Neural Surface Detection for Unsigned Distance Fields
This work addresses a domain-specific problem for researchers and practitioners in 3D computer vision and graphics, offering an incremental improvement by enabling existing surface extraction algorithms to work with UDFs.
The paper tackles the problem of extracting surfaces from Unsigned Distance Fields (UDFs), which traditional methods like Marching Cubes cannot handle directly, by introducing a deep-learning approach that converts UDFs locally into Signed Distance Fields (SDFs) for triangulation, achieving better accuracy than existing methods and generalizing well to unseen shapes and datasets.
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.