Effective Point Cloud Analysis Using Multi-Scale Features

Fully exploring the correlation of local features and their spatial distribution in point clouds is essential for feature modeling. This paper, inspired by convolutional neural networks (CNNs), explores the relationship between local patterns and point coordinates from a novel perspective and proposes a lightweight structure based on multi-scale features and a two-step fusion strategy. Specifically, local features of multi-scales and their spatial distribution can be regarded as independent features corresponding to different levels of geometric significance, which are extracted by multiple parallel branches and then merged on multiple levels. In this way, the proposed model generates a shape-level representation that contains rich local characteristics and the spatial relationship between them. Moreover, with the shared multi-layer perceptrons (MLPs) as basic operators, the proposed structure is so concise that it converges rapidly, and so we introduce the snapshot ensemble to improve performance further. The model is evaluated on classification and part segmentation tasks. The experiments prove that our model achieves on-par or better performance than previous state-of-the-art (SOTA) methods.