Table of Contents
Fetching ...

Robust Watertight Manifold Surface Generation Method for ShapeNet Models

Jingwei Huang, Hao Su, Leonidas Guibas

TL;DR

The paper presents a robust pipeline for generating watertight 2-Manifold surfaces from ShapeNet triangle meshes by converting to a sign-based distance field and extracting an isosurface via an octree representation. It builds a detailed octree, establishes neighbor connectivity, and resolves non-manifold cases to ensure manifold surfaces, followed by vertex projection onto the original mesh with smoothing to preserve geometry. The approach yields consistent 2-Manifold outputs across ShapeNet models, with a low rate of incidental face flips, enabling reliable downstream processing. This method offers an efficient, topology-conscious alternative to traditional grid-based isosurface methods for large-scale model collections.

Abstract

In this paper, we describe a robust algorithm for 2-Manifold generation of various kinds of ShapeNet Models. The input of our pipeline is a triangle mesh, with a set of vertices and triangular faces. The output of our pipeline is a 2-Manifold with vertices roughly uniformly distributed on the geometry surface. Our algorithm uses an octree to represent the original mesh, and construct the surface by isosurface extraction. Finally, we project the vertices to the original mesh to achieve high precision. As a result, our method can be adopted efficiently to all ShapeNet models with the guarantee of correct 2-Manifold topology.

Robust Watertight Manifold Surface Generation Method for ShapeNet Models

TL;DR

The paper presents a robust pipeline for generating watertight 2-Manifold surfaces from ShapeNet triangle meshes by converting to a sign-based distance field and extracting an isosurface via an octree representation. It builds a detailed octree, establishes neighbor connectivity, and resolves non-manifold cases to ensure manifold surfaces, followed by vertex projection onto the original mesh with smoothing to preserve geometry. The approach yields consistent 2-Manifold outputs across ShapeNet models, with a low rate of incidental face flips, enabling reliable downstream processing. This method offers an efficient, topology-conscious alternative to traditional grid-based isosurface methods for large-scale model collections.

Abstract

In this paper, we describe a robust algorithm for 2-Manifold generation of various kinds of ShapeNet Models. The input of our pipeline is a triangle mesh, with a set of vertices and triangular faces. The output of our pipeline is a 2-Manifold with vertices roughly uniformly distributed on the geometry surface. Our algorithm uses an octree to represent the original mesh, and construct the surface by isosurface extraction. Finally, we project the vertices to the original mesh to achieve high precision. As a result, our method can be adopted efficiently to all ShapeNet models with the guarantee of correct 2-Manifold topology.

Paper Structure

This paper contains 7 sections, 1 figure, 3 algorithms.

Figures (1)

  • Figure 1: Non-manifold Examples