.png){kind=icon}
返回
PiGraphs: Learning Interaction Snapshots from Observations
.png){kind=icon}
OA
AI
DOI：10.1145/2897824.2925867.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We learn a probabilistic model connecting human poses and arrangements of object geometry from real-world observations of interactions collected with commodity RGB-D sensors. This model is encoded as a set of prototypical interaction graphs (PiGraphs), a human-centric representation capturing physical contact and visual attention linkages between 3D geometry and human body parts. We use this encoding of the joint probability distribution over pose and geometry during everyday interactions to generate interaction snapshots, which are static depictions of human poses and relevant objects during human-object interactions. We demonstrate that our model enables a novel human-centric understanding of 3D content and allows for jointly generating 3D scenes and interaction poses given terse high-level specifications, natural language, or reconstructed real-world scene constraints.
Keyword:
object semantics
human pose modeling
person-object interactions
3D content generation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.5
论文数:
4.7K
被引数:
3.6W
机构
引用论文
.png){kind=icon}
The Relationship between Urbanization, the Built Environment, and Physical Activity among Older Adults in Taiwan台湾老年人的城市化，建筑环境和身体活动之间的关系OAAI
OAAI分享收藏
查看更多内容