Orienting Point Clouds with Dipole Propagation

Abstract

Establishing a consistent normal orientation for point clouds is a notoriously difficult problem in geometry processing, requiring attention to both local and global shape characteristics. The normal direction of a point is a function of the local surface neighborhood; yet, point clouds do not disclose the full underlying surface structure. Even assuming known geodesic proximity, calculating a consistent normal orientation requires the global context. In this work, we introduce a novel approach for establishing a globally consistent normal orientation for point clouds. Our solution separates the local and global components into two different sub-problems. In the local phase, we train a neural network to learn a coherent normal direction per patch (i.e., consistently oriented normals within a single patch). In the global phase, we propagate the orientation across all coherent patches using a dipole propagation. Our dipole propagation decides to orient each patch using the electric field defined by all previously orientated patches. This gives rise to a global propagation that is stable, as well as being robust to nearby surfaces, holes, sharp features and noise.

arXiv commentSIGGRAPH 2021

References in corpus (12)

• Embodied Hands: Modeling and Capturing Hands and Bodies Together
• MeshCNN: A Network with an Edge
• Learning Representations and Generative Models for 3D Point Clouds
• PCPNET: Learning Local Shape Properties from Raw Point Clouds
• Differentiable Surface Splatting for Point-based Geometry Processing
• Point2Mesh: A Self-Prior for Deformable Meshes
• Thingi10K: A Dataset of 10,000 3D-Printing Models
• Differentiable Manifold Reconstruction for Point Cloud Denoising
• L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
• Non-Local Part-Aware Point Cloud Denoising
• Point Cloud Completion by Learning Shape Priors
• Self-Sampling for Neural Point Cloud Consolidation

Cited by in corpus (10)

• Iterative Poisson Surface Reconstruction (iPSR) for Unoriented Points
• Fast and Globally Consistent Normal Orientation based on the Winding Number Normal Consistency
• Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering
• Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction
• Point normal orientation and surface reconstruction by incorporating isovalue constraints to Poisson equation
• LFS-Aware Surface Reconstruction from Unoriented 3D Point Clouds
• Shape As Points: A Differentiable Poisson Solver
• GeoCode: Interpretable Shape Programs
• SDFs from Unoriented Point Clouds using Neural Variational Heat Distances
• Winding Clearness for Differentiable Point Cloud Optimization