PRNet: Self-Supervised Learning for Partial-to-Partial Registration
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 problems. 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.
Oct-29-2019
- Country:
- North America
- Canada (0.04)
- United States > Massachusetts
- Middlesex County > Cambridge (0.04)
- North America
- Genre:
- Research Report (0.64)
- Industry:
- Information Technology (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Inductive Learning (1.00)
- Neural Networks (1.00)
- Statistical Learning (0.95)
- Vision (1.00)
- Machine Learning
- Information Technology > Artificial Intelligence