BriefGPT.xyz
Aug, 2020
通过方向估计进行点云的自监督学习
Self-supervised Learning of Point Clouds via Orientation Estimation
HTML
PDF
Omid Poursaeed, Tianxing Jiang, Quintessa Qiao, Nayun Xu, Vladimir G. Kim
TL;DR
本文提出了一种基于3D自监督学习的点云学习方法，通过旋转点云实现无标签的自我监督，在形状分类和3D关键点预测等任务上表现出色，学习到的特征优于其他自监督方法。
Abstract
Point clouds provide a compact and efficient representation of 3D shapes. While deep
neural networks
have achieved impressive results on
point cloud
learning tasks, they require massive amounts of manually labele
→