论文HF Daily Papers · arXiv 2611.252794 天前
Accord开源单目IMU稠密度量建图,5cm阈值F-score全平台最优
本文由 AI 根据公开内容整理,可能有误,请以原文为准:Accord: Universal Online Metric Localization and Dense Mapping from one Camera and an IMU(HF Daily Papers · arXiv 2611.25279)
核心内容
针对单相机加IMU难以兼顾度量运动与稠密几何的痛点,研究团队提出Accord在线稠密度量建图框架。该系统通过VIO滤波器提供度量位姿,结合条件化深度基础模型预测短关键帧窗口深度,并利用因子图融合子地图。在5个公开相机-IMU配置及新建Phone-rig/GoPro数据集测试中,仅依赖自身轨迹对齐且未做任何针对性调参,Accord在所有平台上均取得5cm阈值下最佳或次佳平均F-score,验证了通用性。
技术核心在于利用多视图几何一致性(Multi-view Agreement)解决尺度问题:将关键帧窗口锚定至由滤波器位姿三角化的度量3D点,利用共视图像间双向稠密深度一致性估计并修正单帧尺度误差,同时保留锚点建立的度量基准;上下文关键帧进一步优化深度预测精度。为降低落地门槛,团队已开源完整算法代码及配套的Phone-rig数据集,支持任意相机+IMU组合进行在线稠密度量地图构建,填补了轻量级传感器高精度建图空白。
关键看点
- 架构融合:集成VIO度量位姿与深度基础模型,通过因子图融合子地图,解决纯视觉稀疏与纯深度无尺度问题
- 尺度修正:基于多视图双向稠密深度一致性与三角化锚点,在线估计并校正逐帧尺度误差,保持全局度量统一
- 泛化性能:跨5种公开硬件配置及自采数据集零调参测试,5cm阈值F-score稳居前二,验证单配置通用性
- 开源资产:发布完整算法源码及Phone-rig/GoPro数据集,支持低成本消费级传感器实现高精度在线度量建图
工程与产业观察
该工作证明了深度基础模型与经典几何约束结合可解决单目IMU尺度漂移,为具身智能提供了低成本、高精度的在线空间感知基座。其零调参泛化能力与开源数据集显著降低了移动机器人稠密SLAM的工程部署门槛,对端侧导航与三维重建具有重要参考价值。
英文摘要 (Abstract)
Dense metric mapping from a single camera and IMU remains challenging: visual-inertial odometry (VIO) provides metric motion but sparse geometry, whereas feed-forward depth models predict dense structure without ensuring metric scale. We present Accord, which constructs an accurate online dense metric map from any camera with an IMU. A VIO filter publishes metric poses, a depth foundation model conditioned on them predicts depth for short keyframe windows, and a factor graph fuses the resulting submaps. Recent work has explored several approaches to this problem. What is essential is the multi-view agreement (Accord), which is considered in SLAM as a source of geometric self-consistency. Accord anchors each keyframe window to metric 3D points triangulated from the filter poses, then exploits bidirectional dense depth agreement between co-visible images to estimate and correct per-image scale errors while preserving the metric scale established by the anchors. Context keyframes further improve depth prediction, and the resulting submaps are fused in a factor graph. We evaluate a single mapping configuration across five public camera-IMU setups and a new Phone-rig/GoPro dataset. With nothing tuned per dataset/setup and every map aligned only by Accord's own trajectory, Accord achieves consistently best/second-best mean F-score at 5 cm on every platform. Accord is open-source along with the phone-rig dataset for the benefit of the research community
Hugging Face Daily Papers 热度:6 upvotes 作者:Jaafar Mahmoud, Arthur Movsesyan, Cuong Huynh, Mikhail Iumanov, Sergey Zagoruyko, Sergey Kolyubin
外部来源
本页事实对应的公开页面,以原文为准。(点击将离开本站)