philip lelyveld The world of entertainment technology


Google Scientists Generate Realistic Videos at Scale with AI

Google_Logo_SignThe systems are based on a neural architecture known as Transformers, as described in a Google Brain paper, and are autoregressive, “meaning they generate videos pixel by pixel.”

VentureBeat reports that the scientists, in a paper titled “Scaling Autoregressive Video Models” on preprint server, described that the group’s “[AI] models are capable of producing diverse and surprisingly realistic continuations on a subset of videos from Kinetics, a large scale action recognition data set of … videos exhibiting phenomena such as camera movement, complex object interactions, and diverse human movement.”

“This marks a departure from the often very narrow domains discussed in the video generation literature to date, such as artificially generated videos of moving digits or shapes, or videos depicting natural, yet highly constrained environments, such as robot arms interacting with a small number of different objects with a fixed camera angle and background,” they wrote.

See the full story here:

Comments (0) Trackbacks (0)

Sorry, the comment form is closed at this time.

Trackbacks are disabled.