Skeleton-based Robust Registration Framework for Corrupted 3D Point Clouds

2025-09-29

AI Summary

To address the degraded robustness of 3D point cloud registration under noise, non-uniform density, and geometric deformation, this paper proposes a skeleton-based end-to-end robust registration framework. Our method models point cloud topology and global structure via a damage-resilient skeletal representation. We introduce a distribution distance loss that explicitly enforces consistency between source and target skeletons, jointly preserving local geometric fidelity and global structural stability. Furthermore, we adopt a joint point-cloud–skeleton transformation and co-optimization strategy to achieve deep integration of geometric and topological information. Extensive experiments across diverse degradation scenarios demonstrate that our approach achieves significantly higher accuracy and robustness than current state-of-the-art methods. The framework is validated on real-world perception tasks including autonomous driving, robotic navigation, and medical 3D imaging.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Point cloud registration is fundamental in 3D vision applications, including autonomous driving, robotics, and medical imaging, where precise alignment of multiple point clouds is essential for accurate environment reconstruction. However, real-world point clouds are often affected by sensor limitations, environmental noise, and preprocessing errors, making registration challenging due to density distortions, noise contamination, and geometric deformations. Existing registration methods rely on direct point matching or surface feature extraction, which are highly susceptible to these corruptions and lead to reduced alignment accuracy. To address these challenges, a skeleton-based robust registration framework is presented, which introduces a corruption-resilient skeletal representation to improve registration robustness and accuracy. The framework integrates skeletal structures into the registration process and combines the transformations obtained from both the corrupted point cloud alignment and its skeleton alignment to achieve optimal registration. In addition, a distribution distance loss function is designed to enforce the consistency between the source and target skeletons, which significantly improves the registration performance. This framework ensures that the alignment considers both the original local geometric features and the global stability of the skeleton structure, resulting in robust and accurate registration results. Experimental evaluations on diverse corrupted datasets demonstrate that SRRF consistently outperforms state-of-the-art registration methods across various corruption scenarios, including density distortions, noise contamination, and geometric deformations. The results confirm the robustness of SRRF in handling corrupted point clouds, making it a potential approach for 3D perception tasks in real-world scenarios.

Problem

• Addressing corrupted 3D point clouds with density distortions and noise
• Overcoming limitations of direct point matching in registration methods
• Improving alignment accuracy under geometric deformations and corruptions

Innovation

• Skeleton-based registration framework for corrupted 3D point clouds
• Combines point cloud and skeleton alignment transformations
• Uses distribution distance loss for skeleton consistency enforcement