ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups

TL;DR

ManifoldPlus is a new scalable and robust method for converting complex, non-manifold triangle meshes into accurate, watertight manifold surfaces without relying on face normals, suitable for high-complexity models.

Contribution

It introduces a simple, projection-based optimization approach that accurately recovers watertight manifolds from triangle soups, handling zero-volume structures and scaling efficiently.

Findings

Successfully generates watertight meshes from diverse datasets.

Outperforms existing methods in robustness, efficiency, and accuracy.

Handles high-complexity models like city-scale meshes.

Abstract

We present ManifoldPlus, a method for robust and scalable conversion of triangle soups to watertight manifolds. While many algorithms in computer graphics require the input mesh to be a watertight manifold, in practice many meshes designed by artists are often for visualization purposes, and thus have non-manifold structures such as incorrect connectivity, ambiguous face orientation, double surfaces, open boundaries, self-intersections, etc. Existing methods suffer from problems in the inputs with face orientation and zero-volume structures. Additionally most methods do not scale to meshes of high complexity. In this paper, we propose a method that extracts exterior faces between occupied voxels and empty voxels, and uses a projection-based optimization method to accurately recover a watertight manifold that resembles the reference mesh. Compared to previous methods, our methodology is simpler. It does not rely on face normals of the input triangle soups and can accurately recover zero-volume structures. Our algorithm is scalable, because it employs an adaptive Gauss-Seidel method for shape optimization, in which each step is an easy-to-solve convex problem. We test ManifoldPlus on ModelNet10 and AccuCity datasets to verify that our methods can generate watertight meshes ranging from object-level shapes to city-level models. Furthermore, through our experimental evaluations, we show that our method is more robust, efficient and accurate than the state-of-the-art. Our implementation is publicly available.