Generalized-CVO: Fast and Correspondence-Free Local Point Cloud Registration with Second Order Riemannian Optimization
Quick Answer
This paper shows that The Generalized-CVO method accelerates local point cloud registration by up to 10x using second-order Riemannian optimization, significantly reducing drift in LiDAR tracking by over 55% in challenging environments.
Quick Take
The Generalized-CVO method accelerates local point cloud registration by up to 10x using second-order Riemannian optimization, significantly reducing drift in LiDAR tracking by over 55% in challenging environments. It outperforms traditional ICP methods, enhancing robustness and accuracy in diverse datasets.
Key Points
- Achieves up to 10x speedup over first-order solvers in point cloud registration.
- Reduces translational and rotational drift by over 55% in LiDAR tracking tasks.
- Demonstrates improved accuracy in frame-to-frame tracking across various datasets.
- Outperforms ICP-based methods in object registration benchmarks.
- Enhances robustness, especially during global initialization refinement.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 10019v1 Announce Type: new Abstract: We propose a fast and correspondence-free local point cloud registration method that leverages geometric surface structure and reproducing kernel Hilbert space (RKHS) embeddings. The method represents point clouds as continuous functions with point-wise anisotropic kernels that encode local geometry. This formulation improves alignment along surface normals while relaxing alignment along tangential directions.
To solve the resulting registration problem, we propose a second-order on-manifold optimization scheme with approximate Riemannian Hessians, achieving a speedup of up to 10x over the first-order solvers used in prior correspondence-free RKHS-based methods. We demonstrate improved frame-to-frame LiDAR and RGB-D tracking accuracy across diverse indoor and outdoor datasets.
On a LiDAR tracking registration task in the driving domain, we achieve a reduction of $>55\%$ in both translational and rotational drift in challenging feature-sparse environments. On object registration benchmarks, we show improved robustness over ICP-based methods and further gains when refining global initialization, particularly under moderate misalignment.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.