Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds

TL;DR

This paper introduces an unsupervised method to learn meaningful low-dimensional vector representations of 3D objects from point clouds, leveraging contextual information to improve semantic clustering and enable interpolation of object embeddings.

Contribution

It presents a novel unsupervised approach for object-level feature learning from point clouds, inspired by word embedding techniques, and demonstrates its effectiveness in semantic clustering and embedding interpolation.

Findings

Enhanced clustering of semantic object classes

Generated continuous and meaningful object embeddings

Improved differentiation of object categories

Abstract

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the context of 3D vision. This, despite the fact that the physical 3D spaces have a similar semantic structure to bodies of text: words are surrounded by words that are semantically related, just like objects are surrounded by other objects that are similar in concept and usage. In this work, we exploit this structure in learning semantically meaningful low dimensional vector representations of objects. We learn these vector representations by mining a dataset of scanned 3D spaces using an unsupervised algorithm. We represent objects as point clouds, a flexible and general representation for 3D data, which we encode into a vector representation. We show that using our method to include context increases the ability of a clustering algorithm to distinguish different semantic classes from each other. Furthermore, we show that our algorithm produces continuous and meaningful object embeddings through interpolation experiments.