HybridReg：面向混合运动的鲁棒三维点云配准
HybridReg: Robust 3D Point Cloud Registration with Hybrid Motions
AI总结：
本文提出HybridReg，通过不确定性掩码学习处理背景刚性与前景非刚性/刚性混合运动，并构建HybridMatch场景级数据集，在室内外数据集上实现最先进的鲁棒点云配准性能。
摘要：
在考虑动态前景时，场景级点云配准极具挑战性。现有室内数据集大多假设刚性运动，因此训练出的模型无法鲁棒地处理具有非刚性运动的场景。另一方面，非刚性数据集主要处于物体级，因此训练出的模型难以很好地泛化到复杂场景。本文提出HybridReg，一种新的三维点云配准方法，通过学习不确定性掩码来处理混合运动：背景为刚性运动，实例级前景为非刚性或刚性运动。首先，我们构建了一个场景级三维配准数据集HybridMatch，该数据集专门设计了以可控方式布置多样变形前景的策略。其次，我们考虑不同运动类型，设计了一个掩码学习模块，以减轻变形离群点的干扰。第三，我们利用一种简单而有效的负对数似然损失，采用不确定性来引导特征提取和相关性计算。据我们所知，HybridReg是首个利用混合运动实现鲁棒点云配准的工作。大量实验表明HybridReg的优势，使其在广泛使用的室内和室外数据集上均取得了最先进的性能。
英文摘要：
Scene-level point cloud registration is very challenging when considering dynamic foregrounds. Existing indoor datasets mostly assume rigid motions, so the trained models cannot robustly handle scenes with non-rigid motions. On the other hand, non-rigid datasets are mainly object-level, so the trained models cannot generalize well to complex scenes. This paper presents HybridReg, a new approach to 3D point cloud registration, learning uncertainty mask to account for hybrid motions: rigid for backgrounds and non-rigid/rigid for instance-level foregrounds. First, we build a scene-level 3D registration dataset, namely HybridMatch, designed specifically with strategies to arrange diverse deforming foregrounds in a controllable manner. Second, we account for different motion types and formulate a mask-learning module to alleviate the interference of deforming outliers. Third, we exploit a simple yet effective negative log-likelihood loss to adopt uncertainty to guide the feature extraction and correlation computation. To our best knowledge, HybridReg is the first work that exploits hybrid motions for robust point cloud registration. Extensive experiments show HybridReg's strengths, leading it to achieve state-of-the-art performance on both widely-used indoor and outdoor datasets.
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。
