3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration

2024-11-12

arXiv.org

AI Summary

To address multi-instance point cloud registration under cluttered occlusion, this paper proposes a novel “localize-then-match” paradigm that decouples object center detection from pairwise rigid registration. Methodologically: (1) a 3D multi-object focusing module is designed for learnable object center regression; (2) a dual-mask instance matching module jointly models instance masks and overlap masks to constrain correspondence prediction; (3) self-attention and cross-attention mechanisms are introduced for the first time to model structural similarity across multiple instances. Evaluated on Scan2CAD and ROBI benchmarks, the method achieves state-of-the-art performance, significantly improving both registration accuracy and recall. The source code is publicly available.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Multi-instance point cloud registration aims to estimate the pose of all instances of a model point cloud in the whole scene. Existing methods all adopt the strategy of first obtaining the global correspondence and then clustering to obtain the pose of each instance. However, due to the cluttered and occluded objects in the scene, it is difficult to obtain an accurate correspondence between the model point cloud and all instances in the scene. To this end, we propose a simple yet powerful 3D focusing-and-matching network for multi-instance point cloud registration by learning the multiple pair-wise point cloud registration. Specifically, we first present a 3D multi-object focusing module to locate the center of each object and generate object proposals. By using self-attention and cross-attention to associate the model point cloud with structurally similar objects, we can locate potential matching instances by regressing object centers. Then, we propose a 3D dual masking instance matching module to estimate the pose between the model point cloud and each object proposal. It performs instance mask and overlap mask masks to accurately predict the pair-wise correspondence. Extensive experiments on two public benchmarks, Scan2CAD and ROBI, show that our method achieves a new state-of-the-art performance on the multi-instance point cloud registration task. Code is available at https://github.com/zlynpu/3DFMNet.

Problem

• Multi-instance Point Cloud Registration
• Occlusion Handling
• Accuracy Improvement

Innovation

• 3D Focusing Module
• Self-Attention and Cross-Attention Mechanism
• 3D Dual Mask Matching Module