User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach
Image completion models based on deep neural networks have been a research hot spot in computer vision. However, most of the previous methods focus on natural images, such as faces and landscapes. In this paper, we propose a novel image completion model for a special set of artificial ancient Chines...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9216082/ |
| _version_ | 1818330493290020864 |
|---|---|
| author | Jieting Xue Jingtao Guo Yi Liu |
| author_facet | Jieting Xue Jingtao Guo Yi Liu |
| author_sort | Jieting Xue |
| collection | DOAJ |
| description | Image completion models based on deep neural networks have been a research hot spot in computer vision. However, most of the previous methods focus on natural images, such as faces and landscapes. In this paper, we propose a novel image completion model for a special set of artificial ancient Chinese paintings to address this limitation. Specifically, we integrate three complements: the Wasserstein Generative Adversarial Networks (WGAN), Perceptual loss, and Mean Squared Error (MSE) to train the model robustly. We propose a unique generator which can not only pay more attention to complete the details of ancient Chinese paintings but also can provide the synthesized lines to help artists to analyze paintings conveniently. Additionally, we also allow a user to supply a structure hint to guide our model to complete Chinese paintings according to his/her preference. Extensive experiments firmly demonstrate the effectiveness of our approach to complete ancient Chinese paintings and remove abnormal color blocks from them. |
| first_indexed | 2024-12-13T13:04:50Z |
| format | Article |
| id | doaj.art-da8cbab7208f4f2280e6e35da2685dea |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T13:04:50Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-da8cbab7208f4f2280e6e35da2685dea2022-12-21T23:44:52ZengIEEEIEEE Access2169-35362020-01-01818743118744010.1109/ACCESS.2020.30290849216082User-Guided Chinese Painting Completion–A Generative Adversarial Network ApproachJieting Xue0https://orcid.org/0000-0003-3882-3099Jingtao Guo1Yi Liu2https://orcid.org/0000-0003-1868-4052Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer and Information Technology, Beijing Jiao Tong University, Beijing, ChinaBeijing Key Lab of Traffic Data Analysis and Mining, School of Computer and Information Technology, Beijing Jiao Tong University, Beijing, ChinaBeijing Key Lab of Traffic Data Analysis and Mining, School of Computer and Information Technology, Beijing Jiao Tong University, Beijing, ChinaImage completion models based on deep neural networks have been a research hot spot in computer vision. However, most of the previous methods focus on natural images, such as faces and landscapes. In this paper, we propose a novel image completion model for a special set of artificial ancient Chinese paintings to address this limitation. Specifically, we integrate three complements: the Wasserstein Generative Adversarial Networks (WGAN), Perceptual loss, and Mean Squared Error (MSE) to train the model robustly. We propose a unique generator which can not only pay more attention to complete the details of ancient Chinese paintings but also can provide the synthesized lines to help artists to analyze paintings conveniently. Additionally, we also allow a user to supply a structure hint to guide our model to complete Chinese paintings according to his/her preference. Extensive experiments firmly demonstrate the effectiveness of our approach to complete ancient Chinese paintings and remove abnormal color blocks from them.https://ieeexplore.ieee.org/document/9216082/Deep learningGenerative adversarial networkImage completion |
| spellingShingle | Jieting Xue Jingtao Guo Yi Liu User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach IEEE Access Deep learning Generative adversarial network Image completion |
| title | User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach |
| title_full | User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach |
| title_fullStr | User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach |
| title_full_unstemmed | User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach |
| title_short | User-Guided Chinese Painting Completion–A Generative Adversarial Network Approach |
| title_sort | user guided chinese painting completion x2013 a generative adversarial network approach |
| topic | Deep learning Generative adversarial network Image completion |
| url | https://ieeexplore.ieee.org/document/9216082/ |
| work_keys_str_mv | AT jietingxue userguidedchinesepaintingcompletionx2013agenerativeadversarialnetworkapproach AT jingtaoguo userguidedchinesepaintingcompletionx2013agenerativeadversarialnetworkapproach AT yiliu userguidedchinesepaintingcompletionx2013agenerativeadversarialnetworkapproach |