Shrink Wrapping Small Objects

We consider the problem of scanning and modelling small objects using easily available RGBD sensors such as the Kinect. These sensors allow for the acquisition of view-based registered depth and color data. We register the point clouds by recovering the rigid transformation between successive pairs in a sequence of views, and then demonstrate the utility of surface evolution for shrink wrapping the result using geometric flow based approaches for surface modelling. In our experiments we use a PrimeSense Carmine 1.09, which is a high resolution short range RGBD sensor suited to capture small objects. We obtain high quality surface and appearance models of small objects that are competitive with commercial software packages while better capturing surface detail.