StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
2024-07-30
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 HumanObject 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. 

DOIarXiv:2407.20545
相关网址查看原文
出处Arxiv
WOS记录号PPRN:91196313
WOS类目Computer Science, Software Engineering
文献类型预印本
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/408315
专题信息科学与技术学院_PI研究组_石野组
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_硕士生
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
通讯作者Wang, Jingya
作者单位
1.ShanghaiTech Univ, Shanghai, Peoples R China
2.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China
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. 2024.
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。