Your Email

Pasword

University of Washington 

Scientists at the Washington University in the US have found a way to produce a photorealistic footage of former US President Barack Obama. Artificial intelligence was used to precisely model how Mr. Obama moves his mouth when he speaks. The synthetic Obama face is functioned to speak any words; the technique allows putting any words into the former president?s mouth. 

Watch the video here- 

Courtesy- BBC 

The University posted the lip-synced video of Obama online. The program uses artificial intelligence (AI) to match audio of a person speaking with realistic mouth shapes, which it then grafts on to an existing video. After analyzing millions of video frames in stock footage, reviewing mouth shapes and sound patterns, the program is able to produce highly realistic simulations. 

The researchers selected Obama for their venture as there were numerous amounts of HD footages of him on the web. The research team had a neural net analyze millions of frames of video to determine how elements of Obama's face moved as he talked, such as his lips and teeth and wrinkles around his mouth and chin. The researchers took audio clips and dubbed them over the original sound files of a video. They next took mouth shapes that matched the new audio clips and grafted and blended them onto the video 

How is this useful? 

Ira Kemelmacher-Shlizerman at the University of Washington said that the application for this new technology is improving videoconferencing. The Computer scientists at the University of Washington previously revealed they could generate digital doppelgängers of anyone by analyzing images of them collected from the Internet, from celebrities such as Tom Hanks and Arnold Schwarzenegger to public figures such as George W. Bush and Barack Obama. Such work suggested it could one day be relatively easy to create such models of anybody, when there are untold numbers of digital photos of everyone on the Internet. 

This new research also suggests ways to detect fake videos in the future. The research was funded by Samsung, Google, Facebook, Intel and the University of Washington. 

The scientists revealed their research in a PDF at SIGGRAPH Technologies in New York on 2nd August. They came out with an eight minute short video. The invention combines the physical and the digital world. It is fascinating to know that machine learning and artificial intelligence blurred the line between the virtual and the physical.   

© www.newsandstory.com