Your House in 3D
Turn a handful of phone photos into a watertight, 3D-printable model of your home.
The problem
People love a physical keepsake of their home, but getting one normally means a CAD modeler, a 3D scan, or expensive bespoke work. There was no self-serve way to go from "a few photos on my phone" to a printable model of a specific house.
The approach
The pipeline never touches map footprint data — geometry is derived entirely from the uploaded photos. Claude Vision runs a multi-pass elevation analysis to infer massing, roof lines, and proportions, which a Python FastAPI service turns into a solid via CSG operations (manifold3d / trimesh) and exports as a watertight STL. Each mesh is validated for printability before it's accepted. A Next.js storefront handles Stripe checkout, with Google Maps used only for address autocomplete on the order form.
Highlights
- Multi-pass Claude Vision elevation analysis derives geometry from photos alone
- CSG meshing (manifold3d / trimesh) produces watertight, printable STL files
- Print-readiness validation before a model ships to the slicer
- Stripe checkout storefront with Google Maps address autocomplete
Tech stack
Want to talk through how this was built?
I build and ship production apps end-to-end. Happy to dig into the architecture, the tradeoffs, or your next project.