Neural saliency algorithm guide bi-directional visual perception style transfer
The artistic style transfer of images aims to synthesise novel images by combining the content of one image with the style of another, which is a long-standing research topic and already has been widely applied in real world. However, defining the aesthetic perception from the human visual system is...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-10-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0034 |
| _version_ | 1818725874777718784 |
|---|---|
| author | Chunbiao Zhu Wei Yan Wei Yan Xing Cai Shan Liu Thomas H. Li Ge Li |
| author_facet | Chunbiao Zhu Wei Yan Wei Yan Xing Cai Shan Liu Thomas H. Li Ge Li |
| author_sort | Chunbiao Zhu |
| collection | DOAJ |
| description | The artistic style transfer of images aims to synthesise novel images by combining the content of one image with the style of another, which is a long-standing research topic and already has been widely applied in real world. However, defining the aesthetic perception from the human visual system is a challenging problem. In this study, the authors propose a novel method for automatic visual perception style transfer. First, they render a novel saliency detection algorithm to automatically perceive the visual attention of an image. Then, different from conventional style transfer algorithm in which style transferring is applied uniformly across all image regions, the authors apply a saliency algorithm to guide the style transferring process, enabling different types of style transferring to occur in different regions. Extensive experiments show that the proposed saliency detection algorithm and the style transfer algorithm are superior in performance and efficiency. |
| first_indexed | 2024-12-17T21:49:15Z |
| format | Article |
| id | doaj.art-961d19254db848fc9a6fceeb40ad0934 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-12-17T21:49:15Z |
| publishDate | 2019-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-961d19254db848fc9a6fceeb40ad09342022-12-21T21:31:22ZengWileyCAAI Transactions on Intelligence Technology2468-23222019-10-0110.1049/trit.2019.0034TRIT.2019.0034Neural saliency algorithm guide bi-directional visual perception style transferChunbiao Zhu0Wei Yan1Wei Yan2Xing Cai3Shan LiuThomas H. Li4Ge Li5Shenzhen Graduate School, Peking UniversityShenzhen Graduate School, Peking UniversityShenzhen Graduate School, Peking UniversityShenzhen Graduate School, Peking UniversityShenzhen Graduate School, Peking UniversityShenzhen Graduate School, Peking UniversityThe artistic style transfer of images aims to synthesise novel images by combining the content of one image with the style of another, which is a long-standing research topic and already has been widely applied in real world. However, defining the aesthetic perception from the human visual system is a challenging problem. In this study, the authors propose a novel method for automatic visual perception style transfer. First, they render a novel saliency detection algorithm to automatically perceive the visual attention of an image. Then, different from conventional style transfer algorithm in which style transferring is applied uniformly across all image regions, the authors apply a saliency algorithm to guide the style transferring process, enabling different types of style transferring to occur in different regions. Extensive experiments show that the proposed saliency detection algorithm and the style transfer algorithm are superior in performance and efficiency.https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0034visual perceptionfeature extractionimage segmentationimage colour analysisobject detectionhuman visual systemautomatic visual perception style transfernovel saliency detection algorithmvisual attentionconventional style transfer algorithmimage regionsstyle transferring processartistic style transferaesthetic perceptionneural saliency algorithm guide bi-directional visual perception style transfer |
| spellingShingle | Chunbiao Zhu Wei Yan Wei Yan Xing Cai Shan Liu Thomas H. Li Ge Li Neural saliency algorithm guide bi-directional visual perception style transfer CAAI Transactions on Intelligence Technology visual perception feature extraction image segmentation image colour analysis object detection human visual system automatic visual perception style transfer novel saliency detection algorithm visual attention conventional style transfer algorithm image regions style transferring process artistic style transfer aesthetic perception neural saliency algorithm guide bi-directional visual perception style transfer |
| title | Neural saliency algorithm guide bi-directional visual perception style transfer |
| title_full | Neural saliency algorithm guide bi-directional visual perception style transfer |
| title_fullStr | Neural saliency algorithm guide bi-directional visual perception style transfer |
| title_full_unstemmed | Neural saliency algorithm guide bi-directional visual perception style transfer |
| title_short | Neural saliency algorithm guide bi-directional visual perception style transfer |
| title_sort | neural saliency algorithm guide bi directional visual perception style transfer |
| topic | visual perception feature extraction image segmentation image colour analysis object detection human visual system automatic visual perception style transfer novel saliency detection algorithm visual attention conventional style transfer algorithm image regions style transferring process artistic style transfer aesthetic perception neural saliency algorithm guide bi-directional visual perception style transfer |
| url | https://digital-library.theiet.org/content/journals/10.1049/trit.2019.0034 |
| work_keys_str_mv | AT chunbiaozhu neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT weiyan neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT weiyan neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT xingcai neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT shanliu neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT thomashli neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer AT geli neuralsaliencyalgorithmguidebidirectionalvisualperceptionstyletransfer |