论文标题
动作的结构：铰接对象的学习互动3D结构发现
Structure from Action: Learning Interactions for Articulated Object 3D Structure Discovery
论文作者
论文摘要
我们从Action（SFA）引入结构，该结构是通过一系列推断相互作用的序列来发现3D部分几何形状和未看到的铰接对象的关节参数。我们的关键见解是，应考虑构建3D铰接的CAD模型的3D相互作用和感知，尤其是对于训练期间未见的类别。通过选择信息性的相互作用，SFA发现零件并揭示遮挡的表面，例如封闭抽屉的内部。通过在3D中汇总视觉观测，SFA可以准确段段多个部分，重建零件几何形状，并在规范坐标框架中渗透所有关节参数。我们的实验表明，在模拟中训练的SFA模型可以推广到具有不同结构和现实世界对象的许多看不见的对象类别。从经验上讲，SFA在看不见的类别上优于最先进的组件的渠道25.4 3D IOU百分比点，同时匹配已经具有性能的联合估计基线。
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.
