English

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

Machine Learning 2019-10-30 v2 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1910.12240,
  title  = {PRNet: Self-Supervised Learning for Partial-to-Partial Registration},
  author = {Yue Wang and Justin M. Solomon},
  journal= {arXiv preprint arXiv:1910.12240},
  year   = {2019}
}

Comments

NeurIPS 2019

R2 v1 2026-06-23T11:56:11.292Z