I'm looking for a good way to generate high resolution results.
Currently I see two different strategies to achieve that.
Either using pix2pixhd with high resolution datasets or using pix2pix or cyclegan with low resolution datasets and upscale it with Image and Super-Resolution Using an Efficient Sub-Pixel Convolutional ?
I'm not sure which is the better approach and or did I miss something out there ?
I do appreciate any hints or tips !