Robust Watertight Manifold Surface Generation Method for ShapeNet Models

By Jingwei Huang, Hao Su, Leonidas J. Guibas. 2018

155 citations recorded by the source corpus.

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.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Geology

Citations in the corpus

Deep Level Sets: Implicit Surface Representations for 3D Shape Inference (2019, methodology): “As ShapeNet models often do not have an empty interior, we used the manifold surface generation method of [17] as a preprocessing stage to generate closed manifolds of those models and used them as ground truth.”
SAPIEN: A SimulAted Part-Based Interactive ENvironment (2020, methodology): “For accurate simulation of contact, we decompose meshes into convex parts [29, 19].”
Implicit Surface Representations As Layers in Neural Networks (2019, methodology): “As ShapeNet models often do not have an empty interior, we used the manifold surface generation method of [17] as a preprocessing stage to generate closed manifolds of those models and used them as ground truth.”
Shape As Points: A Differentiable Poisson Solver (2021, methodology): “If the genus is larger than zero, we apply the watertight manifold algorithm [24] using a low-resolution octree reconstruction on the output mesh of SPSR to obtain a coarse initial mesh.”
CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (2024, unknown): “Popular remeshing tools such as Manifold [Huang et al. 2018a], while efficient, tend to smooth edges and corners, with its updated version, ManifoldPlus [Huang et al. 2020], showing improved but inconsistent results.”
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding (2018, background): “The annotators draw boundary lines on the remeshed watertight surface [15] and the mesh cutting algorithm automatically splits the mesh into multiple smaller subcomponents.”
Local Implicit Grid Representations for 3D Scenes (2020, unknown): “As both SceneNet and Matterport 3D datasets are not watertight, and in addition to that, SceneNet dataset has various artifacts such as double-sided faces that produce conflicting normal samples, we preprocess both datasets using the watertight manifold algorithm as describe in [18].”