IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration

2026-03-13

AI Summary

This work addresses the challenges of insufficient accuracy and poor robustness in point cloud registration under real-world conditions involving strong noise, severe occlusion, and large-scale transformations. To this end, we propose a novel hierarchical pyramid architecture featuring two key innovations: a Hierarchical Cross-Layer Attention (HCLA) mechanism and an Iterative Geometric-Aware Refinement (IGAR) module. The HCLA enhances multi-scale feature fusion through skip connections, while the IGAR iteratively refines correspondences under geometric constraints, jointly improving local consistency and matching precision. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches across four benchmarks—3D(Lo)Match, KITTI, and nuScenes—achieving notable gains in both registration accuracy and robustness.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling. Despite its widespread use, existing methods often fail when facing real-world challenges like heavy noise, significant occlusions, and large-scale transformations. These limitations frequently result in compromised registration accuracy and insufficient robustness in complex environments. In this paper, we propose IGASA as a novel registration framework constructed upon a Hierarchical Pyramid Architecture (HPA) designed for robust multi-scale feature extraction and fusion. The framework integrates two pivotal components consisting of the Hierarchical Cross-Layer Attention (HCLA) module and the Iterative Geometry-Aware Refinement (IGAR) module. The HCLA module utilizes skip attention mechanisms to align multi-resolution features and enhance local geometric consistency. Simultaneously, the IGAR module is designed for the fine matching phase by leveraging reliable correspondences established during coarse matching. This synergistic integration within the architecture allows IGASA to adapt effectively to diverse point cloud structures and intricate transformations. We evaluate the performance of IGASA on four widely recognized benchmark datasets including 3D(Lo)Match, KITTI, and nuScenes. Our extensive experiments consistently demonstrate that IGASA significantly surpasses state-of-the-art methods and achieves notable improvements in registration accuracy. This work provides a robust foundation for advancing point cloud registration techniques while offering valuable insights for practical 3D vision applications. The code for IGASA is available in \href{https://github.com/DongXu-Zhang/IGASA}{https://github.com/DongXu-Zhang/IGASA}.

Problem

• point cloud registration
• noise
• occlusion
• large-scale transformations
• robustness

Innovation

• Hierarchical Pyramid Architecture
• Skip Attention
• Geometry-Aware Refinement
• Point Cloud Registration
• Multi-scale Feature Fusion