EcoSta 2019: Start Registration
View Submission - EcoSta2019
Title: Transform-based unsupervised point registration and unseeded low-rank graph matching Authors:  Yuan Zhang - Ohio State University (United States) [presenting]
Abstract: Unsupervised estimation of the correspondence between two point sets has long been an attractive topic to CS and EE researchers. We focus on the vanilla form of the problem: matching two point sets that are identical over a linear transformation. We propose a novel method using Laplace transformation to directly match the underlying distributions of the two point sets. Our method provably achieves a decent error rate within polynomial time and does not require continuity conditions many previous methods rely on critically. Our method enables network comparison without strong model assumptions when node correspondence is unknown.