DCUDF2: Improving Efficiency and Accuracy in Extracting Zero Level Sets from Unsigned Distance Fields

TL;DR

DCUDF2 is a novel method that significantly improves the accuracy, robustness, and efficiency of extracting zero level sets from unsigned distance fields, enabling better geometric and topological fidelity.

Contribution

We introduce DCUDF2, an enhanced extraction method with an accuracy-aware loss, topology correction, and self-adaptive operations, surpassing previous techniques in quality and robustness.

Findings

Outperforms DCUDF in geometric fidelity and topological accuracy

Reduces hyper-parameter dependence for robustness

Boosts runtime efficiency through new operations

Abstract

Unsigned distance fields (UDFs) allow for the representation of models with complex topologies, but extracting accurate zero level sets from these fields poses significant challenges, particularly in preserving topological accuracy and capturing fine geometric details. To overcome these issues, we introduce DCUDF2, an enhancement over DCUDF--the current state-of-the-art method--for extracting zero level sets from UDFs. Our approach utilizes an accuracy-aware loss function, enhanced with self-adaptive weights, to improve geometric quality significantly. We also propose a topology correction strategy that reduces the dependence on hyper-parameter, increasing the robustness of our method. Furthermore, we develop new operations leveraging self-adaptive weights to boost runtime efficiency. Extensive experiments on surface extraction across diverse datasets demonstrate that DCUDF2 outperforms DCUDF and existing methods in both geometric fidelity and topological accuracy. We will make the source code publicly available.