Revisiting Point Cloud Completion: Are We Ready For The Real-World?

2024-11-26

arXiv.org

AI Summary

Existing point cloud completion methods suffer severe performance degradation on real-world industrial scenarios (e.g., railway infrastructure) due to sparse, incomplete, and non-uniform point distributions. To address this, we introduce RealPC—the first large-scale, realistic railway infrastructure point cloud completion dataset (40K paired samples across 21 structural categories)—and identify topological distortion and structural collapse as fundamental failure modes of mainstream methods on real data. We propose the first integration of algebraic topology and persistent homology (PH) into point cloud completion, designing a 3D skeleton-guided reconstruction framework grounded in 0-dimensional PH priors to enforce topological consistency. Extensive evaluation on RealPC demonstrates that our method significantly improves global structural plausibility and topological fidelity, establishing a new benchmark for point cloud completion in practical industrial settings.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Point clouds acquired in constrained and challenging real-world settings are incomplete, non-uniformly sparse, or both. These obstacles present acute challenges for a vital task - point cloud completion. Using tools from Algebraic Topology and Persistent Homology ($mathcal{PH}$), we demonstrate that current benchmark synthetic point clouds lack rich topological features that are important constituents of point clouds captured in realistic settings. To facilitate research in this direction, we contribute the first real-world industrial point cloud dataset for point cloud completion, RealPC - a diverse set of rich and varied point clouds, consisting of $sim$ 40,000 pairs across 21 categories of industrial structures in railway establishments. Our benchmark results on several strong baselines reveal a striking observation - the existing methods are tailored for synthetic datasets and fail miserably in real-world settings. Building on our observation that RealPC consists of several 0 and 1-dimensional $mathcal{PH}$-based topological features, we demonstrate the potential of integrating Homology-based topological priors into existing works. More specifically, we present how 0-dimensional $mathcal{PH}$ priors, which extract the global topology of a complete shape in the form of a 3-D skeleton, can assist a model in generating topologically-consistent complete shapes.

Problem

• Point Cloud Completion
• Non-uniform Distribution
• Partial Occlusion

Innovation

• Algebraic Topology
• Shape Features
• Point Cloud Completion