Image Neural Style Transfer With Global and Local Optimization Fusion
This paper presents a new image synthesis method for image style transfer. For some common methods, the textures and colors in the style image are sometimes applied inappropriately to the content image, which generates artifacts. In order to improve the results, we propose a novel method based on a...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8736245/ |
id |
doaj-445dcfc093294a2580a32718ec470ffc |
---|---|
record_format |
Article |
spelling |
doaj-445dcfc093294a2580a32718ec470ffc2021-03-29T23:58:08ZengIEEEIEEE Access2169-35362019-01-017855738558010.1109/ACCESS.2019.29225548736245Image Neural Style Transfer With Global and Local Optimization FusionHui-Huang Zhao0https://orcid.org/0000-0002-6261-0088Paul L. Rosin1Yu-Kun Lai2Mu-Gang Lin3Qin-Yun Liu4College of Computer Science and Technology, Hengyang Normal University, Hengyang, ChinaSchool of Computer Science and Informatics, Cardiff University, Cardiff, U.K.School of Computer Science and Informatics, Cardiff University, Cardiff, U.K.College of Computer Science and Technology, Hengyang Normal University, Hengyang, ChinaCollege of Computer Science and Technology, Hengyang Normal University, Hengyang, ChinaThis paper presents a new image synthesis method for image style transfer. For some common methods, the textures and colors in the style image are sometimes applied inappropriately to the content image, which generates artifacts. In order to improve the results, we propose a novel method based on a new strategy that combines both local and global style losses. On the one hand, a style loss function based on a local approach is used to keep the style details. On the other hand, another style loss function based on global measures is used to capture more global structural information. The results on various images show that the proposed method reduces artifacts while faithfully transferring the style image's characteristics and preserving the structure and color of the content image.https://ieeexplore.ieee.org/document/8736245/Deep neural networksstyle transferMarkov random fieldgram matrixlocal patch |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hui-Huang Zhao Paul L. Rosin Yu-Kun Lai Mu-Gang Lin Qin-Yun Liu |
spellingShingle |
Hui-Huang Zhao Paul L. Rosin Yu-Kun Lai Mu-Gang Lin Qin-Yun Liu Image Neural Style Transfer With Global and Local Optimization Fusion IEEE Access Deep neural networks style transfer Markov random field gram matrix local patch |
author_facet |
Hui-Huang Zhao Paul L. Rosin Yu-Kun Lai Mu-Gang Lin Qin-Yun Liu |
author_sort |
Hui-Huang Zhao |
title |
Image Neural Style Transfer With Global and Local Optimization Fusion |
title_short |
Image Neural Style Transfer With Global and Local Optimization Fusion |
title_full |
Image Neural Style Transfer With Global and Local Optimization Fusion |
title_fullStr |
Image Neural Style Transfer With Global and Local Optimization Fusion |
title_full_unstemmed |
Image Neural Style Transfer With Global and Local Optimization Fusion |
title_sort |
image neural style transfer with global and local optimization fusion |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
This paper presents a new image synthesis method for image style transfer. For some common methods, the textures and colors in the style image are sometimes applied inappropriately to the content image, which generates artifacts. In order to improve the results, we propose a novel method based on a new strategy that combines both local and global style losses. On the one hand, a style loss function based on a local approach is used to keep the style details. On the other hand, another style loss function based on global measures is used to capture more global structural information. The results on various images show that the proposed method reduces artifacts while faithfully transferring the style image's characteristics and preserving the structure and color of the content image. |
topic |
Deep neural networks style transfer Markov random field gram matrix local patch |
url |
https://ieeexplore.ieee.org/document/8736245/ |
work_keys_str_mv |
AT huihuangzhao imageneuralstyletransferwithglobalandlocaloptimizationfusion AT paullrosin imageneuralstyletransferwithglobalandlocaloptimizationfusion AT yukunlai imageneuralstyletransferwithglobalandlocaloptimizationfusion AT muganglin imageneuralstyletransferwithglobalandlocaloptimizationfusion AT qinyunliu imageneuralstyletransferwithglobalandlocaloptimizationfusion |
_version_ |
1724188757412806656 |