通过深度特征融合的头发属性转移

Q3 Computer Science

计算机辅助设计与图形学学报 Pub Date : 2021-05-01 DOI:10.3724/sp.j.1089.2021.18544

Zhifeng Xie, Xu Su, Siwei Liu, Guisong Zhang, Lizhuang Ma

{"title":"通过深度特征融合的头发属性转移","authors":"Zhifeng Xie, Xu Su, Siwei Liu, Guisong Zhang, Lizhuang Ma","doi":"10.3724/sp.j.1089.2021.18544","DOIUrl":null,"url":null,"abstract":": To tackle the problem that existing attribute transfer methods can’t transfer hair attributes effectively, a method of hair attribute transfer based on deep feature fusion is presented. This method includes three subnetworks which are responsible for feature extraction, attribute vector extraction and image synthesis. Firstly, feature extraction network extracts features from original images, and keeps the identity of original images unchanged by adding a reconstruction loss. At the same time, attribute vector extraction network constructs the mapping model of hair features and hair attributes","PeriodicalId":52442,"journal":{"name":"计算机辅助设计与图形学学报","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hair Attribute Transfer via Deep Feature Fusion\",\"authors\":\"Zhifeng Xie, Xu Su, Siwei Liu, Guisong Zhang, Lizhuang Ma\",\"doi\":\"10.3724/sp.j.1089.2021.18544\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": To tackle the problem that existing attribute transfer methods can’t transfer hair attributes effectively, a method of hair attribute transfer based on deep feature fusion is presented. This method includes three subnetworks which are responsible for feature extraction, attribute vector extraction and image synthesis. Firstly, feature extraction network extracts features from original images, and keeps the identity of original images unchanged by adding a reconstruction loss. At the same time, attribute vector extraction network constructs the mapping model of hair features and hair attributes\",\"PeriodicalId\":52442,\"journal\":{\"name\":\"计算机辅助设计与图形学学报\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"计算机辅助设计与图形学学报\",\"FirstCategoryId\":\"1093\",\"ListUrlMain\":\"https://doi.org/10.3724/sp.j.1089.2021.18544\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"计算机辅助设计与图形学学报","FirstCategoryId":"1093","ListUrlMain":"https://doi.org/10.3724/sp.j.1089.2021.18544","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 0

摘要

针对现有属性传递方法不能有效传递头发属性的问题，提出了一种基于深度特征融合的头发属性传递方法。该方法包括三个子网络，分别负责特征提取、属性向量提取和图像合成。首先，特征提取网络从原始图像中提取特征，并通过添加重建损失来保持原始图像的同一性不变。同时，属性向量提取网络构建了头发特征与头发属性的映射模型

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Hair Attribute Transfer via Deep Feature Fusion

: To tackle the problem that existing attribute transfer methods can’t transfer hair attributes effectively, a method of hair attribute transfer based on deep feature fusion is presented. This method includes three subnetworks which are responsible for feature extraction, attribute vector extraction and image synthesis. Firstly, feature extraction network extracts features from original images, and keeps the identity of original images unchanged by adding a reconstruction loss. At the same time, attribute vector extraction network constructs the mapping model of hair features and hair attributes

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

计算机辅助设计与图形学学报 Computer Science-Computer Graphics and Computer-Aided Design

CiteScore

1.20

自引率

0.00%

发文量

6833

期刊介绍：