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

TL;DR

This paper introduces a novel 3D focusing-and-matching network that improves multi-instance point cloud registration by accurately locating object centers and estimating poses through pair-wise registration, outperforming existing methods.

Contribution

The paper proposes a 3D focusing module for locating object centers and a dual masking module for precise pair-wise registration, advancing multi-instance point cloud registration techniques.

Findings

Achieves state-of-the-art results on Scan2CAD and ROBI benchmarks.

Effectively locates object centers using self-attention and cross-attention.

Accurately estimates poses with dual masking instance matching.

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.