LightSplat: real-time high-fidelity 3D Gaussian SLAM with loop closure at 8 FPS

zhenjun_zhao · x · 2026-09-11

LightSplat, accepted to IROS 2026, is a hybrid-representation RGB-D SLAM framework: local sparse features drive robust fast tracking while a dual-thread backend progressively builds dense Gaussian submaps; online loop closure via feature-accelerated 3DGS registration plus pose graph optimization refines map consistency. It reaches near-SOTA reconstruction quality on multiple datasets and a real robotic platform, handles practical camera motions, and maintains an average 8 FPS for real-world deployment.

Original post →

More from Embodied

Embodied channel →