Fast generative adversarial networks model for masked image restoration
The conventional masked image restoration algorithms all utilise the correlation between the masked region and its neighbouring pixels, which does not work well for the larger masked image. The latest research utilises Generative Adversarial Networks (GANs) model to generate a better result for the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-05-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-ipr.2018.5592 |
| _version_ | 1818466155573018624 |
|---|---|
| author | Zhiyi Cao Shaozhang Niu Jiwei Zhang Xinyi Wang |
| author_facet | Zhiyi Cao Shaozhang Niu Jiwei Zhang Xinyi Wang |
| author_sort | Zhiyi Cao |
| collection | DOAJ |
| description | The conventional masked image restoration algorithms all utilise the correlation between the masked region and its neighbouring pixels, which does not work well for the larger masked image. The latest research utilises Generative Adversarial Networks (GANs) model to generate a better result for the larger masked image but does not work well for the complex masked region. To get a better result for the complex masked region, the authors propose a novel fast GANs model for masked image restoration. The method used in authors’ research is based on GANs model and fast marching method (FMM). The authors trained an FMMGAN model which consists of a neighbouring network, a generator network, a discriminator network, and two parsing networks. A large number of experimental results on two open datasets show that the proposed model performs well for masked image restoration. |
| first_indexed | 2024-04-13T20:54:42Z |
| format | Article |
| id | doaj.art-758d78137e824d3fa82defbae3d6d9b3 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-13T20:54:42Z |
| publishDate | 2019-05-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-758d78137e824d3fa82defbae3d6d9b32022-12-22T02:30:22ZengWileyIET Image Processing1751-96591751-96672019-05-011371124112910.1049/iet-ipr.2018.5592Fast generative adversarial networks model for masked image restorationZhiyi Cao0Shaozhang Niu1Jiwei Zhang2Xinyi Wang3Beijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and TelecommunicationsBeijingPeople's Republic of ChinaBeijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and TelecommunicationsBeijingPeople's Republic of ChinaBeijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and TelecommunicationsBeijingPeople's Republic of ChinaBeijing Key Lab of Intelligent Telecommunication Software and Multimedia, Beijing University of Posts and TelecommunicationsBeijingPeople's Republic of ChinaThe conventional masked image restoration algorithms all utilise the correlation between the masked region and its neighbouring pixels, which does not work well for the larger masked image. The latest research utilises Generative Adversarial Networks (GANs) model to generate a better result for the larger masked image but does not work well for the complex masked region. To get a better result for the complex masked region, the authors propose a novel fast GANs model for masked image restoration. The method used in authors’ research is based on GANs model and fast marching method (FMM). The authors trained an FMMGAN model which consists of a neighbouring network, a generator network, a discriminator network, and two parsing networks. A large number of experimental results on two open datasets show that the proposed model performs well for masked image restoration.https://doi.org/10.1049/iet-ipr.2018.5592neighbouring networkfast generative adversarial networks modelcomplex masked regionmasked imageconventional masked image restoration algorithmsfast marching method |
| spellingShingle | Zhiyi Cao Shaozhang Niu Jiwei Zhang Xinyi Wang Fast generative adversarial networks model for masked image restoration IET Image Processing neighbouring network fast generative adversarial networks model complex masked region masked image conventional masked image restoration algorithms fast marching method |
| title | Fast generative adversarial networks model for masked image restoration |
| title_full | Fast generative adversarial networks model for masked image restoration |
| title_fullStr | Fast generative adversarial networks model for masked image restoration |
| title_full_unstemmed | Fast generative adversarial networks model for masked image restoration |
| title_short | Fast generative adversarial networks model for masked image restoration |
| title_sort | fast generative adversarial networks model for masked image restoration |
| topic | neighbouring network fast generative adversarial networks model complex masked region masked image conventional masked image restoration algorithms fast marching method |
| url | https://doi.org/10.1049/iet-ipr.2018.5592 |
| work_keys_str_mv | AT zhiyicao fastgenerativeadversarialnetworksmodelformaskedimagerestoration AT shaozhangniu fastgenerativeadversarialnetworksmodelformaskedimagerestoration AT jiweizhang fastgenerativeadversarialnetworksmodelformaskedimagerestoration AT xinyiwang fastgenerativeadversarialnetworksmodelformaskedimagerestoration |