[ssivark]

Does anyone know how they do the “virtual object insertion” demonstrated in the paper summary video? Can that be somehow done on the network itself, or is that a diagnostic for scene accuracy by performing SFM on network output?

[theresistor]

I'm pretty sure they're rendering a depth channel and compositing it in.

[teraflop]

You could do that, but I think it's simpler to just introduce additional objects during the raytracing process that generates the images. That would produce accurate results even with semitransparent objects, unlike compositing with an depth buffer.