SOURCE-LINKED INTELLIGENCE

LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop Closure

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

SLAM systems based on 3D Gaussian Splatting (3DGS) have recently demonstrated promising reconstruction accuracy for dense 3D scene representations. However, current 3DGS systems struggle to meet the strict demands of real-world deployments due to severe limitations in operational performance and map adaptability. To this end, we propose LightSplat, a hybrid-representation RGB-D SLAM framework. It synergizes local sparse features for robust and fast tracking with a dual-thread backend that progressively constructs dense Gaussian submaps. Crucially, we enable online loop closure through feature-

Read original source ↗ Open in workspace

recordType

paper

region

Global