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.
Nice explanation. Now call me old fashioned, but I can’t help to wonder if all the effort in making the DLSS neural prediction engine and the “render at low res and then enlarge” would’ve been better spent in a regular rendering engine…