Neural Surface Detection for Unsigned Distance Fields

TL;DR

This paper presents a deep-learning method to convert Unsigned Distance Fields into Signed Distance Fields locally, enabling accurate surface extraction and improving existing dual meshing techniques.

Contribution

The authors introduce a novel neural approach for local conversion of UDFs to SDFs, enhancing surface detection accuracy and compatibility with traditional triangulation algorithms.

Findings

Achieves better surface detection accuracy than existing methods.

Generalizes well to unseen shapes and datasets.

Improves dual meshing results without parameter tuning.

Abstract

Extracting surfaces from Signed Distance Fields (SDFs) can be accomplished using traditional algorithms, such as Marching Cubes. However, since they rely on sign flips across the surface, these algorithms cannot be used directly on Unsigned Distance Fields (UDFs). In this work, we introduce a deep-learning approach to taking a UDF and turning it locally into an SDF, so that it can be effectively triangulated using existing algorithms. We show that it achieves better accuracy in surface detection than existing methods. Furthermore it generalizes well to unseen shapes and datasets, while being parallelizable. We also demonstrate the flexibily of the method by using it in conjunction with DualMeshUDF, a state of the art dual meshing method that can operate on UDFs, improving its results and removing the need to tune its parameters.