VoroUDF: Meshing Unsigned Distance Fields with Voronoi Optimization

TL;DR

VoroUDF introduces a Voronoi-based algorithm for high-quality mesh reconstruction from Unsigned Distance Fields, effectively handling complex geometries and features without common pitfalls of prior methods.

Contribution

The paper presents a novel Voronoi optimization approach for UDF meshing that improves topological accuracy and geometric fidelity over existing techniques.

Findings

Enhanced topological consistency in reconstructed meshes

Improved geometric fidelity compared to previous methods

Produces lightweight meshes suitable for real-time applications

Abstract

We present VoroUDF, an algorithm for reconstructing high-quality triangle meshes from Unsigned Distance Fields (UDFs). Our algorithm supports non-manifold geometry, sharp features, and open boundaries, without relying on error-prone inside/outside estimation, restrictive look-up tables nor topologically noisy optimization. Our Voronoi-based formulation combines a L_1 tangent minimization with feature-aware repulsion to robustly recover complex surface topology. It achieves significantly improved topological consistency and geometric fidelity compared to existing methods, while producing lightweight meshes suitable for downstream real-time and interactive applications.