SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance

2025-03-23

AI Summary

Point cloud completion faces challenges of local geometric detail loss and geometric inconsistency across partially missing regions. To address these, we propose a symmetry-guided high-fidelity completion framework—the first to explicitly incorporate geometric symmetry as a strong prior into the completion process. Our method comprises two core components: (1) a Local Symmetry Transformation Network (LSTNet), which estimates local symmetric structures and constructs geometrically aligned partial-missing pairs; and (2) a Symmetry-Guided Transformer (SGFormer), which leverages symmetry-aware features to drive fine-grained reconstruction of missing regions. Evaluated on multiple benchmarks, our framework significantly outperforms state-of-the-art methods, achieving simultaneous improvements in global completeness, local detail fidelity, and cross-region geometric consistency.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Point cloud completion aims to recover a complete point shape from a partial point cloud. Although existing methods can form satisfactory point clouds in global completeness, they often lose the original geometry details and face the problem of geometric inconsistency between existing point clouds and reconstructed missing parts. To tackle this problem, we introduce SymmCompletion, a highly effective completion method based on symmetry guidance. Our method comprises two primary components: a Local Symmetry Transformation Network (LSTNet) and a Symmetry-Guidance Transformer (SGFormer). First, LSTNet efficiently estimates point-wise local symmetry transformation to transform key geometries of partial inputs into missing regions, thereby generating geometry-align partial-missing pairs and initial point clouds. Second, SGFormer leverages the geometric features of partial-missing pairs as the explicit symmetric guidance that can constrain the refinement process for initial point clouds. As a result, SGFormer can exploit provided priors to form high-fidelity and geometry-consistency final point clouds. Qualitative and quantitative evaluations on several benchmark datasets demonstrate that our method outperforms state-of-the-art completion networks.

Problem

• Recover complete point clouds from partial inputs
• Preserve original geometry details during completion
• Ensure geometric consistency between existing and reconstructed parts

Innovation

• Local Symmetry Transformation Network for geometry-align pairs
• Symmetry-Guidance Transformer for refinement process
• High-fidelity and geometry-consistency final point clouds