformer for Single Image Deraining
Image is one of the most important forms of information expression in multimedia. It is the key factor to determine the visual effect of multimedia software. As an image restoration task, image deraining can effectively restore the original information of the image, which is conducive to the downstr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2023-12-01
|
| Series: | International Journal of Applied Mathematics and Computer Science |
| Subjects: | |
| Online Access: | https://doi.org/10.34768/amcs-2023-0046 |
| _version_ | 1797375845617106944 |
|---|---|
| author | Wang Tianming Wang Kaige Li Qing |
| author_facet | Wang Tianming Wang Kaige Li Qing |
| author_sort | Wang Tianming |
| collection | DOAJ |
| description | Image is one of the most important forms of information expression in multimedia. It is the key factor to determine the visual effect of multimedia software. As an image restoration task, image deraining can effectively restore the original information of the image, which is conducive to the downstream task. In recent years, with the development of deep learning technology, CNN and Transformer structures have shone brightly in computer vision. In this paper, we summarize the key to success of these structures in the past, and on this basis, we introduce the concept of a layer aggregation mechanism to describe how to reuse the information of the previous layer to better extract the features of the current layer. Based on this layer aggregation mechanism, we build the rain removal network called DenseformerNet. Our network strengthens feature promotion and encourages feature reuse, allowing better information and gradient flow. Through a large number of experiments, we prove that our model is efficient and effective, and expect to bring some illumination to the future rain removal network. |
| first_indexed | 2024-03-08T19:30:07Z |
| format | Article |
| id | doaj.art-15f329c96f1c480b918033af58277fb6 |
| institution | Directory Open Access Journal |
| issn | 2083-8492 |
| language | English |
| last_indexed | 2024-03-08T19:30:07Z |
| publishDate | 2023-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | International Journal of Applied Mathematics and Computer Science |
| spelling | doaj.art-15f329c96f1c480b918033af58277fb62023-12-26T07:43:37ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922023-12-0133465166110.34768/amcs-2023-0046Denseformer for Single Image DerainingWang Tianming0Wang Kaige1Li Qing2aIntelligent Manufacturing Electronics Research Center, Institute of Microelectronics of the Chinese Academy of Sciences, 3 Beitu Cheng West Road, Chaoyang District, Beijing100029, ChinaaIntelligent Manufacturing Electronics Research Center, Institute of Microelectronics of the Chinese Academy of Sciences, 3 Beitu Cheng West Road, Chaoyang District, Beijing100029, ChinaaIntelligent Manufacturing Electronics Research Center, Institute of Microelectronics of the Chinese Academy of Sciences, 3 Beitu Cheng West Road, Chaoyang District, Beijing100029, ChinaImage is one of the most important forms of information expression in multimedia. It is the key factor to determine the visual effect of multimedia software. As an image restoration task, image deraining can effectively restore the original information of the image, which is conducive to the downstream task. In recent years, with the development of deep learning technology, CNN and Transformer structures have shone brightly in computer vision. In this paper, we summarize the key to success of these structures in the past, and on this basis, we introduce the concept of a layer aggregation mechanism to describe how to reuse the information of the previous layer to better extract the features of the current layer. Based on this layer aggregation mechanism, we build the rain removal network called DenseformerNet. Our network strengthens feature promotion and encourages feature reuse, allowing better information and gradient flow. Through a large number of experiments, we prove that our model is efficient and effective, and expect to bring some illumination to the future rain removal network.https://doi.org/10.34768/amcs-2023-0046artificial intelligenceconvolutional neural networkimage deraining |
| spellingShingle | Wang Tianming Wang Kaige Li Qing Denseformer for Single Image Deraining International Journal of Applied Mathematics and Computer Science artificial intelligence convolutional neural network image deraining |
| title | Denseformer for Single Image Deraining |
| title_full | Denseformer for Single Image Deraining |
| title_fullStr | Denseformer for Single Image Deraining |
| title_full_unstemmed | Denseformer for Single Image Deraining |
| title_short | Denseformer for Single Image Deraining |
| title_sort | denseformer for single image deraining |
| topic | artificial intelligence convolutional neural network image deraining |
| url | https://doi.org/10.34768/amcs-2023-0046 |
| work_keys_str_mv | AT wangtianming denseformerforsingleimagederaining AT wangkaige denseformerforsingleimagederaining AT liqing denseformerforsingleimagederaining |