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.

TL;DR: 1) A training-free, model-agnostic SLAM system that scales to kilometer-scale trajectories in real time on one consumer GPU; 2) A hierarchical backend that enforces local, mid-level, and global consistency without bundle adjustment, so dynamic scenes work out of the box; 3) One framework that extends to stereo, RGB-D, and LiDAR.

AMB3R-SLAM consists of a front-end that performs low-latency camera pose tracking and a hierarchical backend that progressively ensures local, mid-level, and global consistency through pose graph optimization with span-2, long-context, and loop closure edges.