Experiment 2

Voice-Activated 3D Object Spawning

An end-to-end computer vision and spatial computing pipeline that captures real-world objects using Meta Ray-Ban smart glasses, segments them via voice commands, generates 3D models using AI, and spawns them dynamically at runtime in Unreal Engine.

Wearable Integration

Meta Ray-Ban SDK & Android Studio (Kotlin)

Computer Vision

YOLOv8 & SAM (Segment Anything Model) in Python

Agentic Workflows

n8n & Meshy API

Spatial Computing

Unreal Engine 5

Read Full Breakdown View GitHub Repo Watch Instagram Reel