Works the same way as any other software optimization: lower quality computation as a shortcut.
The predicted frames don't use the same full stack of data that a true frame uses to render, they just use the previous frames data and the motion vectors. The rest is a very efficient nueral-network guessing algorithm based on those two pieces of data instead of the full shader stack.
Say what you want about the aesthetics for Soviet era housing, most of them were surrounded by green space and playgrounds/trees when they were built. Which is more than we can say about modern 4-over apartments. The fact that they weren't kept up is more a sign of the times after they were built.