BriefGPT.xyz
Dec, 2020
CorrNet3D: 3D点云密集对应的无监督端到端学习
CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds
HTML
PDF
Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan...
TL;DR
本文介绍了一种基于无监督和端到端深度学习的框架CorrNet3D,以学习3D形状之间的密集对应关系,并证明了其相对于最先进的方法具有更好的性能,源代码和预先训练好的模型可通过链接获得。
Abstract
This paper addresses the problem of computing dense
correspondence
between
3d shapes
in the form of point clouds, which is a challenging and fundamental problem in computer vision and digital geometry processing.
→