Deep Part Induction from Articulated Object Pairs
Deep Part Induction from Articulated Object Pairs
复制标题
DOI：
10.1145/3272127.3275027
复制
发表时间：
2018-11-01
影响因子：
6.2
通讯作者：
Guibas, Leonidas
中科院分区：
文献类型：
--
作者：
Yi, Li;Huang, Haibin;Guibas, Leonidas
对象功能通常通过部件铰接来表达 - 就像剪刀的两个刚性部件相互枢转以执行切割功能一样。同一功能类别内的对象之间的此类接合通常是相似的。在本文中，我们探讨了不同关节状态的观察如何为 3D 物体的部分结构和运动提供证据。我们的方法将一对未分段的形状作为输入，代表两个功能相关的对象的两种不同的关节状态，并诱导它们的共同部分以及它们底层的刚性运动。这是一个具有挑战性的设置，因为我们假设没有先前的形状结构，没有先前的形状类别信息，没有一致的形状方向，关节状态可能属于不同几何形状的对象，而且我们允许输入是噪声和部分扫描，或者从 RGB 图像中提取的点云。我们的方法学习具有三个模块的神经网络架构，分别提出对应关系、估计 3D 变形流和执行分割。为了实现最佳性能，我们的架构以类似 ICP 的方式在对应、变形流和分割预测之间迭代交替。我们的结果表明，我们的方法在发现物体铰接部分的任务中显着优于最先进的技术。此外，我们的部分归纳与对象类无关，并成功推广到新的和未见过的对象。
Object functionality is often expressed through part articulation - as when the two rigid parts of a scissor pivot against each other to perform the cutting function. Such articulations are often similar across objects within the same functional category. In this paper we explore how the observation of different articulation states provides evidence for part structure and motion of 3D objects. Our method takes as input a pair of unsegmented shapes representing two different articulation states of two functionally related objects, and induces their common parts along with their underlying rigid motion. This is a challenging setting, as we assume no prior shape structure, no prior shape category information, no consistent shape orientation, the articulation states may belong to objects of different geometry, plus we allow inputs to be noisy and partial scans, or point clouds lifted from RGB images. Our method learns a neural network architecture with three modules that respectively propose correspondences, estimate 3D deformation flows, and perform segmentation. To achieve optimal performance, our architecture alternates between correspondence, deformation flow, and segmentation prediction iteratively in an ICP-like fashion. Our results demonstrate that our method significantly outperforms state-of-the-art techniques in the task of discovering articulated parts of objects. In addition, our part induction is object-class agnostic and successfully generalizes to new and unseen objects.