The problems of shape classification and part segmentation from 3D point
clouds have garnered increasing attention in the last few years. Both of these
problems, however, suffer from relatively small training sets, creating the
need for statistically efficient methods to learn 3D shape representations. In
this paper, we investigate the use of Approximate Convex Decompositions (ACD)
as a self-supervisory signal for label-efficient learning of point cloud
representations. We show that using ACD to approximate ground truth
segmentation provides excellent self-supervision for learning 3D point cloud
representations that are highly effective on downstream tasks. We report
improvements over the state-of-the-art for unsupervised representation learning
on the ModelNet40 shape classification dataset and significant gains in
few-shot part segmentation on the ShapeNetPart dataset.Code available at
this https URL

本文研究了在 3D 点云中使用 Approximate Convex Decompositions（ACD）进行自我监督训练的方法，以实现标签高效的学习点云表示。结果表明，ACD 提供了一种极佳的自我监督信号，可以有效地学习 3D 点云表示，并在下游任务中获得卓越的性能，例如 ModelNet40 形状分类数据集的无监督表示学习，并在 ShapeNetPart 数据集上获得显著的少样本部件分割增益。