PRNet: Self-Supervised Learning for Partial-to-Partial Registration
PRNet: Self-Supervised Learning for Partial-to-Partial Registration
复制标题
DOI：
--
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Yue Wang;J. Solomon
中科院分区：
文献类型：
--
作者：
Yue Wang;J. Solomon
我们提出了一个简单、灵活和通用的框架，称为部分注册网络（PRNet），用于部分到部分点云注册。受最近提出的基于学习的配准方法的启发，我们使用深度网络来解决对齐和部分对应问题的非凸性。以前基于学习的方法假设整个形状是可见的，而PRNet适用于部分到部分的配准，在合成数据上优于PointNetLK、DCP和非学习方法。PRNet是自我监督的，共同学习适当的几何表示，找到部分视图之间的共同点的关键点检测器，以及关键点到关键点的对应关系。我们展示了PRNet在视图和对象之间一致地预测关键点和对应关系。此外，学习到的表示可以转移到分类中。
We present a simple, flexible, and general framework titled Partial Registration Network (PRNet), for partial-to-partial point cloud registration. Inspired by recently-proposed learning-based methods for registration, we use deep networks to tackle non-convexity of the alignment and partial correspondence problem. While previous learning-based methods assume the entire shape is visible, PRNet is suitable for partial-to-partial registration, outperforming PointNetLK, DCP, and non-learning methods on synthetic data. PRNet is self-supervised, jointly learning an appropriate geometric representation, a keypoint detector that finds points in common between partial views, and keypoint-to-keypoint correspondences. We show PRNet predicts keypoints and correspondences consistently across views and objects. Furthermore, the learned representation is transferable to classification.