BriefGPT.xyz
Jan, 2022
POCO:点卷积用于曲面重建
POCO: Point Convolution for Surface Reconstruction
HTML
PDF
Alexandre Boulch, Renaud Marlet
TL;DR
研究提出了一种使用点云卷积和在每个输入点计算潜在向量的方法,然后进行最近邻的基于学习的插值。实验结果表明,该方法在大多数经典指标上明显优于其他方法,生成更精细的细节并更好地重建了更薄的体积。
Abstract
implicit neural networks
have been successfully used for
surface reconstruction
from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene i
→