PSReg: Prior-guided Sparse Mixture of Experts for Point Cloud Registration

TL;DR

This paper introduces PSReg, a novel point cloud registration method using prior-guided sparse mixture of experts to improve feature discrimination in overlapping regions, achieving state-of-the-art results.

Contribution

The paper proposes a prior-guided SMoE module combined with a Transformer framework to enhance correspondence accuracy in point cloud registration.

Findings

Achieves 95.7% registration recall on 3DMatch

Outperforms existing methods on 3DLoMatch benchmark

Demonstrates strong performance on ModelNet40

Abstract

The discriminative feature is crucial for point cloud registration. Recent methods improve the feature discriminative by distinguishing between non-overlapping and overlapping region points. However, they still face challenges in distinguishing the ambiguous structures in the overlapping regions. Therefore, the ambiguous features they extracted resulted in a significant number of outlier matches from overlapping regions. To solve this problem, we propose a prior-guided SMoE-based registration method to improve the feature distinctiveness by dispatching the potential correspondences to the same experts. Specifically, we propose a prior-guided SMoE module by fusing prior overlap and potential correspondence embeddings for routing, assigning tokens to the most suitable experts for processing. In addition, we propose a registration framework by a specific combination of Transformer layer and prior-guided SMoE module. The proposed method not only pays attention to the importance of locating the overlapping areas of point clouds, but also commits to finding more accurate correspondences in overlapping areas. Our extensive experiments demonstrate the effectiveness of our method, achieving state-of-the-art registration recall (95.7\%/79.3\%) on the 3DMatch/3DLoMatch benchmark. Moreover, we also test the performance on ModelNet40 and demonstrate excellent performance.