BriefGPT.xyz
Nov, 2019
通过学习可微分表面表示进行形状重建
Shape Reconstruction by Learning Differentiable Surface Representations
HTML
PDF
Jan Bednarik, Shaifali Parashar, Erhan Gundogdu, Mathieu Salzmann, Pascal Fua
TL;DR
本研究利用深度神经网络的可微分性，防止曲面崩溃和强烈减少曲面重叠，在表面重构方面显著超过现有技术。
Abstract
generative models
that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of
parametric representations
. Unfortunately, they offe
→