# Diorama

- **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:** [Ryder Wu](https://cerebralvalley.ai/u/Ryder)
- **GitHub:** https://github.com/ryder1018/Diorama
- **Demo video:** https://youtu.be/-eHnDrMEmpo?si=8IUbBmvMyHL06N1I
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1690

A photo is flat: a game character can't stand on its floor or walk behind its furniture. Diorama turns a single photo into a 2.5D space you can interact with. It splits the photo into depth-ordered layers, measures how far away each object is, finds the ground a character can stand on, and works out which real objects hide it.

## More from Meta Global AI Developer Hackathon

- [JenX](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1687)
- [Aaditya GC](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1688)
- [Tempo](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1689)
- [Shift Sight Ops](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1691)
- [GuardianCall](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1692)
- [Pam](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1693)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1690. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt