Resurrecting the dead in a computer just became a possibilit
Source: JAKE ELLISON
This image of a dead relative could speak old letters or endearments and even interact with you. Of course, the best part is that the image would say what you wanted it to say ... or maybe that's the worst part.
If you have enough media -- photos and video -- of a loved one who has passed away, one day soon you should be able to use those images to generate a 3-D talking head of him or her that accurately represents facial expressions.
Call it a resurrection of sorts.
At any rate, computer scientists at the University of Washington have developed a machine-learning algorithm that can create a digital model of a well-photographed person. As a proof of concept, the UW team created accurate images of Tom Hanks, Daniel Craig and George W. Bush.
University of Washington caption: Researchers have reconstructed 3-D models of celebrities such as Tom Hanks from large Internet photo collections. The models can be controlled by photos or videos of another person.
So, could it recreate my dead grandmother?
"Yes," said UW assistant professor of computer science and engineering Ira Kemelmacher-Shlizerman, "if you have many photos and videos. One of our visions is to be able to interact with a famous person by mining their historic footage."
Related story: 'Stupid' learning machines are cloning you online: UW computer scientist, author of 'The Master Algorithm,' says we need to fight back with better data and a union
Of course, the reason they picked famous people for their experiments is the sheer volume of media of those people that's available online. The UW stated in a news release:
"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 reconstruction, tracking, alignment, multi-texture modeling and puppeteering 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. ...
"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," said senior author Kemelmacher-Shlizerman. "Such technology doesn't exist yet ― the display technology is moving forward really fast ― but how do you actually re-create your mother in three dimensions?"
One day the reconstruction technology could be taken a step further, researchers say.
"Imagine being able to have a conversation with anyone you can't actually get to meet in person ― LeBron James, Barack Obama, Charlie Chaplin ― and interact with them," said co-author Steve Seitz, UW professor of computer science and engineering. "We're trying to get there through a series of research steps. One of the true tests is can you have them say things that they didn't say but it still feels like them? This paper is demonstrating that ability."
| }
|