We've posted a number of fancy video packages this year that feature the enhanced cutscenes ODVS has managed to create. We're careful to not refer to it as just "upscaling" since actual bits of new data are being added to create detail where none existed before. How is this accomplished and what are the limits? What do we mean by saying it's run through an AI routine? ODVS explains all this and more in a new article. You can learn about modern computerized neural networks and all the work ODVS does to manually pre-process the footage before he can turn the crank here.GIGO – QUALITY IS KING
In my case, I use a Neural Net-trained application called Topaz Labs Video Enhance AI. The application has been loaded with several AI models that can be applied to source materials of various quality with varying results.