Tuesday, July 11, 2017
Researchers make a surprisingly smooth artificial video of Obama
The researchers used 14 hours of Obama’s weekly address videos to train a neural network. Once trained, their system was then able to take an audio clip from the former president, create mouth shapes that synced with the audio and then synthesize a realistic looking mouth that matched Obama’s. The mouth synced to the audio was then superimposed and blended onto a video of Obama that was
Subscribe to:
Post Comments (Atom)
Featured Post
Hackers Exploiting ProxyLogon and ProxyShell Flaws in Spam Campaigns
Threat actors are exploiting ProxyLogon and ProxyShell exploits in unpatched Microsoft Exchange Servers as part of an ongoing spam campaign
Popular Posts
-
Threat actors are exploiting ProxyLogon and ProxyShell exploits in unpatched Microsoft Exchange Servers as part of an ongoing spam campaign
-
The connection between the Apple Watch and an iPhone is the core of Apple’s wearable experience, and for the first time, the company gave th...
-
Tired of home security cameras that add nothing to your home (besides, well, surveillance)? The Ulo, created by Luxembourg-based Mu Design, ...
No comments:
Post a Comment