Learning Representations and Generative Models for 3D Point Clouds

TL;DR

This paper introduces a deep autoencoder for 3D point clouds that achieves high-quality reconstruction, improves recognition, and enables shape editing, while also evaluating various generative models with new quantitative metrics.

Contribution

It presents a novel autoencoder architecture for 3D point clouds and comprehensive evaluation of generative models using new metrics, highlighting GMMs' superior performance.

Findings

Autoencoder achieves state-of-the-art reconstruction quality.

Learned representations improve 3D recognition and shape editing.

GMMs trained in the latent space outperform other generative models.

Abstract

Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with state-of-the-art reconstruction quality and generalization ability. The learned representations outperform existing methods on 3D recognition tasks and enable shape editing via simple algebraic manipulations, such as semantic part editing, shape analogies and shape interpolation, as well as shape completion. We perform a thorough study of different generative models including GANs operating on the raw point clouds, significantly improved GANs trained in the fixed latent space of our AEs, and Gaussian Mixture Models (GMMs). To quantitatively evaluate generative models we introduce measures of sample fidelity and diversity based on matchings between sets of point clouds. Interestingly, our evaluation of generalization, fidelity and diversity reveals that GMMs trained in the latent space of our AEs yield the best results overall.