Can this be applied to preprocess low-res FMV cutscenes? Maybe even ones with line-skipping like the Z-vision games? - The GAN need to be trained with frames where half of the line is missing (it's a question of preparing the training set properly) - The GAN need to be temporally coherent - That's ...

This is a big development in the machine learning world and it's great that it can be used for such practical stuff. These results are truly phenomenal. Let's figure out a way to integrate pre-made images into ScummVM instead of the ones in the data files, rather than trying to do this on the fly, ...