Saved in:
Bibliographic Details
Main Authors: Li, Jiayi, Yao, Yuxin, Lu, Qiuhang, Zhang, Juyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.17034
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Noisy, partially overlapping data and the need for real-time processing pose major challenges for rigid registration. Considering that feature-based matching can handle large transformation differences but suffers from limited accuracy, while local geometry-based matching can achieve fine-grained local alignment but relies heavily on a good initial transformation, we propose a novel dual-space paradigm to fully leverage the strengths of both approaches. First, we introduce an efficient filtering mechanism consisting of a computationally lightweight one-point RANSAC algorithm and a subsequent refinement module to eliminate unreliable feature-based correspondences. Subsequently, we treat the filtered correspondences as anchor points, extract geometric proxies, and formulate an effective objective function with a tailored solver to estimate the transformation. Experiments verify our method's effectiveness, as demonstrated by a 32x CPU-time speedup over MAC on KITTI with comparable accuracy. Project page: https://ustc3dv.github.io/DualReg/.