DBMHT:用于视频中三维人体姿态估计的双分支多假设变换器

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Xuezhi Xiang , Xiaoheng Li , Weijie Bao , Yulong Qiao , Abdulmotaleb El Saddik
{"title":"DBMHT:用于视频中三维人体姿态估计的双分支多假设变换器","authors":"Xuezhi Xiang ,&nbsp;Xiaoheng Li ,&nbsp;Weijie Bao ,&nbsp;Yulong Qiao ,&nbsp;Abdulmotaleb El Saddik","doi":"10.1016/j.cviu.2024.104147","DOIUrl":null,"url":null,"abstract":"<div><p>The estimation of 3D human poses from monocular videos presents a significant challenge. The existing methods face the problems of deep ambiguity and self-occlusion. To overcome these problems, we propose a Double-Branch Multi-Hypothesis Transformer (DBMHT). In detail, we utilize a Double-Branch architecture to capture temporal and spatial information and generate multiple hypotheses. To merge these hypotheses, we adopt a lightweight module to integrate spatial and temporal representations. The DBMHT can not only capture spatial information from each joint in the human body and temporal information from each frame in the video but also merge multiple hypotheses that have different spatio-temporal information. Comprehensive evaluation on two challenging datasets (i.e. Human3.6M and MPI-INF-3DHP) demonstrates the superior performance of DBMHT, marking it as a robust and efficient approach for accurate 3D HPE in dynamic scenarios. The results show that our model surpasses the state-of-the-art approach by 1.9% MPJPE with ground truth 2D keypoints as input.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DBMHT: A double-branch multi-hypothesis transformer for 3D human pose estimation in video\",\"authors\":\"Xuezhi Xiang ,&nbsp;Xiaoheng Li ,&nbsp;Weijie Bao ,&nbsp;Yulong Qiao ,&nbsp;Abdulmotaleb El Saddik\",\"doi\":\"10.1016/j.cviu.2024.104147\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The estimation of 3D human poses from monocular videos presents a significant challenge. The existing methods face the problems of deep ambiguity and self-occlusion. To overcome these problems, we propose a Double-Branch Multi-Hypothesis Transformer (DBMHT). In detail, we utilize a Double-Branch architecture to capture temporal and spatial information and generate multiple hypotheses. To merge these hypotheses, we adopt a lightweight module to integrate spatial and temporal representations. The DBMHT can not only capture spatial information from each joint in the human body and temporal information from each frame in the video but also merge multiple hypotheses that have different spatio-temporal information. Comprehensive evaluation on two challenging datasets (i.e. Human3.6M and MPI-INF-3DHP) demonstrates the superior performance of DBMHT, marking it as a robust and efficient approach for accurate 3D HPE in dynamic scenarios. The results show that our model surpasses the state-of-the-art approach by 1.9% MPJPE with ground truth 2D keypoints as input.</p></div>\",\"PeriodicalId\":50633,\"journal\":{\"name\":\"Computer Vision and Image Understanding\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-09-06\",\"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/S1077314224002285\",\"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/S1077314224002285","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

从单目视频中估计三维人体姿态是一项重大挑战。现有方法面临着深度模糊性和自我封闭性的问题。为了克服这些问题,我们提出了双分支多假设变换器(DBMHT)。具体来说,我们利用双分支架构捕捉时间和空间信息并生成多个假设。为了合并这些假设,我们采用了一个轻量级模块来整合空间和时间表征。DBMHT 不仅能捕捉人体每个关节的空间信息和视频中每一帧的时间信息,还能合并具有不同时空信息的多个假设。在两个具有挑战性的数据集(即 Human3.6M 和 MPI-INF-3DHP)上进行的综合评估证明了 DBMHT 的优越性能,使其成为在动态场景中实现精确三维 HPE 的稳健而高效的方法。结果表明,我们的模型在输入地面真实 2D 关键点的情况下,MPJPE 比最先进的方法高出 1.9%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
DBMHT: A double-branch multi-hypothesis transformer for 3D human pose estimation in video

The estimation of 3D human poses from monocular videos presents a significant challenge. The existing methods face the problems of deep ambiguity and self-occlusion. To overcome these problems, we propose a Double-Branch Multi-Hypothesis Transformer (DBMHT). In detail, we utilize a Double-Branch architecture to capture temporal and spatial information and generate multiple hypotheses. To merge these hypotheses, we adopt a lightweight module to integrate spatial and temporal representations. The DBMHT can not only capture spatial information from each joint in the human body and temporal information from each frame in the video but also merge multiple hypotheses that have different spatio-temporal information. Comprehensive evaluation on two challenging datasets (i.e. Human3.6M and MPI-INF-3DHP) demonstrates the superior performance of DBMHT, marking it as a robust and efficient approach for accurate 3D HPE in dynamic scenarios. The results show that our model surpasses the state-of-the-art approach by 1.9% MPJPE with ground truth 2D keypoints as input.

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