BriefGPT.xyz
Nov, 2021
MeshUDF: 快速可微的无符号距离场网格化
MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks
HTML
PDF
Benoit Guillard, Federico Stella, Pascal Fua
TL;DR
本文介绍了一种扩展 Marching Cubes 算法的方法，能够快速而准确地将 Unsigned Distance Fields 表示的非封闭曲面转换为显式网格，并且采用的表面提取方法是可微分的，适用于稀疏数据的训练。
Abstract
Recent work modelling 3D open surfaces train deep neural networks to approximate
unsigned distance fields
(
udfs
) and implicitly represent shapes. To convert this representation to an explicit mesh, they either us
→