Consistent Two-Flow Network for Tele-Registration of Point Clouds

Zihao Yan, Zimu Yi, Ruizhen Hu, Niloy Jyoti Mitra, Daniel Cohen-Or, Hui Huang

Research output: Contribution to journalArticlepeer-review

Abstract

Rigid registration of partial observations is a fundamental problem in various applied fields. In computer graphics, special attention has been given to the registration between two partial point clouds generated by scanning devices. State-of-the-art registration techniques still struggle when the overlap region between the two point clouds is small, and completely fail if there is no overlap between the scan pairs. In this paper, we present a learning-based technique that alleviates this problem, and allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap, a setting that has been referred to as tele-registration. Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape. The key idea is combining the registration and completion tasks in a way that reinforces each other. In particular, we simultaneously train the registration network and completion network using two coupled flows, one that register-and-complete, and one that complete-and-register, and encourage the two flows to produce a consistent result. We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration, and hence to a better point cloud prediction that completes the registered scans. It is also worth mentioning that each of the components in our neural network outperforms state-of-the-art methods in both completion and registration. We further analyze our network with several ablation studies and demonstrate its performance on a large number of partial point clouds.

Original languageEnglish
JournalIEEE Transactions on Visualization and Computer Graphics
DOIs
StateAccepted/In press - 2021

Keywords

  • Automobiles
  • Computational modeling
  • Gold
  • Shape
  • Three-dimensional displays
  • Timing
  • Training

Fingerprint

Dive into the research topics of 'Consistent Two-Flow Network for Tele-Registration of Point Clouds'. Together they form a unique fingerprint.

Cite this