Can I read TEASER: Fast and Certifiable Point Cloud Registration on EtoBox?

TEASER: Fast and Certifiable Point Cloud Registration by Yang, Heng; Shi, Jingnan; Carlone, Luca is a scholarly article available to read on EtoBox.

What is TEASER: Fast and Certifiable Point Cloud Registration about?

We propose the first fast and certifiable algorithm for the registration of two sets of 3D points in the presence of large amounts of outlier correspondences. We first reformulate the registration problem using a Truncated Least Squares (TLS) cost that is insensitive to a large fraction of spurious correspondences. Then, we provide a general graph-theoretic framework to decouple scale, rotation, and translation estimation, which allows solving in cascade for the three transformations. Despite the fact that each subproblem is still non-convex and combinatorial in nature, we show that (i) TLS scale and (component-wise) translation estimation can be solved in polynomial time via adaptive voting, (ii) TLS rotation estimation can be relaxed to a semidefinite program (SDP) and the relaxation is tight, even in the presence of extreme outlier rates, and (iii) the graph-theoretic framework allows drastic pruning of outliers by finding the maximum clique. We name the resulting algorithm TEASER (Truncated least squares Estimation And SEmidefinite Relaxation). While solving large SDP relaxations is typically slow, we develop a second fast and certifiable algorithm, named TEASER++, that uses gr

Author

Yang, Heng; Shi, Jingnan; Carlone, Luca

Published

2020

Language

EN