用于姿势引导的人物合成的对称连体网络

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Quanwei Yang , Lingyun Yu , Fengyuan Liu , Yun Song , Meng Shao , Guoqing Jin , Hongtao Xie
{"title":"用于姿势引导的人物合成的对称连体网络","authors":"Quanwei Yang ,&nbsp;Lingyun Yu ,&nbsp;Fengyuan Liu ,&nbsp;Yun Song ,&nbsp;Meng Shao ,&nbsp;Guoqing Jin ,&nbsp;Hongtao Xie","doi":"10.1016/j.cviu.2024.104134","DOIUrl":null,"url":null,"abstract":"<div><p>Pose-Guided Person Image Synthesis (PGPIS) aims to generate a realistic person image that preserves the appearance of the source person while adopting the target pose. Various appearances and drastic pose changes make this task highly challenging. Due to the insufficient utilization of paired data, existing models face difficulties in accurately preserving the source appearance details and high-frequency textures in the generated images. Meanwhile, although current popular AdaIN-based methods are advantageous in handling drastic pose changes, they struggle to capture diverse clothing shapes imposed by the limitation of global feature statistics. To address these issues, we propose a novel Symmetrical Siamese Network (SSNet) for PGPIS, which consists of two synergistic symmetrical generative branches that leverage prior knowledge of paired data to comprehensively exploit appearance details. For feature integration, we propose a Style Matching Module (SMM) to transfer multi-level region appearance styles and gradient information to the desired pose for enriching the high-frequency textures. Furthermore, to overcome the limitation of global feature statistics, a Spatial Attention Module (SAM) is introduced to complement the SMM for capturing clothing shapes. Extensive experiments show the effectiveness of our SSNet, achieving state-of-the-art results on public datasets. Moreover, our SSNet can also edit the source appearance attributes, making it versatile in wider application scenarios.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"248 ","pages":"Article 104134"},"PeriodicalIF":4.3000,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Symmetrical Siamese Network for pose-guided person synthesis\",\"authors\":\"Quanwei Yang ,&nbsp;Lingyun Yu ,&nbsp;Fengyuan Liu ,&nbsp;Yun Song ,&nbsp;Meng Shao ,&nbsp;Guoqing Jin ,&nbsp;Hongtao Xie\",\"doi\":\"10.1016/j.cviu.2024.104134\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Pose-Guided Person Image Synthesis (PGPIS) aims to generate a realistic person image that preserves the appearance of the source person while adopting the target pose. Various appearances and drastic pose changes make this task highly challenging. Due to the insufficient utilization of paired data, existing models face difficulties in accurately preserving the source appearance details and high-frequency textures in the generated images. Meanwhile, although current popular AdaIN-based methods are advantageous in handling drastic pose changes, they struggle to capture diverse clothing shapes imposed by the limitation of global feature statistics. To address these issues, we propose a novel Symmetrical Siamese Network (SSNet) for PGPIS, which consists of two synergistic symmetrical generative branches that leverage prior knowledge of paired data to comprehensively exploit appearance details. For feature integration, we propose a Style Matching Module (SMM) to transfer multi-level region appearance styles and gradient information to the desired pose for enriching the high-frequency textures. Furthermore, to overcome the limitation of global feature statistics, a Spatial Attention Module (SAM) is introduced to complement the SMM for capturing clothing shapes. Extensive experiments show the effectiveness of our SSNet, achieving state-of-the-art results on public datasets. Moreover, our SSNet can also edit the source appearance attributes, making it versatile in wider application scenarios.</p></div>\",\"PeriodicalId\":50633,\"journal\":{\"name\":\"Computer Vision and Image Understanding\",\"volume\":\"248 \",\"pages\":\"Article 104134\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Vision and Image Understanding\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1077314224002157\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002157","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

姿态引导的人物图像合成(PGPIS)旨在生成逼真的人物图像,在采用目标姿态的同时保留源人物的外观。各种外观和剧烈的姿势变化使这项任务极具挑战性。由于没有充分利用配对数据,现有模型在生成的图像中难以准确保留源外观细节和高频纹理。同时,尽管目前流行的基于 AdaIN 的方法在处理剧烈姿势变化方面具有优势,但由于全局特征统计的限制,这些方法在捕捉不同的服装形状方面存在困难。为了解决这些问题,我们为 PGPIS 提出了一种新颖的对称连体网络(SSNet),它由两个协同对称生成分支组成,可利用配对数据的先验知识来全面利用外观细节。在特征整合方面,我们提出了风格匹配模块(SMM),将多级区域外观风格和梯度信息传输到所需姿势,以丰富高频纹理。此外,为了克服全局特征统计的局限性,我们还引入了空间关注模块(SAM)来补充 SMM,以捕捉服装形状。广泛的实验表明,我们的 SSNet 非常有效,在公共数据集上取得了最先进的结果。此外,我们的 SSNet 还能编辑源外观属性,使其在更广泛的应用场景中发挥更大作用。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Symmetrical Siamese Network for pose-guided person synthesis

Pose-Guided Person Image Synthesis (PGPIS) aims to generate a realistic person image that preserves the appearance of the source person while adopting the target pose. Various appearances and drastic pose changes make this task highly challenging. Due to the insufficient utilization of paired data, existing models face difficulties in accurately preserving the source appearance details and high-frequency textures in the generated images. Meanwhile, although current popular AdaIN-based methods are advantageous in handling drastic pose changes, they struggle to capture diverse clothing shapes imposed by the limitation of global feature statistics. To address these issues, we propose a novel Symmetrical Siamese Network (SSNet) for PGPIS, which consists of two synergistic symmetrical generative branches that leverage prior knowledge of paired data to comprehensively exploit appearance details. For feature integration, we propose a Style Matching Module (SMM) to transfer multi-level region appearance styles and gradient information to the desired pose for enriching the high-frequency textures. Furthermore, to overcome the limitation of global feature statistics, a Spatial Attention Module (SAM) is introduced to complement the SMM for capturing clothing shapes. Extensive experiments show the effectiveness of our SSNet, achieving state-of-the-art results on public datasets. Moreover, our SSNet can also edit the source appearance attributes, making it versatile in wider application scenarios.

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
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信