If you need to make a 3D model of an object, there are many ways to do it, but most of them are only automated to the extent that they know circle around this object together a mesh. This new Fraunhofer system does this in a smarter way, getting a basic idea of ​​the object to scan and planning what the movements will let it do in an efficient and complete way.

This process can take a long time: a scan is completed and the user has to inspect it, find where it is located below (an overhanging part of another, for example, or an area of ​​greater complexity that requires further investigation), and customize a new analysis to compensate for these deficiencies. It is also possible that the scanner already has to load a 3D model in order to recognize what it looks and know where to focus.

The Fraunhofer project, directed by Pedro Santos at the Institute of Computer Graphics Research, aims to do things for the first time by asking the system to evaluate its own images as and when measure and plan his next move.

The peculiarity of our system is that it scans the components autonomously and in real time, “he said in a press release.He is able to” measure any component, regardless of its design – and you do not have to teach it. “

This could help create unique duplicate parts that the system has never seen before, such as a lamp or custom container, or a replacement for the door or engine of a car. collection.

If you are in Hannover in April, go to Hannover Messe and try it yourself.

Stock Image: Fraunhofer