AI Creates Fake Obama




AI software could generate highly realistic fake videos of former president Barack Obama using existing audio and video clips of him, a new study (PDF) finds.
University of Washington: “Given audio of President Barack Obama, we synthesize a high quality video of him speaking with accurate lip sync, composited into a target video clip. Trained on many hours of his weekly address footage, a recurrent neural network learns the mapping from raw audio features to mouth shapes. Given the mouth shape at each time instant, we synthesize high quality mouth texture, and composite it with proper 3D pose matching to change what he appears to be saying in a target video to match the input audio track.”
Source: Supasorn Suwajanakorn
Read more: spectrum.ieee.org & washington.edu (PDF)
Face2Face: Real-time Face Capture and Reenactment of RGB Videos
Facial Recognition
Visual Recognition
Computer Vision
AI News & AI Books
Computer Vision, AI Creates Fake Obama | Synthesizing Obama - Learning Lip Sync from Audio, Artificial Intelligence

Donate BTC: 1DUUZbiqjbJvzjuRZEwTS47bqgmnhEJ4XG

Donate ETH: 0x981FcEAAa895C6cee76D2876e9AfC649Dc0C4c75

More Posts:

Urban Postal Delivery Services Embodied In ‘Follow Me’
Fast Trans-Oceanic Travel: Tubes Option
Elevated & Multifunctional New York City Theatre
Google Glasses: Directional Sound & Speech To The Deaf
EML-2 Station: Possible Future For The American Space Program
Nanoflower Structure Will Lead To More Efficient Batteries
Humans, Cyborgs, Posthumans: Francesca Ferrando at TEDxSiliconAlley
A ‘Wikipedia’ For Neurons
Tomorrowland - Trailer #2
Volvo Pioneers Autonomous, Self-Driving Refuse Truck In The Urban Environment