arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.05070cs.CVcs.AI
收藏

物理基元分解

Physical Primitive Decomposition

Massachusetts Institute of Technology(麻省理工学院);Google Research(谷歌研究院)

Zhijian Liu, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu

摘要:

对象是由部件组成的,每个部件都有不同的几何形状、物理特性、功能和启示。开发这种分布式的、物理的、可解释的对象表示将有助于智能代理更好地探索世界并与世界互动。在本文中,我们研究了物理基元分解-通过其组件来理解对象,每个组件都具有物理和几何属性。由于对象部件和物理的注释数据很少,我们提出了一种新的配方,通过解释对象的外观和物理事件中的行为来学习物理原语。我们的模型在合成和真实场景中的积木塔和工具上表现良好;我们还证明了视觉和物理观测通常提供互补信号。我们进一步提出了消融和行为研究,以更好地理解我们的模型,并将其与人类的表现进行对比。

英文摘要:

Objects are made of parts, each with distinct geometry, physics, functionality, and affordances. Developing such a distributed, physical, interpretable representation of objects will facilitate intelligent agents to better explore and interact with the world. In this paper, we study physical primitive decomposition---understanding an object through its components, each with physical and geometric attributes. As annotated data for object parts and physics are rare, we propose a novel formulation that learns physical primitives by explaining both an object's appearance and its behaviors in physical events. Our model performs well on block towers and tools in both synthetic and real scenarios; we also demonstrate that visual and physical observations often provide complementary signals. We further present ablation and behavioral studies to better understand our model and contrast it with human performance.

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。

↑