A shopping app for when you cannot tell if furniture will fit your room. AI reads dimensions and existing pieces from photos and builds a 3D digital twin. Products drop into that twin for checking, and because the AI knows what is on screen and where things sit, you can ask for advice, or a search, without explaining.
Judges called the link between e-commerce and a digital twin forward-looking, praising an experience aimed at furnishing a room, not merely searching, AI that blends naturally, implementation strength with Three.js, and potential reaching logistics.
The award name names the criterion: technical depth. Estimating dimensions from photographs, rebuilding the room in 3D, rendering it and layering products into it are jobs of very different kinds, bundled into one application. The quieter move is that the AI holds the current view and coordinates, removing the need to describe your situation before asking anything. That attacks a familiar weakness of conversational interfaces, and likely sits near the heart of the result.
See all winners of 第2回 AI Agent Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).