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.

We formulate the surface detection problem as a per-cell classification task. In each cell, we map point distances and gradients to a sign configuration of the cell vertices, which can be used to mesh the surface via Marching Cubes or Dual Contouring.

We compute Chamfer Distance and Image Consistency over hundreds of shapes to find the following results.
Note: DCUDF can achieve better accuracy by removing the cutting step. However this would make the surface double layered.

@misc{stella2024neuralsurfacedetectionunsigned,
      title={Neural Surface Detection for Unsigned Distance Fields}, 
      author={Federico Stella and Nicolas Talabot and Hieu Le and Pascal Fua},
      year={2024},
      eprint={2407.18381},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.18381}, 
}