UMERegRobust - 用于鲁棒点云配准的通用流形嵌入兼容特征
UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration
AI总结：
本文扩展了通用流形嵌入（UME）框架，提出 UMERegRobust 点云配准流程及 RotKITTI 基准，在部分重叠和不同采样场景下实现鲁棒配准，并在 KITTI 和 RotKITTI 上显著超越 SOTA。
摘要：
在本文中，我们采用通用流形嵌入（UME）框架进行刚性变换估计，并对其进行扩展，使其能够适应涉及部分重叠和不同采样点云的场景。UME 是一种旨在将同一物体（通过刚性变换相关联）的观测映射到单一低维线性子空间的方法。此过程产生观测的变换不变表示，其矩阵形式表示与变换是协变的（即等变的）。我们通过引入一种 UME 兼容的特征提取方法（辅以独特的 UME 对比损失和采样均衡器）来扩展 UME 框架。这些组件被集成到一个全面且鲁棒的配准流程中，命名为 UMERegRobust。我们提出了 RotKITTI 配准基准，专门用于评估涉及大旋转场景的配准方法。UMERegRobust 在 KITTI 基准上取得了优于 SOTA 的性能，特别是在考虑 (1°, 10cm) 的严格精度时（平均增益为 +9%），并在 RotKITTI 基准上显著优于 SOTA 方法（与最新 SOTA 方法相比增益为 +45%）。
英文摘要：
In this paper, we adopt the Universal Manifold Embedding (UME) framework for the estimation of rigid transformations and extend it, so that it can accommodate scenarios involving partial overlap and differently sampled point clouds. UME is a methodology designed for mapping observations of the same object, related by rigid transformations, into a single low-dimensional linear subspace. This process yields a transformation-invariant representation of the observations, with its matrix form representation being covariant (i.e. equivariant) with the transformation. We extend the UME framework by introducing a UME-compatible feature extraction method augmented with a unique UME contrastive loss and a sampling equalizer. These components are integrated into a comprehensive and robust registration pipeline, named UMERegRobust. We propose the RotKITTI registration benchmark, specifically tailored to evaluate registration methods for scenarios involving large rotations. UMERegRobust achieves better than state-of-the-art performance on the KITTI benchmark, especially when strict precision of (1°, 10cm) is considered (with an average gain of +9%), and notably outperform SOTA methods on the RotKITTI benchmark (with +45% gain compared the most recent SOTA method).
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。
