# oglybogly

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Sai Krishna](https://cerebralvalley.ai/u/skrisps)
- **GitHub:** https://github.com/Skrisps26/splatsam
- **Demo video:** https://youtu.be/ALfZ7QYvPgU
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5150

Robotics developers waste days manually modeling physical tabletop environments in simulation and evaluating grasp heuristics on arbitrary, uncalibrated scenarios.

SplatSAM automates this entire loop from a casual desk video:
1. Zero-shot Video Perception: Tracks persistent objects across frames using SAM 3.1 video segmentation, extracting metric homographies from known reference objects (A4 paper or laptop chassis).
2. Automated Physics Sandbox: Reconstructs metric 3D primitives (boxes, cylinders, spheres) and instantiates a fully interactive MuJoCo simulation environment with realistic collision bounds, estimated mass, and contact friction.
3. Autonomous Heuristic Tuning: Couples Muse Wonder 1.0 (for bounded parameter proposals) and Muse Spark 1.3 (for multi-frame failure diagnosis) in an iterative optimization loop to tune a parallel-jaw grasp planner across randomized physics curriculums.
4. Rigorous Validation & Sealed Evaluation: Implements paired bootstrap significance testing (n=10,000) to accept proposals only when mean gains exceed thresholds and regressions are protected, preventing simulator overfitting.

SplatSAM provides a dark, interactive desktop/mobile Streamlit cockpit that replays perception reveals, metric footprint warps, 3D scene orbits, live token traces, and physical grasp trials—delivering transparent sim-to-real evaluation with zero manual simulation authoring.

## More from Meta Global AI Developer Hackathon

- [MediClear](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5147)
- [Ashish Karigar - MemoryOS](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5148)
- [Team Mila](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5149)
- [NovelTroupe](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5151)
- [ArgusAI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5152)
- [LAK](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5153)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/5150. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt