alt Hacker NewsIn an earlier video they made a couple years back about Disney's sodium vapor technique Paul Debevec suggested he was considering creating a dataset using a similar premise: filming enough perfectly masked references to be able to train models to achieve better keying. So it was interesting seeing Corridor tackle this by instead using synthetic data.
With regards to the sodium vapor process, an idea has been percolating in the back of my head ever since I saw that video. But I don't really have the budget to try it out.
theory: make the mask out of non-visable light
illuminate the backing screen in near Infra-Red light. (after a bit of thought I chose near-IR as opposed to near-UV for hopefully obvious reasons)
point two cameras at a splitting prism with a near IR pass filter(I have confirmed that such thing exists and is commercially available)
Leave the 90 degree(unaltered path) camera untouched, this is the visible camera.
Remove the IR filter from the 180 degree(filter path) camera, this is the mask camera.
Now you get a perfect non-color shifting mask(in theory), The splitting prism would hurt light intake. It might be worth it to try putting the cameras really close together , pointed same direction, no prism, and see if that is close enough.