AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend

2026-09-16

AI Summary

本文提出AMB3R-SLAM系统，通过结合轻量前端与分层后端，在不依赖静态世界假设的情况下，实现公里级轨迹重建，并支持多种传感器输入，显著降低了相机跟踪误差。

Abstract

We present AMB3R-SLAM, a real-time monocular SLAM system capable of reconstructing kilometer-scale trajectories over 10k frames on a single consumer-grade GPU. Our model couples a lightweight front-end for low-latency online tracking with a hierarchical backend that progressively enforces local, mid-level, and global consistency. By avoiding bundle adjustment that relies on the static world assumption, our system naturally handles complex dynamic scenes out of the box. Furthermore, we demonstrate that our method can be extended to leverage stereo, RGB-D, and LiDAR as additional inputs. AMB3R-SLAM achieves strong camera tracking performance across 9 datasets, reducing the absolute trajectory error (ATE) of previous state-of-the-art methods on VBR and Oxford Spires by over 70%. With additional LiDAR input, our model further reduces ATE to sub-meter level on KITTI and VBR datasets.

Problem

• SLAM
• kilometer-scale
• real-time
• monocular
• dynamic scenes

Innovation

• Hierarchical Backend
• Kilometer-scale SLAM
• Dynamic Scenes Handling
• Multi-sensor Fusion