by martinmusio7 on 9/13/22, 3:28 PM with 1 comments
Perpetual View/Video Generation (PVG). AI models generate open-ended videos from one image only - at least that’s the newest approach from Google Research [1]. These videos are “flying“ through a scene depicted in the input image. The range of potential applications is endless. Further, the tech behind it is incredibly smart and it marks the next cornerstone of generative AI.
In this episode we talk about the PVG's tech side and brainstorm about its future applications. (+ a little digression about the future usage of synthetic data in AI training.)
Best, Martin
by jschveibinz on 9/13/22, 3:35 PM