NeuralMeshing: Differentiable Meshing of Implicit Neural Representations

Abstract

The generation of triangle meshes from point clouds, i.e. meshing, is a core task in computer graphics and computer vision. Traditional techniques directly construct a surface mesh using local decision heuristics, while some recent methods based on neural implicit representations try to leverage data-driven approaches for this meshing process. However, it is challenging to define a learnable representation for triangle meshes of unknown topology and size and for this reason, neural implicit representations rely on non-differentiable post-processing in order to extract the final triangle mesh. In this work, we propose a novel differentiable meshing algorithm for extracting surface meshes from neural implicit representations. Our method produces the mesh in an iterative fashion, which makes it applicable to shapes of various scales and adaptive to the local curvature of the shape. Furthermore, our method produces meshes with regular tessellation patterns and fewer triangle faces compared to existing methods. Experiments demonstrate the comparable reconstruction performance and favorable mesh properties over baselines.

A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds

“…Recently, mesh extraction has also been addressed by the deep learning community. Neural meshing [26] specifically addresses the case where an implicit function is represented by a neural network, and aims to extract meshes with fewer triangles compared to Marching Cubes from such a function.…”