October 13, 2025Open Access

OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding

View Full Paper

Ask AI

Bookmark

OpenGS-SLAM improves 3D object-level scene understanding in open-set environments with effective semantic representation.
The method achieves 10 times faster semantic rendering and 2 times lower storage costs compared to traditional approaches.
Gaussian Voting Splatting enables rapid 2D label map rendering, ensuring efficient scene updates and processing.
Extensive experiments demonstrate significant advancements in tracking and mapping with improved labeling across views.

Discussion

No takes yet. Share an insight, caveat, or question.

This framework integrates 3D gaussian splatting for dense semantic slam, enhancing scene understanding and labeling consistency.

Yang et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark