VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
This work addresses incremental improvements in SLAM for robotics and AR/VR by handling uncalibrated camera scenarios more robustly.
The paper tackles the problem of dense RGB SLAM with uncalibrated monocular cameras by optimizing submap alignment on the SL(4) manifold to handle projective ambiguities, resulting in improved map quality for long video sequences compared to prior methods.
We present VGGT-SLAM, a dense RGB SLAM system constructed by incrementally and globally aligning submaps created from the feed-forward scene reconstruction approach VGGT using only uncalibrated monocular cameras. While related works align submaps using similarity transforms (i.e., translation, rotation, and scale), we show that such approaches are inadequate in the case of uncalibrated cameras. In particular, we revisit the idea of reconstruction ambiguity, where given a set of uncalibrated cameras with no assumption on the camera motion or scene structure, the scene can only be reconstructed up to a 15-degrees-of-freedom projective transformation of the true geometry. This inspires us to recover a consistent scene reconstruction across submaps by optimizing over the SL(4) manifold, thus estimating 15-degrees-of-freedom homography transforms between sequential submaps while accounting for potential loop closure constraints. As verified by extensive experiments, we demonstrate that VGGT-SLAM achieves improved map quality using long video sequences that are infeasible for VGGT due to its high GPU requirements.