A team of researchers from University of Washington has developed a revolutionary 3D model algorithm that relies on bulk of images of celebrities that are available on the web to made 3D models.

The team even released a video in which it showed how their tool projected that facial mannerism of celebrities kike Tom hanks and former US President George Bush onto other 3D facial reconstructions.

Developing this outstanding 3D imaging tool took five years of time. The work has been led by graduate student Supasorn Suwajanakorn and assistant professor of computers science and engineering Ira Kemelmacher-Shlizerman.

The team presented their findings in a paper at the International Conference on Computer Vision, which was held in Chile on December 16.

Lead author of the study Suwajanakorn said the entire goal of their tool is to find out what make person look like himself when he/ she talks, and how facial expressions can be predicted in 3D.

As the technology keeps on evolving the reserachers dream of a future where anyone’s photos and videos can be used to create an interactive 3D model from the persona captured in media.

Study senior author Kemelmacher-Shlizerman said, “You might one day be able to put on a pair of augmented reality glasses and there is a 3-D model of your mother on the couch”.

In order to recreate public figures like Tom Hanks, Barack Obama, and Daniel Craig, which the researchers did for the project called ‘What Makes Tom Hanks Look Like Tom Hanks’, the algorithm used at least 200 images from the web of each person covering different periods of time, and various poses, and actions.