AI RESEARCH
SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors
arXiv CS.CV
•
ArXi:2511.17207v2 Announce Type: replace Recent advances in dense 3D reconstruction have nstrated strong capability in accurately capturing local geometry. However, extending these methods to incremental global reconstruction, as required in SLAM systems, remains challenging. Without explicit modeling of global geometric consistency, existing approaches often suffer from accumulated drift, scale inconsistency, and suboptimal local geometry. To address these issues, we propose SING3R-SLAM, a globally consistent Gaussian-based monocular indoor SLAM framework.