PCPNET: Learning Local Shape Properties from Raw Point Clouds

TL;DR

PCPNet is a deep learning method that estimates local shape properties like normals and curvature from raw, noisy point clouds using a multi-scale patch-based approach, outperforming existing techniques.

Contribution

The paper introduces a novel multi-scale PointNet-based architecture focused on local shape property estimation from raw point clouds, with new applications in shape reconstruction.

Findings

Outperforms state-of-the-art methods in normal and curvature estimation.

Effective in noisy and multi-scale point cloud scenarios.

Useful for shape reconstruction tasks.

Abstract

In this paper, we propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid-level attributes, e.g., for shape classification or semantic labeling, we suggest a patch-based learning method, in which a series of local patches at multiple scales around each point is encoded in a structured manner. Our approach is especially well-adapted for estimating local shape properties such as normals (both unoriented and oriented) and curvature from raw point clouds in the presence of strong noise and multi-scale features. Our main contributions include both a novel multi-scale variant of the recently proposed PointNet architecture with emphasis on local shape information, and a series of novel applications in which we demonstrate how learning from training data arising from well-structured triangle meshes, and applying the trained model to noisy point clouds can produce superior results compared to specialized state-of-the-art techniques. Finally, we demonstrate the utility of our approach in the context of shape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.