Model Targets

Model Targets enable apps built using Vuforia Engine to recognize and track particular objects in the real world based on the shape of the object. A wide variety of objects can be used as Model Targets, from home appliances and toys, to vehicles, to large-scale industrial equipment and even architectural landmarks.


To make a Model Target for a particular object you need to have access to 3D model data for the object, such as a 3D CAD model or a 3D scan of the object obtained from a 3rd party source or application. For more information, see Model Targets Supported Objects & CAD Model Best Practices.

Model Targets are supported on all Vuforia Engine platforms, however the Model Target Generator and the Model Target Test App require Windows 7 or newer (64 bit).

Model Target types

There are two kinds of Model Targets, based on whether or not they are backed by a Deep Learning-trained database.

Model Targets provide tracking for a single object, with recognition from a single Guide View. 

Model Targets with Advanced Recognition (MT-AR) provide tracking for multiple objects and/or recognition from multiple Guide Views. Because they are based on Deep Learning techniques, a training process is necessary when creating Model Targets of this type. The training is fully automated but takes some time (generally a little over 60 minutes on a typical laptop).

Creating Model Targets

Create a Model Target using the Model Target Generator application, which is provided as part of the Vuforia Engine SDK. The Model Target Generator outputs special data files which you can use with Vuforia Engine's Unity integration, or in your own native application, in order to track the object. 

For more information, see the Model Target Generator User Guide.

Testing Model Targets

The Model Targets feature has certain requirements for the object being tracked in order to ensure good recognition and high-quality tracking. Even after following our Best Practices guide, you may find that a 3D model has to be adjusted to ensure good tracking of the object, or even that the object itself is simply not suitable for tracking in the first place.

To assist with this process, the Vuforia Engine SDK ships with a Model Target Test App. Use it to try out tracking for a given object without any additional development.

For more information, see the Model Target Test App User Guide.

Using Model Targets


In a Unity app, Model Targets are recognized and tracked using the ModelTarget GameObject, provided as part of the Vuforia Engine Unity integration. Import the data files output by the Model Target Generator, add a ModelTarget GameObject to your scene, and configure the ModelTarget component to use the imported data files.

See the Introduction to Model Targets in Unity for more information.


In a native app, Model Targets are recognized and tracked by the ObjectTracker. Create a DataSet using the ObjectTracker and load the data files output by the Model Target Generator. Results are delivered via ModelTargetResult instances.

See the Model Targets API Overview for more information.