DOGL-SLAM

Robot
18

Dynamic Object-Level SLAM via Joint Gaussian-Landmark Tracking. Integrates 3D Gaussian Splatting (3DGS) into SLAM pipeline, enabling accurate camera pose tracking, object-level interaction, and high-fidelity scene reconstruction in dynamic environments.

Implemented Skills

No skills extracted yet

README

DOGL-SLAM: Dynamic Object-level SLAM via Joint Gaussian-Landmark Tracking. Recent advancements in 3D Gaussian Splatting (3DGS) have significantly improved the mapping quality and computational efficiency of visual Simultaneous Localization and Mapping (SLAM). DOGL-SLAM integrates 3DGS into its core pipeline, enabling accurate camera pose tracking, object-level interaction, and high-fidelity scene reconstruction in dynamic environments. Features joint graph optimization, consistent object-level semantic fusion, and hierarchical dynamic filtering pipeline.

Timeline

discover2/23/2026

Discovered DOGL-SLAM during February 2026 content audit

View source
Project Info
C++
Updated 2/3/2026