SIA OpenIR  > 机器人学研究室
基于对抗生成网络的纹理合成方法
Alternative TitleTexture synthesis method based on generative adversarial networks
余思泉; 韩志; 唐延东; 吴成东
Department机器人学研究室
Source Publication红外与激光工程
ISSN1007-2276
2018
Volume47Issue:2Pages:43-48
Indexed ByEI ; CSCD
EI Accession number20182105214038
CSCD IDCSCD:6207497
Contribution Rank1
Funding Organization国家自然科学基金(61773367, 61303168) ; 中国科学院青年创新促进会(2016183)
Keyword纹理合成 深度学习 生成模型 对抗生成网络
Abstract

纹理合成是计算机图形学、计算机视觉和图像处理领域的研究热点之一。传统的纹理合成方法往往通过提取有效的特征样式或统计量并在该特征信息的约束下生成随机图像来实现。对抗生成网络作为一种较新的深度网络形式,通过生成器和判别器的对抗训练能够随机生成与观测数据具有相同分布的新数据。鉴于此,提出了一种基于对抗生成网络的纹理合成方法。该算法的优点是不需要经过多次迭代就能够生成更真实纹理图像,且生成图像在视觉上与观测纹理图像一致的同时具有一定随机性。一系列针对随机纹理和结构性纹理的合成实验验证了该算法的有效性。

Other Abstract

Texture synthesis is a hot research topic in the fields of computer graphics, vision, and image processing. Traditional texture synthesis methods are generally achieved by extracting effective feature patterns or statistics and generating random images under the constraint of the feature information. Generative adversarial networks (GANs) is a new type of deep network. It can randomly generate new data of the same distribution as the observed data by training generator and discriminator in an adversarial learning mechanism. Inspired by this point, a texture synthesis method based on GANs was proposed. The advantage of the algorithm was that it could generate more realistic texture images without iteration; the generated images were visually consistent with the observed texture image and also had randomness. A series of experiments for random texture and structured texture synthesis verify the effectiveness of the proposed algorithm.

Language中文
Citation statistics
Cited Times:1[CSCD]   [CSCD Record]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/21581
Collection机器人学研究室
Corresponding Author余思泉
Affiliation1.东北大学信息科学与工程学院
2.中国科学院沈阳自动化研究所机器人学国家重点实验室
Recommended Citation
GB/T 7714
余思泉,韩志,唐延东,等. 基于对抗生成网络的纹理合成方法[J]. 红外与激光工程,2018,47(2):43-48.
APA 余思泉,韩志,唐延东,&吴成东.(2018).基于对抗生成网络的纹理合成方法.红外与激光工程,47(2),43-48.
MLA 余思泉,et al."基于对抗生成网络的纹理合成方法".红外与激光工程 47.2(2018):43-48.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于对抗生成网络的纹理合成方法.pdf(555KB)期刊论文作者接受稿开放获取ODC PDDLView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[余思泉]'s Articles
[韩志]'s Articles
[唐延东]'s Articles
Baidu academic
Similar articles in Baidu academic
[余思泉]'s Articles
[韩志]'s Articles
[唐延东]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[余思泉]'s Articles
[韩志]'s Articles
[唐延东]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于对抗生成网络的纹理合成方法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.