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

doi:10.1109/TVCG.2025.3588659

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

0

PRE

AI

DOI：10.1109/TVCG.2025.3588659

Original

Original request for help

Save

Abstract

En 中文

Unsigned distance fields (UDFs) provide a flexible representation for models with complex topologies, but accurately extracting their zero level sets remains challenging, particularly in preserving topological correctness and fine geometric details. We present DCUDF2, an enhanced method that builds upon DCUDF to address these limitations. Our approach introduces an accuracy-aware loss function with self-adaptive weights, enabling precise geometric fitting while avoiding over-smoothing. To improve robustness, we propose a topology correction strategy that reduces the sensitivity to hyper-parameter settings. Furthermore, we develop new operations leveraging self-adaptive weights to accelerate convergence and improve runtime efficiency. Extensive experiments on diverse datasets demonstrate that DCUDF2 consistently outperforms DCUDF and existing methods in both geometric fidelity and topological accuracy.

Keywords:

Unsigned distance fields

mesh extraction

neural implicit fields

double covering

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

Abstract

Journal

Organization