An unsupervised generative adversarial network for single image deraining
Abstract As the basis of image processing, single image deraining has always been a significant and challenging issue. Due to the lack of real rainy images and corresponding clean images, most deraining networks are trained by synthetic datasets, which makes the output images unsatisfactory in real...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | IET Image Processing |
| Online Access: | https://doi.org/10.1049/ipr2.12301 |
| _version_ | 1828010578650595328 |
|---|---|
| author | Zhiying Song Yuting Guo Zifan Ma Ruocong Tang Linfeng Liu |
| author_facet | Zhiying Song Yuting Guo Zifan Ma Ruocong Tang Linfeng Liu |
| author_sort | Zhiying Song |
| collection | DOAJ |
| description | Abstract As the basis of image processing, single image deraining has always been a significant and challenging issue. Due to the lack of real rainy images and corresponding clean images, most deraining networks are trained by synthetic datasets, which makes the output images unsatisfactory in real applications. Besides, note that a heavy rainfall is typically accompanied with some fog. Although some deraining networks have been proposed to remove the rain streaks in the rainy images, the output images may still be blurred due to the accompanied fog. In this paper, these problems existing in single image deraining is comprehensively considered, and propose a Cycle‐Derain network based on an unsupervised attention‐guided mechanism. Specifically, the Cycle‐Derain network takes advantage of generative adversarial networks with two mappings and the cycle consistency loss to train both unpaired rainy images and rain‐free images. Moreover, it introduces an unsupervised attention‐guided mechanism and exploits the loop‐search positioning algorithm to deal with the details of rain and fog in images. Extensive experiments have been carried out, and the results show that the proposed Cycle‐Derain network is preferable compared with other deraining networks, especially in term of rainy image restoration. |
| first_indexed | 2024-04-10T09:02:08Z |
| format | Article |
| id | doaj.art-5bf94766c3834c1f952634f72299c02c |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-10T09:02:08Z |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-5bf94766c3834c1f952634f72299c02c2023-02-21T11:57:05ZengWileyIET Image Processing1751-96591751-96672021-11-0115133105311710.1049/ipr2.12301An unsupervised generative adversarial network for single image derainingZhiying Song0Yuting Guo1Zifan Ma2Ruocong Tang3Linfeng Liu4School of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing ChinaSchool of Science Nanjing University of Posts and Telecommunications Nanjing ChinaSchool of Electronic and Optical Engineering Nanjing University of Posts and Telecommunications Nanjing ChinaSchool of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing ChinaSchool of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing ChinaAbstract As the basis of image processing, single image deraining has always been a significant and challenging issue. Due to the lack of real rainy images and corresponding clean images, most deraining networks are trained by synthetic datasets, which makes the output images unsatisfactory in real applications. Besides, note that a heavy rainfall is typically accompanied with some fog. Although some deraining networks have been proposed to remove the rain streaks in the rainy images, the output images may still be blurred due to the accompanied fog. In this paper, these problems existing in single image deraining is comprehensively considered, and propose a Cycle‐Derain network based on an unsupervised attention‐guided mechanism. Specifically, the Cycle‐Derain network takes advantage of generative adversarial networks with two mappings and the cycle consistency loss to train both unpaired rainy images and rain‐free images. Moreover, it introduces an unsupervised attention‐guided mechanism and exploits the loop‐search positioning algorithm to deal with the details of rain and fog in images. Extensive experiments have been carried out, and the results show that the proposed Cycle‐Derain network is preferable compared with other deraining networks, especially in term of rainy image restoration.https://doi.org/10.1049/ipr2.12301 |
| spellingShingle | Zhiying Song Yuting Guo Zifan Ma Ruocong Tang Linfeng Liu An unsupervised generative adversarial network for single image deraining IET Image Processing |
| title | An unsupervised generative adversarial network for single image deraining |
| title_full | An unsupervised generative adversarial network for single image deraining |
| title_fullStr | An unsupervised generative adversarial network for single image deraining |
| title_full_unstemmed | An unsupervised generative adversarial network for single image deraining |
| title_short | An unsupervised generative adversarial network for single image deraining |
| title_sort | unsupervised generative adversarial network for single image deraining |
| url | https://doi.org/10.1049/ipr2.12301 |
| work_keys_str_mv | AT zhiyingsong anunsupervisedgenerativeadversarialnetworkforsingleimagederaining AT yutingguo anunsupervisedgenerativeadversarialnetworkforsingleimagederaining AT zifanma anunsupervisedgenerativeadversarialnetworkforsingleimagederaining AT ruocongtang anunsupervisedgenerativeadversarialnetworkforsingleimagederaining AT linfengliu anunsupervisedgenerativeadversarialnetworkforsingleimagederaining AT zhiyingsong unsupervisedgenerativeadversarialnetworkforsingleimagederaining AT yutingguo unsupervisedgenerativeadversarialnetworkforsingleimagederaining AT zifanma unsupervisedgenerativeadversarialnetworkforsingleimagederaining AT ruocongtang unsupervisedgenerativeadversarialnetworkforsingleimagederaining AT linfengliu unsupervisedgenerativeadversarialnetworkforsingleimagederaining |