Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning
This addresses the problem of expensive annotation in 3D vision tasks by enabling more effective unsupervised learning for point clouds, though it appears incremental as it builds on existing auto-encoder frameworks.
The paper tackles unsupervised learning for point clouds by proposing PSG-Net, a novel auto-encoder that generates input-dependent features for latent point sets, achieving state-of-the-art performance in reconstruction and unsupervised classification with comparable results in supervised completion.
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.