GAMesh: Guided and Augmented Meshing for Deep Point Networks

TL;DR

GAMesh is a novel meshing algorithm that combines a mesh prior with point network outputs to produce accurate, topology-preserving surfaces, improving single-view shape prediction and surface reconstruction for sparse point clouds.

Contribution

This paper introduces GAMesh, a new meshing method that separates geometry from topology, enabling better surface reconstruction and direct vertex optimization in point networks.

Findings

GAMesh produces topology-preserving surfaces with high geometric fidelity.

It improves surface reconstruction for sparse and single-view point clouds.

Training with GAMesh allows direct vertex position optimization for adaptive meshes.

Abstract

We present a new meshing algorithm called guided and augmented meshing, GAMesh, which uses a mesh prior to generate a surface for the output points of a point network. By projecting the output points onto this prior and simplifying the resulting mesh, GAMesh ensures a surface with the same topology as the mesh prior but whose geometric fidelity is controlled by the point network. This makes GAMesh independent of both the density and distribution of the output points, a common artifact in traditional surface reconstruction algorithms. We show that such a separation of geometry from topology can have several advantages especially in single-view shape prediction, fair evaluation of point networks and reconstructing surfaces for networks which output sparse point clouds. We further show that by training point networks with GAMesh, we can directly optimize the vertex positions to generate adaptive meshes with arbitrary topologies.