im familiar with this work and specifically they tried replicating the sodium vapor style approach but what worked for poppins level isnt actually good enough for today. Specifically you still end up with light spill that contaminates the foreground, especially for things like the fresnel reflections on the side of a face. the magenta idea was to still do what is basically a color difference key, but increase the color separation between fg and bg by lighting the two with different opposite colored lights. then using a ml model to recover the original fg color.