OPT OpenIR  > 光谱成像技术研究室
Channel-Grouping Based Patch Swap for Arbitrary Style Transfer
Zhu, Yan1; Niu, Yi1; Li, Fu1; Zou, Chunbo2; Shi, Guangming1
2020-10
会议名称2020 IEEE International Conference on Image Processing, ICIP 2020
会议录名称2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
卷号2020-October
页码613-617
会议日期2020-09-25
会议地点Virtual, Abu Dhabi, United arab emirates
出版者IEEE Computer Society
产权排序2
摘要

The basic principle of the patch-matching based style transfer is to substitute the patches of the content image feature maps by the closest patches from the style image feature maps. Since the finite features harvested from one single aesthetic style image are inadequate to represent the rich textures of the content natural image, existing techniques treat the full-channel style feature patches as simple signal tensors and create new style feature patches via signal-level fusion. In this paper, we propose a channel-grouping based patch swap technique to group the style feature maps into surface and texture channels, and the new features are created by the combination of these two groups, which can be regarded as a semantic-level fusion of the raw style features. Experimental results demonstrate that the proposed method outperforms the existing techniques in providing more style-consistent textures while keeping the content fidelity. © 2020 IEEE.

关键词Arbitrary style transfer patch-matching channel grouping texture synthesis
作者部门光谱成像技术研究室
DOI10.1109/ICIP40778.2020.9190962
收录类别EI ; CPCI
ISBN号9781728163956
语种英语
ISSN号15224880
WOS记录号WOS:000646178500122
EI入藏号20210109724787
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/94239
专题光谱成像技术研究室
作者单位1.The Telecommunication Engineering, School of Xidian University, China;
2.Xi'an Institute of Optics and Precision Mechanics of Cas, China
推荐引用方式
GB/T 7714
Zhu, Yan,Niu, Yi,Li, Fu,et al. Channel-Grouping Based Patch Swap for Arbitrary Style Transfer[C]:IEEE Computer Society,2020:613-617.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Channel-Grouping Bas(971KB)会议论文 限制开放CC BY-NC-SA请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu, Yan]的文章
[Niu, Yi]的文章
[Li, Fu]的文章
百度学术
百度学术中相似的文章
[Zhu, Yan]的文章
[Niu, Yi]的文章
[Li, Fu]的文章
必应学术
必应学术中相似的文章
[Zhu, Yan]的文章
[Niu, Yi]的文章
[Li, Fu]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。