从动作中构建结构：学习交互以发现铰接物体的3D结构
Structure from Action: Learning Interactions for Articulated Object 3D Structure Discovery
AI总结：
本文提出SfA框架，通过选择信息量大的交互并结合3D感知，准确分割、重建未见铰接物体的部件几何并推断关节参数，在未见类别上显著优于现有方法。
摘要：
我们提出了Structure from Action (SfA)框架，通过一系列推断的交互来发现未见铰接物体的3D部件几何形状和关节参数。我们的核心见解是，构建3D铰接CAD模型时应将3D交互与感知结合考虑，尤其是对于训练中未见的类别。通过选择信息量大的交互，SfA能发现部件并揭示被遮挡的表面，例如关闭抽屉的内部。通过在3D中聚合视觉观测，SfA能准确分割多个部件，重建部件几何形状，并在规范坐标系中推断所有关节参数。实验表明，在仿真中训练的SfA模型能泛化至多种结构各异的未见类别及真实世界物体。实验结果显示，在未见类别上，SfA比由最先进组件构成的流程高出25.4个3D IoU百分点，同时与已表现出色的关节估计基线相匹配。
英文摘要：
We introduce Structure from Action (SfA), a framework to discover 3D part geometry and joint parameters of unseen articulated objects via a sequence of inferred interactions. Our key insight is that 3D interaction and perception should be considered in conjunction to construct 3D articulated CAD models, especially for categories not seen during training. By selecting informative interactions, SfA discovers parts and reveals occluded surfaces, like the inside of a closed drawer. By aggregating visual observations in 3D, SfA accurately segments multiple parts, reconstructs part geometry, and infers all joint parameters in a canonical coordinate frame. Our experiments demonstrate that a SfA model trained in simulation can generalize to many unseen object categories with diverse structures and to real-world objects. Empirically, SfA outperforms a pipeline of state-of-the-art components by 25.4 3D IoU percentage points on unseen categories, while matching already performant joint estimation baselines.
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。
