UW News

Steve Seitz


July 11, 2017

Lip-syncing Obama: New tools turn audio clips into realistic video

Reel of Obama photos

A new machine learning tool developed by UW computer vision researchers can create realistic videos from audio files alone – including speeches by President Barack Obama.


December 7, 2015

What makes Tom Hanks look like Tom Hanks?

UW researchers reconstructed have 3-D models of celebrities such as Tom Hanks from  Internet photo collections. The models can be controlled by photos or videos of another person.

UW researchers have reconstructed 3-D models of celebrities such as Tom Hanks from large Internet photo collections. The model can deliver speeches that the real actor never performed – one step toward developing fully interactive digital personas of people from family or historic photo collections.