Prototype a Gaussian-Splatting Capture App for Consumer AR
Overview
What this challenge is about.
You will design and prototype (no app-store deploy required) a 5-step capture-to-share flow: (1) capture about 60 photos with on-screen guidance, (2) upload to a backend job queue, (3) train a Gaussian-Splatting model on a GPU VM (about 10 minutes), (4) deliver a shareable interactive viewer link, (5) let the user trim and re-share. The viewer can be a web page (gsplat.js or similar). Build the Figma flow + a working backend that proves the timing claim, and write a 3-page design rationale covering UX trade-offs, time-to-result, and a quality bar the founders can hold the team to.
The Brief
What you'll do, and what you'll demonstrate.
Design and prove out the end-to-end consumer flow for a Gaussian-Splatting capture-and-share app, with both a clickable UX and a working backend timing proof.
Earning criteria — what you'll demonstrate
- Apply Gaussian Splatting as a practical 3D scene representation
- Design a consumer flow under hard 3D-pipeline constraints (capture quality, training time)
- Connect a research-grade rendering pipeline to a product surface
- Communicate a quality bar that is measurable, not vibes-based
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.