Luma AI: New smartphone app creates 3D models of any object

In the field of AI, the step from study to startup happens pretty fast - so the new company LumaLabsAI demonstrates its Luma AI app, which can generate 3D views (and also models) of objects on a smartphone just based on some photos. For now, the project is still in closed beta (you can apply for access), but there are already some impressive examples of various 3D models generated by Luma AI. For now, Luma AI is only available for iOS, but an Android version is planned.

The applications of such an app are numerous - for example, the 3D object can then be further edited in a 3D modeling program like Blender or a game engine like Unreal, exported as a photo in a specific view, or imported into augmented or virtual reality environments.

LumaLabsAI (not to be confused with LumaFusion, makers of the popular mobile video editing app LumaTouch) was founded just about a year ago by engineers who previously worked in Apple&s AR and computer vision group. In order to present the resulting 3D models on the web, the company plans to develop its own embeddable player for its products, allowing online stores, for example, to offer interactive three-dimensional views of a product.

In the following video, you can see how the Luma AI app works: in an augmented reality view of the live camera image, the user can create a virtual 3D box in the app around an object that is to be captured. Then you have to walk in a circle, the camera always pointed at the object, to capture views from all sides.