MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
This provides a plug-and-play solution for real-time 3D mapping and localization in robotics or AR/VR, though it appears incremental as it builds on existing priors with efficiency improvements.
The researchers tackled the problem of real-time dense SLAM (simultaneous localization and mapping) from monocular video by developing a system that uses 3D reconstruction priors for robustness in uncontrolled environments, achieving operation at 15 FPS with globally-consistent poses and dense geometry.
We present a real-time monocular dense SLAM system designed bottom-up from MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system is robust on in-the-wild video sequences despite making no assumption on a fixed or parametric camera model beyond a unique camera centre. We introduce efficient methods for pointmap matching, camera tracking and local fusion, graph construction and loop closure, and second-order global optimisation. With known calibration, a simple modification to the system achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.