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 2012.11581cs.CV
收藏

通过学习人-场景交互填充3D场景

Populating 3D Scenes by Learning Human-Scene Interaction

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Mohamed Hassan, Partha Ghosh, Joachim Tesch, Dimitrios Tzionas, Michael J. Black

摘要:

人类生活在3D空间中,并不断与它互动以执行任务。这样的交互涉及在语义上有意义的表面之间的物理接触。我们的目标是了解人类如何与场景互动,并利用这一点使虚拟角色也能做到这一点。为此,我们引入了一种新的人的场景交互(HSI)模型,编码近端的关系,称为POSA的“姿态与proximitieS和接触”。交互的表示是以身体为中心的,这使得它能够推广到新的场景。具体而言,POSA增强了SMPL-X参数化人体模型,使得对于每个网格顶点,它编码(a)与场景表面的接触概率和(b)对应的语义场景标签。我们学习POSA与SMPL-X顶点条件下的VAE,并在PROX数据集上进行训练,该数据集包含与3D场景交互的SMPL-X网格,以及来自PROX-E数据集的相应场景语义。我们证明了POSA的价值与两个应用程序。首先,我们自动将人的3D扫描放置在场景中。我们使用适合扫描的SMPL-X模型作为代理,然后在3D中找到其最可能的位置。POSA提供了一个有效的表示,以搜索场景中的“启示”,匹配可能的接触关系,该姿势。我们进行了一项感知研究,显示出在这项任务上的最新技术水平的显着改善。其次,我们表明,POSA的学习表示的身体场景交互支持单眼人体姿态估计,是一致的3D场景,提高了最先进的。我们的模型和代码可用于研究目的在https://posa.is.tue.mpg.de。

英文摘要:

Humans live within a 3D space and constantly interact with it to perform tasks. Such interactions involve physical contact between surfaces that is semantically meaningful. Our goal is to learn how humans interact with scenes and leverage this to enable virtual characters to do the same. To that end, we introduce a novel Human-Scene Interaction (HSI) model that encodes proximal relationships, called POSA for "Pose with prOximitieS and contActs". The representation of interaction is body-centric, which enables it to generalize to new scenes. Specifically, POSA augments the SMPL-X parametric human body model such that, for every mesh vertex, it encodes (a) the contact probability with the scene surface and (b) the corresponding semantic scene label. We learn POSA with a VAE conditioned on the SMPL-X vertices, and train on the PROX dataset, which contains SMPL-X meshes of people interacting with 3D scenes, and the corresponding scene semantics from the PROX-E dataset. We demonstrate the value of POSA with two applications. First, we automatically place 3D scans of people in scenes. We use a SMPL-X model fit to the scan as a proxy and then find its most likely placement in 3D. POSA provides an effective representation to search for "affordances" in the scene that match the likely contact relationships for that pose. We perform a perceptual study that shows significant improvement over the state of the art on this task. Second, we show that POSA's learned representation of body-scene interaction supports monocular human pose estimation that is consistent with a 3D scene, improving on the state of the art. Our model and code are available for research purposes at https://posa.is.tue.mpg.de.

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。

↑