Pyramid style-attentional network for arbitrary style transfer
Article
Yang, Gaoming, Zhang, Shicheng, Fang, Xianjin and Zhang, Ji. 2024. "Pyramid style-attentional network for arbitrary style transfer." Multimedia Tools and Applications. 83 (5), pp. 3483-13502. https://doi.org/10.1007/s11042-023-15650-0
Article Title | Pyramid style-attentional network for arbitrary style transfer |
---|---|
ERA Journal ID | 18083 |
Article Category | Article |
Authors | Yang, Gaoming, Zhang, Shicheng, Fang, Xianjin and Zhang, Ji |
Journal Title | Multimedia Tools and Applications |
Journal Citation | 83 (5), pp. 3483-13502 |
Number of Pages | 20 |
Year | 2024 |
Publisher | Springer |
ISSN | 1380-7501 |
1573-7721 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/s11042-023-15650-0 |
Web Address (URL) | https://link.springer.com/article/10.1007/s11042-023-15650-0 |
Abstract | At present, the self-attention mechanism represented by the non-local network has been applied in style transfer widely. Models can achieve good style transfer effects by considering long-range dependencies between content images and style images while well maintaining semantic content information. However, the self-attention mechanism has to calculate the relationship between all positions between the content feature maps and style feature maps. The associated computational complexity of the mechanism is rather high, which will consume a lot of computing resources and adversely impact the efficiency of style transfer of high-resolution images. To solve this problem, we propose a novel Pyramid Style-attentional Network (PSANet) to reduce the computational complexity of the self-attention network by using pyramid pooling on feature maps. We compare our method with the vanilla style-attentional network in terms of speed and quality. The experimental results show that our model can significantly reduce the computational complexity and achieve good transfer effects. Especially for handling high-resolution images, the execution time of our method can reduce by 34.7 % . © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. |
Keywords | Image processing; Style transfer; Pyramid pooling; Self-attentio |
ANZSRC Field of Research 2020 | 461299. Software engineering not elsewhere classified |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Anhui University of Science and Technology, China |
School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z272x/pyramid-style-attentional-network-for-arbitrary-style-transfer
62
total views0
total downloads4
views this month0
downloads this month