Inspiration
In places like Dhumalwadi, brilliant students are forced to rote-learn complex science concepts because their schools lack access to expensive practical laboratories. Watching students memorize textbook diagrams without ever seeing how things actually work inspired the core idea: What if every student had a world-class science lab right on their desk, powered by just a smartphone?
What it does
Aura AR is a conceptual mobile application designed to democratize practical education. By scanning any standard 2D textbook diagram (like a human heart, a solar system, or an engine), the app instantly generates an interactive, photorealistic 3D holographic model. Students can rotate, zoom, and dissect these models in real-time AR space, turning passive reading into active, practical learning.
How we built it
The core intelligence of Aura AR is conceptualized around Google Gemini's multimodal capabilities.
- Vision: Gemini analyzes the camera feed to recognize and interpret the 2D educational diagrams.
- Generation: Based on the visual context and prompt engineering, the app requests high-resolution 3D spatial data.
- Frontend: The pitch and UI simulation were built using React, TypeScript, and Vite, leveraging Framer Motion for smooth, continuous video transitions that mimic the AR experience.
Challenges we ran into
The biggest challenge was figuring out how to present a complex AR concept effectively within a strict 1-minute pitch constraint. We had to ensure the problem (lack of labs) and the solution (Gemini-powered AR) were visually connected without relying on a physical working prototype. We solved this by building a custom, auto-advancing React presentation that seamlessly crossfaded concept videos.
Accomplishments that we're proud of
I am extremely proud of taking a "crazy idea" that solves a real local problem and turning it into a highly professional, compelling pitch. The transition from a simple thought to a fully automated React-based presentation with synchronized timings and BGM was a huge personal win.
What's next for Aura AR
The next step is to move from concept to functional prototype. I plan to dive deeper into the Gemini API to build a working proof-of-concept that can accurately recognize 3-5 specific textbook diagrams and render basic 3D WebGL models on screen.
Built With
- css3
- framer-motion
- gemini
- html5
- react
- typescript
- vite
Log in or sign up for Devpost to join the conversation.