Unsupervised Watertight Mesh Generation for Physics Simulation Applications Using Growing Neural Gas on Noisy Free-Form Object Models

TL;DR

This paper introduces an unsupervised framework that generates watertight, high-quality meshes from noisy, incomplete point clouds of complex objects, suitable for physics simulations, using a modified Growing Neural Gas technique.

Contribution

The novel framework combines a modified Growing Neural Gas method with post-processing to produce watertight meshes from noisy, real-world sensor data without user intervention.

Findings

Handles noisy, incomplete point clouds from consumer RGBD sensors.

Produces watertight meshes suitable for physics simulation.

Unsupervised parameter optimization improves mesh quality.

Abstract

We present a framework to generate watertight mesh representations in an unsupervised manner from noisy point clouds of complex, heterogeneous objects with free-form surfaces. The resulting meshes are ready to use in applications like kinematics and dynamics simulation where watertightness and fast processing are the main quality criteria. This works with no necessity of user interaction, mainly by utilizing a modified Growing Neural Gas technique for surface reconstruction combined with several post-processing steps. In contrast to existing methods, the proposed framework is able to cope with input point clouds generated by consumer-grade RGBD sensors and works even if the input data features large holes, e.g. a missing bottom which was not covered by the sensor. Additionally, we explain a method to unsupervisedly optimize the parameters of our framework in order to improve generalization quality and, at the same time, keep the resulting meshes as coherent as possible to the original object regarding visual and geometric properties.