Tom Hanks has appeared in many acting¹ roles over the years, playing young and old, smart and simple. Yet we always recognize him as Tom Hanks. Why? Is it his appearance? His mannerisms? The way he moves? 

 

University of Washington researchers have demonstrated that it's possible for machine learning algorithms to capture the 'persona' and create a digital model of a well-photographed person like Tom Hanks from the vast number of images of them available on the Internet.

 

With enough visual data to mine, the algorithms can also animate² the digital model of Tom Hanks to deliver speeches that the real actor never performed.

 

"One answer to what makes Tom Hanks look like Tom Hanks can be demonstrated with a computer system that imitates what Tom Hanks will do," said lead author Supasorn Suwajanakorn, a UW graduate student in computer science and engineering.

 

The technology relies on advances in 3-D face reconstruction³, tracking, alignment⁴, multi-texture modeling and puppeteering⁵ that have been developed over the last five years by a research group led by UW assistant professor of computer science and engineering Ira Kemelmacher-Shlizerman. The new results will be presented in a paper at the International Conference on Computer Vision in Chile on Dec. 16.

点击收听单词发音