Recurrent Attention Dense Network for Single Image De-Raining
The problem of single image rain removal has attracted tremendous attention as the blurry images caused by rain streaks can degrade the performance of many computer vision algorithms. Although deep learning based de-raining methods have achieved a significant success, there are still unresolved issu...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9119398/ |
| _version_ | 1818479787694358528 |
|---|---|
| author | Guoqiang Chai Zhaoba Wang Guodong Guo Youxing Chen Yong Jin Wei Wang Xia Zhao |
| author_facet | Guoqiang Chai Zhaoba Wang Guodong Guo Youxing Chen Yong Jin Wei Wang Xia Zhao |
| author_sort | Guoqiang Chai |
| collection | DOAJ |
| description | The problem of single image rain removal has attracted tremendous attention as the blurry images caused by rain streaks can degrade the performance of many computer vision algorithms. Although deep learning based de-raining methods have achieved a significant success, there are still unresolved issues in terms of the performance. In this work, we propose a novel recurrent attention dense network (RADN) for single image de-raining. In RADN, a region-level attention module is first utilized to identify rain streaks regions for the subsequent removal task. As rain streaks have different sizes and shapes, a modified densely connected convolutional network (DenseNet) with dilation convolutions and reduced channels is developed for an effective feature representation. The rain streaks are removed stage by stage and a Gate Recurrent Unit (GRU) is incorporated to deliver useful information from previous stages to later stages for a better performance. Qualitative and quantitative evaluations on both synthetic and real-world datasets demonstrate that the proposed approach can achieve a remarkable performance in comparison with the state-of-the-art methods for single image rain removal. |
| first_indexed | 2024-12-10T11:15:22Z |
| format | Article |
| id | doaj.art-a3a452a923c14407a132da580db01b81 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-10T11:15:22Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-a3a452a923c14407a132da580db01b812022-12-22T01:51:13ZengIEEEIEEE Access2169-35362020-01-01811127811128810.1109/ACCESS.2020.30031269119398Recurrent Attention Dense Network for Single Image De-RainingGuoqiang Chai0https://orcid.org/0000-0003-0465-280XZhaoba Wang1https://orcid.org/0000-0002-0143-8149Guodong Guo2https://orcid.org/0000-0001-9583-0055Youxing Chen3https://orcid.org/0000-0002-8915-2689Yong Jin4https://orcid.org/0000-0002-7664-1416Wei Wang5https://orcid.org/0000-0001-9474-6214Xia Zhao6https://orcid.org/0000-0003-1965-957XSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaSchool of Information and Communication Engineering, North University of China, Taiyuan, ChinaThe problem of single image rain removal has attracted tremendous attention as the blurry images caused by rain streaks can degrade the performance of many computer vision algorithms. Although deep learning based de-raining methods have achieved a significant success, there are still unresolved issues in terms of the performance. In this work, we propose a novel recurrent attention dense network (RADN) for single image de-raining. In RADN, a region-level attention module is first utilized to identify rain streaks regions for the subsequent removal task. As rain streaks have different sizes and shapes, a modified densely connected convolutional network (DenseNet) with dilation convolutions and reduced channels is developed for an effective feature representation. The rain streaks are removed stage by stage and a Gate Recurrent Unit (GRU) is incorporated to deliver useful information from previous stages to later stages for a better performance. Qualitative and quantitative evaluations on both synthetic and real-world datasets demonstrate that the proposed approach can achieve a remarkable performance in comparison with the state-of-the-art methods for single image rain removal.https://ieeexplore.ieee.org/document/9119398/Image de-rainingDenseNetdeep learning |
| spellingShingle | Guoqiang Chai Zhaoba Wang Guodong Guo Youxing Chen Yong Jin Wei Wang Xia Zhao Recurrent Attention Dense Network for Single Image De-Raining IEEE Access Image de-raining DenseNet deep learning |
| title | Recurrent Attention Dense Network for Single Image De-Raining |
| title_full | Recurrent Attention Dense Network for Single Image De-Raining |
| title_fullStr | Recurrent Attention Dense Network for Single Image De-Raining |
| title_full_unstemmed | Recurrent Attention Dense Network for Single Image De-Raining |
| title_short | Recurrent Attention Dense Network for Single Image De-Raining |
| title_sort | recurrent attention dense network for single image de raining |
| topic | Image de-raining DenseNet deep learning |
| url | https://ieeexplore.ieee.org/document/9119398/ |
| work_keys_str_mv | AT guoqiangchai recurrentattentiondensenetworkforsingleimagederaining AT zhaobawang recurrentattentiondensenetworkforsingleimagederaining AT guodongguo recurrentattentiondensenetworkforsingleimagederaining AT youxingchen recurrentattentiondensenetworkforsingleimagederaining AT yongjin recurrentattentiondensenetworkforsingleimagederaining AT weiwang recurrentattentiondensenetworkforsingleimagederaining AT xiazhao recurrentattentiondensenetworkforsingleimagederaining |