At the SIGGRAPH computer graphics conference in Vancouver, B.C., Microsoft demonstrated “KinectFusion: Real-Time Dynamic 3D Surface Reconstruction and Interaction,” showcasing how the device can scan an entire, object room or person and then re-build them as a 3D model.
"Our technique for tracking is directly suited to the point-based depth data of Kinect, and requires no feature extraction or feature tracking. Once the 3D pose of the camera is known, each depth measurement from the sensor can be integrated into a volumetric representation," reads a small part of Microsoft's offical blurb on KinectFusion.
The following video gives you a glimpse at its potential.
So far Kinect has largely been used for casual gaming and hasn’t impressed, though Ubisoft has hinted at its potential with the upcoming Ghost Recon: Future Soldier, in which players can sweep their hands across the screen to customise weapons. If utilised fully by developers, the potential with KinectFusion is quite incredible. The only thing stopping developers create the next-generation of games will be their own imaginations, so let’s hope they can come up with something more creative than Fruit Ninja Kinect.
