Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions
Image rain removal is extremely important since rain streaks can severely degrade the visibility which can decrease accuracy of many current computer vision algorithms. However, many deep-learning methods cannot adapt to the rain streak removal of different density labels, meanwhile retain the backg...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8931602/ |
| _version_ | 1819179348715896832 |
|---|---|
| author | Junsheng Wang Xiang Huang Shan Gai |
| author_facet | Junsheng Wang Xiang Huang Shan Gai |
| author_sort | Junsheng Wang |
| collection | DOAJ |
| description | Image rain removal is extremely important since rain streaks can severely degrade the visibility which can decrease accuracy of many current computer vision algorithms. However, many deep-learning methods cannot adapt to the rain streak removal of different density labels, meanwhile retain the background details. To address this problem, we propose a novel image rain removal algorithm (CAAN) based on deep cascaded network and dual-channel attention mechanism. As contextual information is very crucial for rain removal, hence firstly the dilated convolution kernels of different scale branches are used to extract features of different rain streak sizes. Then we applied residual attention module (LMSRAM) to guide the learned features to be discriminative and beneficial. Specifically, a novel cascaded sub-network is developed to propagate information from lower to higher layers and decrease the loss of detailed information. Finally, the dual channel attention mechanism is used to make feature fusion efficiently. The experimental results demonstrate that the proposed method achieves the state-of-the-art results compared to the prevailing methods in terms of both quantitative metrics and visual quality. The source code of our proposed CAAN can download from the personal website. https://github.com/baiyihan/CAAN. |
| first_indexed | 2024-12-22T21:57:01Z |
| format | Article |
| id | doaj.art-4feb0415390744389487748079221428 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T21:57:01Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4feb04153907443894877480792214282022-12-21T18:11:12ZengIEEEIEEE Access2169-35362019-01-01717884817886110.1109/ACCESS.2019.29590418931602Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather ConditionsJunsheng Wang0https://orcid.org/0000-0001-6139-1410Xiang Huang1https://orcid.org/0000-0001-5569-4255Shan Gai2School of Information Engineering, Nanchang Hangkong University, Nanchang, ChinaSchool of Information Engineering, Nanchang Hangkong University, Nanchang, ChinaSchool of Information Engineering, Nanchang Hangkong University, Nanchang, ChinaImage rain removal is extremely important since rain streaks can severely degrade the visibility which can decrease accuracy of many current computer vision algorithms. However, many deep-learning methods cannot adapt to the rain streak removal of different density labels, meanwhile retain the background details. To address this problem, we propose a novel image rain removal algorithm (CAAN) based on deep cascaded network and dual-channel attention mechanism. As contextual information is very crucial for rain removal, hence firstly the dilated convolution kernels of different scale branches are used to extract features of different rain streak sizes. Then we applied residual attention module (LMSRAM) to guide the learned features to be discriminative and beneficial. Specifically, a novel cascaded sub-network is developed to propagate information from lower to higher layers and decrease the loss of detailed information. Finally, the dual channel attention mechanism is used to make feature fusion efficiently. The experimental results demonstrate that the proposed method achieves the state-of-the-art results compared to the prevailing methods in terms of both quantitative metrics and visual quality. The source code of our proposed CAAN can download from the personal website. https://github.com/baiyihan/CAAN.https://ieeexplore.ieee.org/document/8931602/Cascaded networkdual attention mechanismlocal multi-scale residual attention moduleimage rain removal |
| spellingShingle | Junsheng Wang Xiang Huang Shan Gai Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions IEEE Access Cascaded network dual attention mechanism local multi-scale residual attention module image rain removal |
| title | Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions |
| title_full | Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions |
| title_fullStr | Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions |
| title_full_unstemmed | Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions |
| title_short | Single Image Rain Removal via Cascading Attention Aggregation Network on Challenging Weather Conditions |
| title_sort | single image rain removal via cascading attention aggregation network on challenging weather conditions |
| topic | Cascaded network dual attention mechanism local multi-scale residual attention module image rain removal |
| url | https://ieeexplore.ieee.org/document/8931602/ |
| work_keys_str_mv | AT junshengwang singleimagerainremovalviacascadingattentionaggregationnetworkonchallengingweatherconditions AT xianghuang singleimagerainremovalviacascadingattentionaggregationnetworkonchallengingweatherconditions AT shangai singleimagerainremovalviacascadingattentionaggregationnetworkonchallengingweatherconditions |