MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers

Title: MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers

标题：MemReg：基于混合内存缓冲区的流式室外激光雷达点云配准

Abstract: Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences. In this paper, we propose a novel multi-frame outdoor point cloud registration network for streaming LiDAR scans enhanced with pose-related memory buffers.

摘要：以往的室外激光雷达配准工作通常受限于成对输入范式，忽略了流式序列中固有的时间相关性。在本文中，我们提出了一种新颖的多帧室外点云配准网络，用于通过姿态相关内存缓冲区增强的流式激光雷达扫描。

The key observation is that long-term temporal LiDAR sequences can provide rich global contextual information to complete sparse measurements, filter outliers, and address low-overlap problems, thereby boosting registration performance. Specifically, two hybrid memory buffers are designed, including an implicit memory feature buffer and an explicit memory pose buffer, to store and dynamically update pose-related temporal features.

关键的观察结果是，长期的激光雷达时间序列可以提供丰富的全局上下文信息，以补全稀疏测量、过滤异常值并解决低重叠问题，从而提升配准性能。具体而言，我们设计了两个混合内存缓冲区，包括隐式内存特征缓冲区和显式内存姿态缓冲区，用于存储和动态更新与姿态相关的时间特征。

Moreover, a novel dynamic history weighting module is developed to adaptively fuse current and history pose-related features. Extensive experiments on three outdoor datasets, including KITTI, nuScenes, and Apollo-Southbay, demonstrate state-of-the-art performance of MemReg, surpassing all previous pair-wise methods and also multi-frame SLAM systems.

此外，我们开发了一种新颖的动态历史加权模块，以自适应地融合当前和历史的姿态相关特征。在包括 KITTI、nuScenes 和 Apollo-Southbay 在内的三个室外数据集上的大量实验表明，MemReg 达到了最先进的性能，超越了所有以往的成对方法以及多帧 SLAM 系统。

Our method also generalizes surprisingly well to multiview indoor registration scenarios with rather competitive performance on 3DMatch, 3DLoMatch, and ScanNet. Code will be released at this https URL.

我们的方法在多视图室内配准场景中也表现出惊人的泛化能力，在 3DMatch、3DLoMatch 和 ScanNet 上具有相当强的竞争力。代码将在该网址发布。