We present an efficient and robust point cloud registration (PCR) workflow
for part-wise rigid point cloud alignment using the Microsoft HoloLens 2. Point
Cloud Registration (PCR) is an important problem in Augmented and Mixed Reality
use cases, and we present a study for a special class of non-rigid
transformations. Many commonly encountered objects are composed of rigid parts
that move relative to one another about joints resulting in non-rigid
deformation of the whole object such as robots with manipulators, and machines
with hinges. The workflow presented allows us to register the point cloud with
various configurations of the point cloud.

本研究旨在介绍一种基于微软 HoloLens2 的高效和鲁棒的点云配准（PCR）工作流程，用于非刚性变换点云对齐，与常见刚性部分运动物体如机器人和机械相适用。

PWR-Align：利用部分 - 整体关系进行混合现实应用程序中的部分刚性点云配准

PWR-Align: Leveraging Part-Whole Relationships for Part-wise Rigid Point  Cloud Registration in Mixed Reality Applications

Despite the advances in extracting local features achieved by handcrafted and
learning-based descriptors, they are still limited by the lack of invariance to
non-rigid transformations. In this paper, we present a new approach to compute
features from still images that are robust to non-rigid deformations to
circumvent the problem of matching deformable surfaces and objects. Our
deformation-aware local descriptor, named DEAL, leverages a polar sampling and
a spatial transformer warping to provide invariance to rotation, scale, and
image deformations. We train the model architecture end-to-end by applying
isometric non-rigid deformations to objects in a simulated environment as
guidance to provide highly discriminative local features. The experiments show
that our method outperforms state-of-the-art handcrafted, learning-based image,
and RGB-D descriptors in different datasets with both real and realistic
synthetic deformable objects in still images. The source code and trained model
of the descriptor are publicly available at
this https URL

本文提出了一种新的局部特征计算方法 DEAL，通过极坐标采样和空间变换器抵消旋转、尺度和形变的影响，能够提供不变性。我们将模型应用于模拟环境中的几何体进行同构非刚性变形，以提供高度判别局部特征，并证明了该方法在不同数据集中相对于现有的局部特征和 RGB-D 描述符跑出了更好的结果。