MemReg：基于混合内存缓冲区的流式户外激光雷达点云配准
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
AI总结：
该研究针对流式户外激光雷达配准忽略时间相关性的问题，提出带混合内存缓冲区的多帧配准网络MemReg，在户外数据集上性能优于现有方法，还可泛化到室内多视图配准场景。
摘要：
现有户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。本文提出一种新型多帧户外点云配准网络，用于增强了位姿相关内存缓冲区的流式激光雷达扫描。关键观察是，长期时间激光雷达序列可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，设计了两种混合内存缓冲区，包括隐式内存特征缓冲区和显式内存位姿缓冲区，用于存储和动态更新位姿相关的时间特征。此外，开发了一种新型动态历史加权模块，以自适应融合当前和历史位姿相关特征。在三个户外数据集（包括KITTI、nuScenes和Apollo-Southbay）上进行的大量实验表明，MemReg达到了最先进的性能，优于所有先前的成对方法以及多帧SLAM系统。我们的方法还意外地很好地泛化到多视图室内配准场景，在3DMatch、3DLoMatch和ScanNet上表现出相当有竞争力的性能。代码将在此httpsURL发布。
英文摘要：
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. 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. 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. 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 https://github.com/IRMVLab/MemReg.
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。
