OpenFusion is an open source project, an alternative implementation of the system KinectFusion.

The system we implemented enables real-time tracking and reconstruction of 3D scene using a depth sensor, such as the Kinect or Asus XtionPro. The system receives a constant stream of depth maps from the camera, which it uses to track the 6DOF camera pose and update the model accordingly. As the user moves around the scene new views of the scanned objects are discovered and integrated, resulting in a complete high quality model. Though OpenFusion builds a static model, a small amount of dynamic interaction with the scene is possible; over time the system will "fix" the model using the new data received.

Our project is complete yet compact open source project, and works with every depth camera.

Watch our project demonstration - 360 degrees reconstruction:

Another demonstration, with explanations about the algorithm and the making of:

3D Printed Models

With OpenFusion you can easily scan yourself, extract the 3D model and print it using a 3D printer.
Using MakerBot Replicator 2 3D printer we have printed our own mini-me!


IMVC 2013

In February 2013 we demonstrated OpenFusion at IMVC (Israel Machine Vision Conference & Exhibition) as part of the Technion booth.

We scanned the conference attendees and sent them their reconstructed model by e-mail.


Technical Details

For technical details please read our report or take a look at our poster.

The project was conducted as the final project of two computer science students from the Technion, with the associated labs and department:

Click here to contact us.