Gemini-powered Spatial OS turns 8 photos into 3D digital twins
AI_Andrew · x · 2026-09-02
A project called GeminiSpace demonstrates a spatial intelligence OS built on Google Gemini for indoor navigation. It transforms 8 panoramic photos into photorealistic 2D blueprints, 3D voxel digital twins, SLAM relational graphs, and ROS2 trajectories.
Key Tech Breakthroughs:
- Model: Uses Gemini 3.7 Flash for sub-second spatial reasoning and chat.
- Visual SLAM: Employs Seam Keypoints & 360° Loop Closure for drift-free geometry and hallucination elimination.
- Rendering: Supports photorealistic material rendering (marble, brass, oak).
- Cockpit: Features a 360° Radar Compass and metric grid overlays.
The project is open-source on GitHub with full architecture docs.
More from Embodied
- China’s real robot revolution is not about humanoids, but industrial application — zijing_wu · 2026-09-02
- Robot Training Video: Squire Model Shows New Skills — MocaPoka · 2026-09-02
- Open-source humanoid robot Asimov 1 starts shipping to 20+ countries — MikeBirdTech · 2026-09-02
- Physical AI Deep Dive: From Static Programming to Imitation Learning and Edge Compute — ShawnHymel · 2026-09-02
- Arduino's Zephyr-based core officially leaves beta as mbedOS cores enter deprecation — JeremyCMorgan · 2026-09-02
- Robot dog learns to hook and drag IKEA chairs, succeeding in 40/58 trials — ChongZzZhang · 2026-09-02