海角大神

鈥淭here is no聽one聽alive who is Youer than聽You," wrote Dr. Suess. But what is it about you that makes you you? Researchers, using none other than Tom Hanks, have sought to find out.聽

Leveraging the enormous web presence of the prolific actor 鈥� a "Tom Hanks" Google search generates nearly 40 million entries 鈥撀燬upasorn Suwajanakorn,聽Steven M. Seitz, and Ira Kemelmacher-Shlizerman from the University of Washington compiled some of that visual data, combined it with an algorithm they created, and generated a 3D likeness that they say captures the "persona" of the well-liked actor. The digital likeness can be manipulated to deliver lines Mr. Hanks himself has never uttered, like a kind of futuristic puppet.聽

鈥淥ne answer to what makes Tom Hanks look like Tom Hanks can be that imitates what Tom Hanks will do,鈥� said Mr. Suwajanakorn, the study's lead author and a UW graduate student in computer science and engineering, in a statement explaining the study.

As technologies evolve, from augmented reality to three-dimensional printing, the researchers聽envision a future where anyone's photos and videos can be used to create an interactive 3D model from the persona captured in media.聽

鈥淵ou 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,鈥� said Professor Kemelmacher-Shlizerman, a senior author on the paper, which will be presented at the聽International Conference on Computer Vision in Chile on Dec. 16. 鈥淪uch technology doesn鈥檛 exist yet 鈥� the display technology is moving forward really fast 鈥� but how do you actually re-create your mother in three dimensions?鈥�

To "reconstruct" public figures like Tom Hanks, Barack Obama, and Daniel Craig, which the researchers did for the project called "," the algorithm pulled at least 200 images from the web of each person covering different periods of time, and various poses, and actions. The ability to synthesize "unconstrained data" signifies "a big deal in the world of digital modeling, said聽Kemelmacher-Shlizerman.

The results are an intricate map of one person鈥檚 features and expressions that can be transferred to another person鈥檚 3D digital likeness. Such 鈥渃ontrol鈥� of the digital model, according to the team, could open new doors for animation and virtual reality innovations.

鈥淗ow do you map one person鈥檚 performance onto someone else鈥檚 face without losing their identity?鈥� said Professor Seitz. 鈥淭hat鈥檚 one of the more interesting aspects of this work. We鈥檝e shown you can have George Bush鈥檚 expressions and mouth and movements, but it still looks like George Clooney.鈥�