arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.01591cs.CV
收藏

从互联网视频中估计人-物体相互作用的3D运动和力

Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos

École normale supérieure(巴黎高等师范学院);CNRS(法国国家科学研究中心);PSL Research University(巴黎文理研究大学);Inria Paris(法国国家信息与自动化研究所巴黎中心);Czech Technical University in Prague(布拉格捷克理工大学);Université de Toulouse(图卢兹大学)

Zongmian Li, Jiri Sedlar, Justin Carpentier, Ivan Laptev, Nicolas Mansard, Josef Sivic

摘要:

在本文中,我们介绍了一种方法来自动重建一个人与一个物体从一个单一的RGB视频的3D运动。我们的方法估计的3D姿态的人连同对象的姿态,接触位置和接触力施加在人体上。这项工作的主要贡献有三个方面。首先,我们介绍了一种方法来共同估计的运动和驱动力的人对被操纵的对象建模接触和动态的相互作用。这是一个大规模的轨迹优化问题。其次,我们开发了一种方法,可以从输入视频中自动识别人与物体或地面之间接触的2D位置和时间,从而大大简化了优化的复杂性。第三,我们在最近的视频+MoCap数据集上验证了我们的方法,该数据集捕捉了典型的跑酷动作,并在一个新的互联网视频数据集上展示了它的性能,该数据集显示人们在不受约束的环境中操纵各种工具。

英文摘要:

In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video. Our method estimates the 3D poses of the person together with the object pose, the contact positions and the contact forces exerted on the human body. The main contributions of this work are three-fold. First, we introduce an approach to jointly estimate the motion and the actuation forces of the person on the manipulated object by modeling contacts and the dynamics of the interactions. This is cast as a large-scale trajectory optimization problem. Second, we develop a method to automatically recognize from the input video the 2D position and timing of contacts between the person and the object or the ground, thereby significantly simplifying the complexity of the optimization. Third, we validate our approach on a recent video+MoCap dataset capturing typical parkour actions, and demonstrate its performance on a new dataset of Internet videos showing people manipulating a variety of tools in unconstrained environments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑