Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds

by   Yongming Rao, et al.

Local and global patterns of an object are closely related. Although each part of an object is incomplete, the underlying attributes about the object are shared among all parts, which makes reasoning the whole object from a single part possible. We hypothesize that a powerful representation of a 3D object should model the attributes that are shared between parts and the whole object, and distinguishable from other objects. Based on this hypothesis, we propose to learn point cloud representation by bidirectional reasoning between the local structures at different abstraction hierarchies and the global shape without human supervision. Experimental results on various benchmark datasets demonstrate the unsupervisedly learned representation is even better than supervised representation in discriminative power, generalization ability, and robustness. We show that unsupervisedly trained point cloud models can outperform their supervised counterparts on downstream classification tasks. Most notably, by simply increasing the channel width of an SSG PointNet++, our unsupervised model surpasses the state-of-the-art supervised methods on both synthetic and real-world 3D object classification datasets. We expect our observations to offer a new perspective on learning better representation from data structures instead of human annotations for point cloud understanding.


page 1

page 2

page 3

page 4


Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning

In this paper, we propose a simple and general framework for self-superv...

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

The point cloud representation of an object can have a large geometric v...

Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds

Recently deep learning has achieved significant progress on point cloud ...

Unsupervised Representation Learning for 3D Point Cloud Data

Though a number of point cloud learning methods have been proposed to ha...

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

Few-shot segmentation of point cloud remains a challenging task, as ther...

CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration

This paper considers online object-level mapping using partial point-clo...

Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting

Learning from unlabeled or partially labeled data to alleviate human lab...