An Adaptive Data Representation for Robust Point-Set Registration and Merging

TL;DR

This paper introduces a robust, adaptive data representation for point-set registration and merging that improves noise and occlusion handling using Gaussian mixture models derived from support vector machines.

Contribution

It proposes a novel framework combining SVM-based point-set representation with Gaussian mixtures, enhancing robustness and efficiency in registration and merging tasks.

Findings

Outperforms existing methods in noisy and occluded scenarios

Demonstrates robustness on 2D and 3D datasets

Introduces GMMerge for efficient model merging

Abstract

This paper presents a framework for rigid point-set registration and merging using a robust continuous data representation. Our point-set representation is constructed by training a one-class support vector machine with a Gaussian radial basis function kernel and subsequently approximating the output function with a Gaussian mixture model. We leverage the representation's sparse parametrisation and robustness to noise, outliers and occlusions in an efficient registration algorithm that minimises the L2 distance between our support vector--parametrised Gaussian mixtures. In contrast, existing techniques, such as Iterative Closest Point and Gaussian mixture approaches, manifest a narrower region of convergence and are less robust to occlusions and missing data, as demonstrated in the evaluation on a range of 2D and 3D datasets. Finally, we present a novel algorithm, GMMerge, that parsimoniously and equitably merges aligned mixture models, allowing the framework to be used for reconstruction and mapping.