PCPNet Learning Local Shape Properties from Raw Point Clouds

2017/10/31 by Paul Guerrero, Yanir Kleiman, Maks Ovsjanikov +1 · 1 citation
Computer Science · Engineering · Mathematics · #3D Shape Modeling and Analysis #Advanced Numerical Analysis Techniques #Artificial intelligence #Cartography #Computer Graphics and Visualization Techniques #Computer graphics (images) #Computer science #Computer vision #Context (archaeology) #Curvature #Geography #Geometry #Image (mathematics) #Mathematics #Noise (video) #Pattern recognition (psychology) #Point (geometry) #Point cloud #Polygon mesh #Scale (ratio) #Series (stratigraphy) #Shape context #cs.CG

paper · pdf · doi:10.1111/cgf.13343

presented at Eurographics 2018

openalex created_date 2017/11/10 · openalex publication_date 2018/05/01 · arxiv created 2018/06/19 · arxiv updated 2018/06/20 · openalex updated_date 2026/08/05

Abstract

Abstract In this paper, we propose PCPN ET , 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.

Citations

• Deep Convolutional Networks on Graph-Structured Data
• Consolidation of unorganized point clouds for surface reconstruction
• Estimating differential quantities using polynomial fitting of osculating jets
• Geometric deep learning: going beyond Euclidean data
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• Learning shape correspondence with anisotropic convolutional neural networks

Cited by

• Normal Estimation for 3D Point Clouds via Local Plane Constraint and Multi-scale Selection

Related

• Shape Generation using Spatially Partitioned Point Clouds
• ODFNet: Using orientation distribution functions to characterize 3D\n point clouds
• PIE-NET: Parametric Inference of Point Cloud Edges
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds