Photograph any object, remove its background instantly with on-device ML, organize collections into mood boards, and place items in real spaces using AR. No internet needed — all models run locally.
View on App StoreTake a photo or pick from your gallery. The on-device ML model removes the background instantly — no internet required. Works on furniture, art, plants, anything. Clean cutouts every time.
Save every cutout to your personal collection. Organize items into themed groups. Build a visual library of objects you can reuse across mood boards and AR scenes.
Arrange collected objects into mood boards. Change background colors to test combinations. See which pieces work together before committing to a design. Export boards as images.
Place any collected object in real space using AR. See how furniture fits in a room, how art looks on a wall, or how a collection works in context. No internet needed — all rendering happens on-device.
Swap backgrounds, adjust sizing, and fine-tune cutouts. Export clean PNGs for use in other design tools. The app fits into existing creative workflows without replacing them.
Native iOS app optimized for camera, ML inference, and AR rendering.
Custom on-device ML models for real-time background removal without internet.
Apple's AR framework for placing collected objects in real-world spaces.
Apple's ML framework for optimized on-device inference and model management.
Image processing pipeline for cutout refinement and background manipulation.
Design system created for creative professionals and interior designers.
Making every feature work without internet was the biggest challenge. In-house ML models for background removal had to be small enough for mobile yet accurate enough for professional use. The constraint produced better engineering.
Building an app for creative professionals pushed our designers and engineers to think differently. Our designers built for people like themselves. Our engineers loved the puzzle of real-time ML on mobile.
Working with custom machine learning models that identify patterns and improve over time showed us how vast the possibilities are. Every project since benefits from what we learned building Dezigner.