Incremental Multiview Point Cloud Registration with Two-stage Candidate Retrieval
This addresses the problem of robust multiview point cloud registration for computer vision applications, but it is incremental as it builds on existing paradigms with specific enhancements.
The paper tackles multiview point cloud registration by proposing an incremental method that progressively registers scans to a growing meta-shape, using a two-stage candidate retrieval strategy for ordering and transformation averaging to reduce errors. Experimental results show it outperforms previous methods, achieving 92.3% registration accuracy on the KITTI dataset.
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.