Italian Duo Launches AI App to Furnish Rooms in Seconds

An AI-powered app called elephantroom aims to simplify the process of furnishing a home by generating complete room layouts in seconds. The app, co-founded by architect Lora Fahmy and AI engineer Alessandro Duico, addresses the common challenges shoppers face, such as uncertainty about how pieces will fit together or if they will match the available space.

Traditional online furniture shopping often involves browsing numerous retailer websites, requiring manual measurement and leaving shoppers unsure of the final aesthetic or practical fit of their selections. Existing AI design applications have also faced limitations, sometimes generating photorealistic rooms with non-purchasable furniture or inaccurately representing product dimensions.

"The problem is that it’s never going to be physically accurate, at least for the foreseeable future, because it doesn’t know the space the picture represents or the measurements of the furniture," said Duico, the app's chief technology officer. He explained that many apps superimpose furniture onto photos, which can create visually convincing but impractical results for shoppers trying to order items.

Fahmy, an architect, encountered these issues firsthand when furnishing her own home. She found the process fragmented and time-consuming, even with professional design software. This personal experience, combined with Duico's background in AI and product development honed in the San Francisco startup scene, led to the creation of elephantroom.

The app, now available on the App Store, allows users to set up a room, define their style, layout, and budget, and receive AI-generated options. Unlike other tools, elephantroom builds room designs within a 3D engine using actual product dimensions. This approach ensures that the on-screen representation closely matches real-world sizes, allowing users to see how pieces will physically fit and are available for purchase.

Elephantroom can generate hundreds of room arrangements within approximately two seconds. The furniture featured in these designs is sourced from actual retail catalogs and local makers, rather than generic placeholders. Users can edit the generated plans, rearranging items, changing styles, or adjusting budgets. The app also provides direct links to purchase items and includes a photo mode for realistic rendering overlays on the 3D layouts.

Duico stated, "You’ll get real 3D designs matched to real products you can instantly buy. No dummy furniture, no complicated tools, no hidden paywalls."

Technology Behind the Layouts

The accuracy of elephantroom is attributed to its method of digitizing retail catalogs. Product information, including dimensions, prices, and materials, is converted into 3D models. Automated scripts then resize these models to match the exact measurements provided by retailers. This process involves an image-to-3D model conversion for the form and a language model that extracts textual data for precise width and depth.

"Our LLM goes through every catalog, works out a product’s depth and width, and converts it to different units," Duico explained. "That’s how we have a catalog of 3D models with true-to-scale measurements."

These scaled 3D models are then fed into a layout algorithm that respects the real-world dimensions of each product. This ensures that items are arranged realistically within the room, considering necessary walking space and preventing furniture from appearing to occupy impossible dimensions, thereby reducing the likelihood of unexpected sizing issues upon delivery.

The collaboration between Fahmy's architectural expertise and Duico's AI technology seeks to transform furniture shopping from a process of guesswork into a data-driven, AI-enhanced planning experience.