Getting Started with Advanced Model Targets 360

The Advanced Model Target 360 feature is available with Vuforia Engine 8.3 and includes the updated Model Target Generator desktop tool (MTG). The Advanced Model Target 360 introduces instantaneous recognition and tracking of physical objects, regardless of the viewing position and realistically augments digital content on an object by detecting the edges of the object from all angles.

The Advanced Model Target 360 works through a database that is trained in the MTG desktop tool. It is a process that uploads the Model Target database to the Vuforia Cloud where it is trained by a deep learning process. The exported database allows for 360˚ detection and can be easily imported to Unity or a native application (XCode, Visual Studio, Android Studio) for development.

The Vuforia sample package presents the NASA Viking lander, which can be 3D printed and tested with the new feature. The model and printing instructions can be found on the 3D Printing Instructions for the Viking Mars Lander page. It demonstrates the Advanced Model Targets 360 and is a resource to help you get started. The sample package is available on Vuforia’s website in the Downloads section under the Samples tab.

The Model Target Generator (MTG)

The Model Target Generator is a software tool developed by Vuforia to create Vuforia Device Databases required for detection and tracking of physical 3d objects represented by their digital 3d model. It is currently only available for Windows. It takes a CAD model as input and outputs a Vuforia Device Database. See Model Target Generator User Guide for more information regarding installation and general information on Model Targets and Guide Views.

Creating an Advanced Model Target 360 Database

This section will guide you through the process of creating a Model Target database with the 360˚ detection feature.

  1. Install the Model Target Generator which can be downloaded from the Vuforia Developer portal in the Downloads section on the Tools tab.

NOTE: Trained datasets created by the MTG only work with Vuforia Engine 8.3 and later.

  1. Obtain a physical object and its 3D model in any format listed in Model Targets Supported Objects & CAD Model Best Practices or use the Vuforia Sample Project with the NASA Viking Lander. See Printing and Assembling the Viking Lander for more information. 
  1. Save the files you have selected or the Sample Project in a new folder.

NOTE: the files generated by the MTG are by default stored in a subfolder at the same location where the MTG was installed.

  1. Open the MTG.
Vuforia Image
  1. Use your Vuforia Developer credentials to log in.
  2. Start creating a new Model Target by clicking Create New Model. Choose a name and the Model you wish to use.
  3. In the Model View, navigate to Model Attributes and, if needed, appoint the Up Vector and the File Units correctly according to the plane and your model’s dimensions.
Vuforia Image

NOTE: using an incorrect scale and measurements can result in poorer recognition. See How to Create a Model Target for more information on this topic.

  1. Select the new feature 360˚-button and click the Create 360° Guide View button.
    This will generate a single Guide View that defines the recognition range and is necessary for training the Model Target in the following section. See Model Target Guide View for more information on the role of recognition range and Advanced Model Target 360.
Vuforia Image
  1. Click the Generate Model Target button.

NOTE: the database that is generated is by default stored in a subfolder named SampleData in the location where the MTG is installed. With each generation the Model Targets quota is reduced by one.

Training the Model Target 360

The next step is to train the newly generated Model Target database. This is achieved by creating a New Database in the MTG. There are two types of trained sessions that the MTG offers. Training of multiple Model Targets each with one or more Guide Views and the training of a single Model Target for 360˚ detection.

  1. Click the Create Database button.
  2. Fill out the name and description. Choose the 360˚feature and select realistic if your model includes texture or color information that is the same as the physical model or non-realistic if this is not the case.
Vuforia Image
  1. Press the Create Database button.
  2. Now the training set is ready. On the right column, you will now see a list of your databases ready to be trained. Press the train set button next to the training set recently created. This action will upload the Training Set to the Vuforia cloud for the training process to take place.
    NOTE: this is a significantly time-consuming process, which depending on the complexity of the model(s), can take approximately two hours or more. An estimate will be shown next to the training set during training.
  3. Once the training set has been trained by the Deep Learning technology, the database can be exported by clicking Export.
  4. The database just created by the MTG can now be imported into Unity or a native application.

Loading the Advanced Model Target 360 to Unity or Native

The Model Target Generator saves the database to your disk as .unitypackage files and .dat and .xml file pairs.

If you are working with Unity, import the .unitypackage into your project, then add and configure a ModelTarget GameObject.See Introduction to Model Targets in Unity for a step by step guide.


If you are building a native app, load the .dat .xml file pair into a Dataset created from the ObjectTracker. For further information, refer to the Model Target Native Workflow.

Testing with the Test Application

Alternatively, Vuforia offers an Android Model Target Test App for viewing and testing your generated and advanced databases. Simply, load the two database files to the directory of the installed test application on your Android device and test your newly generated Advanced Model Target 360. The directory on your device is usually found here:


Once the two database files have been copied to the directory, you can run the application. Press OK, on the information screen. Now, double tap on the screen to access your advanced database that is available in a list. The object will be outlined once recognition and tracking have begun.


Learn more and next steps

Introduction to Model Targets In Unity

Model Targets Native Workflow

Model Targets Test App User Guide