StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
2023
会议录名称IJCAI INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
ISSN1045-0823
卷号2023-August
页码902-910
发表状态已发表
摘要

Modeling and capturing the 3D spatial arrangement of the human and the object is the key to perceiving 3D human-object interaction from monocular images. In this work, we propose to use the Human-Object Offset between anchors which are densely sampled from the surface of human mesh and object mesh to represent human-object spatial relation. Compared with previous works which use contact map or implicit distance filed to encode 3D human-object spatial relations, our method is a simple and efficient way to encode the highly detailed spatial correlation between the human and object. Based on this representation, we propose Stacked Normalizing Flow (StackFLOW) to infer the posterior distribution of human-object spatial relations from the image. During the optimization stage, we finetune the human body pose and object 6D pose by maximizing the likelihood of samples based on this posterior distribution and minimizing the 2D-3D corresponding reprojection loss. Extensive experimental results show that our method achieves impressive results on two challenging benchmarks, BEHAVE and InterCap datasets. Our code has been publicly available at https://github.com/huochf/StackFLOW. © 2023 International Joint Conferences on Artificial Intelligence. All rights reserved.

会议录编者/会议主办者International Joint Conferences on Artifical Intelligence (IJCAI)
关键词Artificial intelligence Mesh generation Contacts map Human-object interaction Monocular image Object reconstruction Optimisations Posterior distributions Simple++ Spatial arrangements Spatial correlations Spatial relations
会议名称32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
会议地点Macao, China
会议日期August 19, 2023 - August 25, 2023
收录类别EI
语种英语
出版者International Joint Conferences on Artificial Intelligence
EI入藏号20233714713485
EI主题词Encoding (symbols)
EI分类号723.2 Data Processing and Image Processing ; 723.4 Artificial Intelligence ; 723.5 Computer Applications ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
原始文献类型Conference article (CA)
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348727
专题信息科学与技术学院_硕士生
信息科学与技术学院_PI研究组_虞晶怡组
信息科学与技术学院_PI研究组_许岚组
信息科学与技术学院_PI研究组_马月昕
信息科学与技术学院_PI研究组_汪婧雅组
信息科学与技术学院_PI研究组_石野组
通讯作者Wang, Jingya
作者单位
1.ShanghaiTech University, China
2.Shanghai Engineering Research Center of Intelligent Vision and Imaging, China
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Huo, Chaofan,Shi, Ye,Ma, Yuexin,et al. StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset[C]//International Joint Conferences on Artifical Intelligence (IJCAI):International Joint Conferences on Artificial Intelligence,2023:902-910.
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
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Huo, Chaofan]的文章
[Shi, Ye]的文章
[Ma, Yuexin]的文章
百度学术
百度学术中相似的文章
[Huo, Chaofan]的文章
[Shi, Ye]的文章
[Ma, Yuexin]的文章
必应学术
必应学术中相似的文章
[Huo, Chaofan]的文章
[Shi, Ye]的文章
[Ma, Yuexin]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。