With Machine Learning, The Era of Synthetic Video Is Here

Stanford engineers make editing video as easy as editing text

By Andrew Myers

With Machine Learning, The Era of Synthetic Video Is Here

Stanford University:

A new algorithm allows video editors to modify talking head videos as if they were editing text – copying, pasting, or adding and deleting words.

A new algorithm makes it possible to perform text-based editing of videos of “talking heads”; that is, speakers from the shoulders up.

To make the video appear more natural, the algorithm applies intelligent smoothing to the motion parameters and renders a 3D animated version of the desired result. However, that rendered face is still far from realistic. As a final step, a machine learning technique called Neural Rendering converts the low-fidelity digital model into a photorealistic video in perfect lip-synch.

Click here to read the original article at news.stanford.edu