Timezone: »

PRNet: Self-Supervised Learning for Partial-to-Partial Registration
Yue Wang · Justin Solomon

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #96

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.

Author Information

Yue Wang (MIT)
Justin Solomon (MIT)

More from the Same Authors