Stanford University researchers have developed a video-editing algorithm that works on talking-head videos, or those that clearly show the speaker face-on, from the shoulders up, enabling producers to correct misspoken lines without the need for re-shoots. All one would have to do is change the words in a transcript of the actor’s speech, enabling you to add, remove or rearrange them as desired. Read more for a video and additional information.
“To show the potential of the system, researchers made complex edits to sample footage, including adding, changing and removing words, as well as transitioning into different languages and creating whole new sentences from scratch. The edited videos were rated as appearing authentic almost 60 per cent of the time in a crowd-sourced survey of 138 participants,” reports The Daily Mail.