Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning

TL;DR

This paper introduces PSG-Net, a novel auto-encoder architecture for unsupervised point cloud learning that generates input-dependent features, leading to improved reconstruction and classification performance.

Contribution

The paper presents PSG-Net, a new auto-encoder framework with seed generation and feature propagation modules for enhanced unsupervised point cloud learning.

Findings

State-of-the-art reconstruction performance

Superior unsupervised classification results

Competitive supervised completion performance

Abstract

With the development of 3D scanning technologies, 3D vision tasks have become a popular research area. Owing to the large amount of data acquired by sensors, unsupervised learning is essential for understanding and utilizing point clouds without an expensive annotation process. In this paper, we propose a novel framework and an effective auto-encoder architecture named "PSG-Net" for reconstruction-based learning of point clouds. Unlike existing studies that used fixed or random 2D points, our framework generates input-dependent point-wise features for the latent point set. PSG-Net uses the encoded input to produce point-wise features through the seed generation module and extracts richer features in multiple stages with gradually increasing resolution by applying the seed feature propagation module progressively. We prove the effectiveness of PSG-Net experimentally; PSG-Net shows state-of-the-art performances in point cloud reconstruction and unsupervised classification, and achieves comparable performance to counterpart methods in supervised completion.