StreamVLO：带累积漂移补偿的流式视觉-激光雷达里程计
StreamVLO: Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
用 Mamba 做跨多帧的视觉-激光雷达统一时空关联，并以因果方式从历史帧学习残差修正来抑制累积漂移，可直接迁移到视觉里程计/SLAM 的长序列位姿估计与多传感器融合骨干设计。
原文依据 a unified spatio-temporal correlation module built on Mamba to fuse heterogeneous visual and LiDAR cues across multi-frame clips
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 StreamVLO，一个流式视觉-激光雷达里程计框架，利用 Mamba 模型进行统一的时空关联，并通过在线累积漂移补偿方案解决长期存在的累积漂移问题，从而在 4D 动态环境中实现定位。具体而言，StreamVLO 引入一个基于 Mamba 构建的统一时空关联模块，跨多帧片段融合异构的视觉与激光雷达线索，克服了以往成对方法在时序探索上的局限。此外，累积漂移补偿模块以因果方式从多个历史帧中迭代学习残差修正，从而最小化累积漂移。为增强显著区域上的空间特征表示，本文采用基于赢者通吃策略的关键点感知辅助损失。StreamVLO 在两个常用的自动驾驶数据集上取得最优性能，在 KITTI 上将 t_rel 与 r_rel 误差分别降低 19% 和 22%，在 Argoverse 上将 ATE 与 RPE 分别降低 18% 和 16%，同时仍适合实时部署。
英文原文摘要 1079 字符
We propose StreamVLO, a streaming visual-LiDAR odometry framework that performs unified spatio-temporal correlation with Mamba models and tackles the long-standing cumulative drift problem via an online Cumulative Drift Compensation scheme for localization in 4D dynamic environments. Specifically, StreamVLO introduces a unified spatio-temporal correlation module built on Mamba to fuse heterogeneous visual and LiDAR cues across multi-frame clips, overcoming the limited temporal exploration of prior pairwise methods. Furthermore, a Cumulative Drift Compensation module minimizes cumulative drift by iteratively learning residual corrections from multiple historical frames in a causal manner. To strengthen spatial feature representation on salient regions, we adopt a Keypoint-Aware Auxiliary Loss with a winner-takes-all strategy. StreamVLO achieves state-of-the-art performance on two commonly used autonomous driving datasets, reducing errors by 19% t_rel and 22% r_rel on KITTI, and by 18% ATE and 16% RPE on Argoverse, while remaining suitable for real-time deployment.