Direct Fitting of Gaussian Mixture Models

Leonid Keselman and Martial Hebert
CRV 2019

[Code]   [Paper]   [Slides]



Abstract

When fitting Gaussian Mixture Models to 3D geometry, the model is typically fit to point clouds, even when the shapes were obtained as 3D meshes. Here we present a formulation for fitting Gaussian Mixture Models (GMMs) directly to a triangular mesh instead of using points sampled from its surface. Part of this work analyzes a general formulation for evaluating likelihood of geometric objects. This modification enables fitting higher-quality GMMs under a wider range of initialization conditions. Additionally, models obtained from this fitting method are shown to produce an improvement in 3D registration for both meshes and RGB-D frames. This result is general and applicable to arbitrary geometric objects, including representing uncertainty from sensor measurements.


Visualizations

Pose Estimation Results

Triangle Covariance Structure


Paper

Leonid Keselman and Martial Hebert Direct Fitting of Gaussian Mixture Models CRV 2019.

[pdf] [bibtex]