Go-SLAM: Grounded Object Segmentation and Localization with Gaussian Splatting SLAM

Phu Pham, Dipam Patel, Damon Conover, Aniket Bera

Abstract: We introduce Go-Slam, a novel framework that combines 3D Gaussian Splatting SLAM with grounded object segmentation and open-vocabulary querying to enable object-aware 3D scene reconstruction. Go-Slam incrementally builds high-fidelity 3D maps from RGB-D inputs while embedding semantic information by assigning unique object identifiers to Gaussian primitives. This integration allows the system to support flexible, natural language queries and accurately localize objects in complex, static environments. To achieve robust semantic mapping, Go-Slam leverages object detection and segmentation models, enabling consistent object identification across frames without relying on predefined categories. We evaluate Go-Slam across diverse indoor scenes, demonstrating improvements over existing baselines in both reconstruction quality and object localization accuracy. Our results show that Go-Slam effectively bridges the gap between geometric mapping and semantic understanding, supporting real-time scene interaction and object retrieval in open-world environments.

External IDs:dblp:conf/iros/PhamPCB25