NeuralMeshing: Differentiable Meshing of Implicit Neural Representations

TL;DR

NeuralMeshing introduces a differentiable, iterative algorithm for extracting high-quality, adaptive triangle meshes from neural implicit representations, improving mesh regularity and efficiency.

Contribution

It presents the first differentiable meshing method that handles unknown topology and size, producing regular, adaptive meshes directly from neural implicit models.

Findings

Produces meshes with fewer triangles and regular tessellation patterns.

Achieves comparable reconstruction accuracy to existing methods.

Demonstrates adaptability to various shape scales and local curvature.

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.