vS-Graphs (visual_sgraphs)
- Software
- Navigation and mapping
- Framework
A visual SLAM framework extending ORB-SLAM 3.0 with optimizable 3D scene graphs that model walls, ground surfaces, rooms and corridors for more accurate mapping and localization.
Made by snt-arg.
Source on GitHub: github.com/snt-arg/visual_sgraphs (opens in a new tab). Facts read at commit ffdcf51 (opens in a new tab).
Licenses
- Code
- GPL-3.0-only (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (GPL-3.0-only) at commit ffdcf51 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
Copyleft: Modified source must be published.
What it does
- Extends ORB-SLAM 3.0 by integrating optimizable 3D scene graphs into mapping and localization.
- Recognizes building components such as wall and ground surfaces through a semantic segmentation module.
- Infers structural elements like rooms, corridors and floors, optionally using Voxblox integration.
- Can use ArUco markers as a database of room and corridor labels.
- Runs on ROS2 and supports RGB-D and RGB-D-Inertial setups, including recorded bag files and RealSense cameras.
- Benchmarking documentation is provided for comparing against other visual SLAM frameworks.
Written by Robotheca from the project's README (opens in a new tab) at commit ffdcf51.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 7 Jul 2026 on master
- Latest release
- vS-Graphs v1.5.5 (7 Jul 2026)
Checked on GitHub on 22 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.