Incremental Multiview Point Cloud Registration with Two-stage Candidate Retrieval

TL;DR

This paper introduces an incremental multiview point cloud registration method that uses a two-stage candidate retrieval process and transformation averaging to improve registration accuracy and efficiency, especially in low-overlap scenarios.

Contribution

It presents a novel incremental registration framework with a two-stage candidate retrieval strategy and error mitigation techniques, advancing multiview point cloud registration methods.

Findings

Outperforms existing methods on multiple benchmarks.

Effectively handles low-overlap and density variance issues.

Demonstrates improved registration accuracy and computational efficiency.

Abstract

Multiview point cloud registration serves as a cornerstone of various computer vision tasks. Previous approaches typically adhere to a global paradigm, where a pose graph is initially constructed followed by motion synchronization to determine the absolute pose. However, this separated approach may not fully leverage the characteristics of multiview registration and might struggle with low-overlap scenarios. In this paper, we propose an incremental multiview point cloud registration method that progressively registers all scans to a growing meta-shape. To determine the incremental ordering, we employ a two-stage coarse-to-fine strategy for point cloud candidate retrieval. The first stage involves the coarse selection of scans based on neighbor fusion-enhanced global aggregation features, while the second stage further reranks candidates through geometric-based matching. Additionally, we apply a transformation averaging technique to mitigate accumulated errors during the registration process. Finally, we utilize a Reservoir sampling-based technique to address density variance issues while reducing computational load. Comprehensive experimental results across various benchmarks validate the effectiveness and generalization of our approach.