arXiv 2605.304882026-09-10cs.RO

CoMo3R-SLAM: 面向室外多智能体系统的协作式单目稠密SLAM与学习型3D重建先验

CoMo3R-SLAM: Collaborative Monocular Dense SLAM with Learned 3D Reconstruction Priors for Outdoor Multi-Agent Systems

ETH Zurich（苏黎世联邦理工学院）；University of Liverpool（利物浦大学）；Harbin Engineering University（哈尔滨工程大学）；University of Ottawa（Ottawa大学）；Shanghai Jiao Tong University（上海交通大学）；Imperial College London（伦敦帝国理工学院）

Zhihao Cao, Qi Shao, Shuhao Zhai, Feng Tian, Anh Nguyen, Hesheng Wang, Baoru Huang

备注：: Code and project website: https://como3r-slam.github.io

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出首个协作式单目稠密RGB SLAM系统CoMo3R-SLAM，利用学习的前馈3D重建先验实现室外多智能体地图构建，无需深度传感器即可生成全局一致的度量地图。

摘要：

协作式稠密SLAM对于多机器人团队在大规模室外环境中实现可扩展且一致的3D感知至关重要。现有系统通常依赖深度传感器，导致显著的载荷、功耗和标定成本。单目RGB相机是一种轻量级替代方案，但协作式单目稠密SLAM仍面临尺度模糊、智能体间数据关联不可靠等困难，尤其是在室外场景中，低重叠和重复结构使得传统特征匹配不可靠，从而需要鲁棒的几何信息。我们提出CoMo3R-SLAM，这是首个利用鲁棒的学习前馈3D重建先验进行室外多智能体地图构建的协作式单目稠密RGB SLAM系统。每个智能体运行一个先验引导的前端，用于实时跟踪和局部稠密融合，而协调器执行稠密点图匹配以进行跨智能体验证、闭式Sim(3)规范同步以及GPU加速的全局光束法平差与分段深度优化。我们的系统既不需要深度传感器也不需要参数化内参，仅凭单目RGB即可产生鲁棒的跨智能体约束和全局一致的度量地图。在Tanks and Temples和Waymo序列上，CoMo3R-SLAM在四个Tanks and Temples场景中的三个上实现了最佳ATE，并在Waymo上达到竞争性精度，匹配或超越最先进的RGB-D方法，同时以8 FPS在线运行。

英文摘要：

Outdoor robot teams need a shared dense map despite limited overlap, independent reference frames, and uncertain monocular scale. Collaborative dense SLAM systems typically resolve this with depth sensors, which add payload, power, and calibration cost. We present CoMo3R-SLAM, a collaborative monocular dense SLAM system that places learned feed-forward 3D reconstruction priors at the center of the multi-agent problem: their dense pointmaps anchor scale across agents and supply correspondences strong enough to verify inter-agent links geometrically. Each agent tracks and fuses its own keyframes from a single RGB stream, while a coordinator retrieves cross-agent keyframes over the prior's encoder features, verifies them by bidirectional dense pointmap matching, synchronizes the independent similarity gauges in closed form, and refines every keyframe in one unified multi-agent sim(3) graph. Finally, a pose-depth alternation over geometry-aware segments lets inter-agent observations constrain dense structure as well as trajectories. Requiring neither measured depth nor supplied intrinsics, CoMo3R-SLAM attains the lowest trajectory error on three of four Tanks and Temples scenes, and competitive accuracy on Waymo driving sequences, while running at approximately 6-8 FPS on RTX 3080 Ti. A long-horizon traversal, independently captured day and night streams, and teams of up to four agents further map its operating range.

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。