It just kinda makes no sense to me. How can you improve the framerate by predicting how the next frame should be rendered while reducing the overhead and not increasing it more than what it already takes to render the scene normally? Like even the simplistic concept of it sounds like pure magic. And yet… It’s real.
You can do a lot without predicting anything. Remember human thresholds are fairly slow by computer standpoints.
Modern systems, depending on the game, can easily react in real time in terms of generating frames. And at that point it’s mostly geometry physics and other mathematical notions to produce the expected output.