arXiv 2409.050652024-09-08cs.CV

用于鲁棒点云配准的 Sight View Constraint

Sight View Constraint for Robust Point Cloud Registration

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Guangdong Provincial Key Laboratory of Construction Robotics and Intelligent Construction（广东省建造机器人与智能建造重点实验室）

Yaojie Zhang, Weijun Wang, Tianlun Huang, Zhiyong Wang, Wei Feng

备注：: 9 pages

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对部分点云配准目标定义不清、低重叠下错误变换难以判别的问题，提出通用 SVC 约束以排除错误变换，并在 3DLoMatch 上将召回率提升至 82%。

摘要：

部分到部分点云配准（partial PCR）仍然是一项具有挑战性的任务，尤其是在处理低重叠率时。与全到全配准任务相比，我们发现 partial PCR 的目标仍未得到良好定义，这表明没有度量能够可靠地识别真实变换。我们将此确定为 partial PCR 任务中最根本的挑战。本文没有直接寻找最优变换，而是提出了一种新颖且通用的 Sight View Constraint（SVC），用以确定性地识别错误变换，从而增强现有 PCR 方法的鲁棒性。大量实验验证了 SVC 在室内和室外场景上的有效性。在具有挑战性的 3DLoMatch 数据集上，我们的方法将配准召回率从 78% 提升到 82%，取得了最先进的结果。本研究还强调了 partial PCR 决策版本问题的重要性，该问题有可能为 partial PCR 问题提供新的见解。

英文摘要：

Partial to Partial Point Cloud Registration (partial PCR) remains a challenging task, particularly when dealing with a low overlap rate. In comparison to the full-to-full registration task, we find that the objective of partial PCR is still not well-defined, indicating no metric can reliably identify the true transformation. We identify this as the most fundamental challenge in partial PCR tasks. In this paper, instead of directly seeking the optimal transformation, we propose a novel and general Sight View Constraint (SVC) to conclusively identify incorrect transformations, thereby enhancing the robustness of existing PCR methods. Extensive experiments validate the effectiveness of SVC on both indoor and outdoor scenes. On the challenging 3DLoMatch dataset, our approach increases the registration recall from 78\% to 82\%, achieving the state-of-the-art result. This research also highlights the significance of the decision version problem of partial PCR, which has the potential to provide novel insights into the partial PCR problem.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。