We propose PCPNet, a deep-learning based approach for estimating local 3D shape properties in noisy point clouds, such as normals and curvature. PCPNet can estimate normals and curvature on a wide range of noise levels without parameters adjustments.

Abstract

PCPNET is 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 eachpoint 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-scalefeatures. 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 trainingdata 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 ofshape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.