MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks

TL;DR

MeshUDF introduces a fast, accurate, and differentiable meshing method for Unsigned Distance Fields, enabling efficient surface extraction and fitting of sparse data with pretrained networks.

Contribution

It extends the marching cube algorithm for UDFs, making surface extraction both fast and differentiable, facilitating better integration with neural networks.

Findings

Achieves faster surface extraction compared to previous methods.

Maintains high accuracy in mesh generation from UDFs.

Enables differentiable surface extraction for neural network fitting.

Abstract

Unsigned Distance Fields (UDFs) can be used to represent non-watertight surfaces. However, current approaches to converting them into explicit meshes tend to either be expensive or to degrade the accuracy. Here, we extend the marching cube algorithm to handle UDFs, both fast and accurately. Moreover, our approach to surface extraction is differentiable, which is key to using pretrained UDF networks to fit sparse data.