Robust Partial 3D Point Cloud Registration via Confidence Estimation under Global Context

2025-09-29

AI Summary

To address low reliability in partial point cloud registration caused by structural ambiguity, occlusion, and noise, this paper proposes a global-context-aware confidence estimation framework. The method jointly models overlap discrimination and correspondence reliability via a hybrid overlap confidence estimation module; it further introduces a global attention mechanism to dynamically generate soft confidence weights, which drive a differentiable weighted SVD solver for end-to-end adaptive registration. By integrating semantic-geometric joint features, context-aware matching, and robust optimization, the approach significantly improves alignment accuracy and generalization. Extensive experiments demonstrate state-of-the-art performance on ModelNet40, ScanObjectNN, and 7Scenes—particularly under high noise and severe occlusion, where it exhibits superior robustness compared to existing methods.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by proposing Confidence Estimation under Global Context (CEGC), a unified, confidence-driven framework for robust partial 3D registration. CEGC enables accurate alignment in complex scenes by jointly modeling overlap confidence and correspondence reliability within a shared global context. Specifically, the hybrid overlap confidence estimation module integrates semantic descriptors and geometric similarity to detect overlapping regions and suppress outliers early. The context-aware matching strategy smitigates ambiguity by employing global attention to assign soft confidence scores to correspondences, improving robustness. These scores guide a differentiable weighted singular value decomposition solver to compute precise transformations. This tightly coupled pipeline adaptively down-weights uncertain regions and emphasizes contextually reliable matches. Experiments on ModelNet40, ScanObjectNN, and 7Scenes 3D vision datasets demonstrate that CEGC outperforms state-of-the-art methods in accuracy, robustness, and generalization. Overall, CEGC offers an interpretable and scalable solution to partial point cloud registration under challenging conditions.

Problem

• Robust partial 3D point cloud registration under structural ambiguity
• Addressing partial visibility and noise in 3D scene understanding
• Improving alignment accuracy in complex autonomous perception scenarios

Innovation

• Confidence-driven framework for robust partial 3D registration
• Hybrid overlap confidence estimation with semantic-geometric integration
• Context-aware matching with global attention and weighted SVD solver