MR.ScaleMaster: Scale-Consistent Collaborative Mapping from Crowd-Sourced Monocular Videos

TL;DR

MR.ScaleMaster is a collaborative monocular mapping system that effectively addresses scale ambiguity and loop closure errors, enabling scalable, multi-session 3D reconstruction from crowd-sourced videos.

Contribution

It introduces a scale-aware Sim(3) formulation, a spurious loop rejection mechanism, and a modular interface for integrating monocular reconstruction models.

Findings

Achieves 7.2x reduction in ATE on KITTI sequences with multiple agents.

Successfully rejects false-positive loops while preserving valid constraints.

Enables multi-robot dense mapping with heterogeneous SLAM systems.

Abstract

Crowd-sourced cooperative mapping from monocular cameras promises scalable 3D reconstruction without specialized sensors, yet remains hindered by two scale-specific failure modes: abrupt scale collapse from false-positive loop closures in repetitive environments, and gradual scale drift over long trajectories and per-robot scale ambiguity that prevent direct multi-session fusion. We present MR$.$ScaleMaster, a cooperative mapping system for crowd-sourced monocular videos that addresses both failure modes. MR$.$ScaleMaster introduces three key mechanisms. First, a Scale Collapse Alarm rejects spurious loop closures before they corrupt the pose graph. Second, a Sim(3) anchor node formulation generalizes the classical SE(3) framework to explicitly estimate per-session scale, resolving per-robot scale ambiguity and enforcing global scale consistency. Third, a modular, open-source, plug-and-play interface enables any monocular reconstruction model to integrate without backend modification. On KITTI sequences with up to 15 agents, the Sim(3) formulation achieves a 7.2x ATE reduction over the SE(3) baseline, and the alarm rejects all false-positive loops while preserving every valid constraint. We further demonstrate heterogeneous multi-robot dense mapping fusing MASt3R-SLAM, pi3, and VGGT-SLAM 2.0 within a single unified map.