Understanding 3D point cloud models for learning purposes has become an
imperative challenge for real-world identification such as autonomous driving
systems. A wide variety of solutions using deep learning have been proposed for
point cloud segmentation, object detection, and classification. These methods,
however, often require a considerable number of model parameters and are
computationally expensive. We study a semantic dimension of given 3D data
points and propose an efficient method called Meta-Semantic Learning
(Meta-SeL). Meta-SeL is an integrated framework that leverages two input 3D
local points (input 3D models and part-segmentation labels), providing a time
and cost-efficient, and precise projection model for a number of 3D recognition
tasks. The results indicate that Meta-SeL yields competitive performance in
comparison with other complex state-of-the-art work. Moreover, being random
shuffle invariant, Meta-SeL is resilient to translation as well as jittering
noise.

本文介绍了一种称为元语义学习 (Meta-SeL) 的方法，该方法利用两个输入的 3D 局部点（输入 3D 模型和部分分割标签），提供了一种时间和成本高效、精确的投影模型，用于许多 3D 识别任务。根据结果表明，Meta-SeL 在与其他复杂的最新研究的比较中，表现出了竞争性能。此外，Meta-SeL 对随机洗牌不变性具有弹性，也对平移和抖动噪声有较高的鲁棒性。