[raghavkhanna]

How is this ML? They use a CNN for foreground segmentation, a minor step in their pipeline. But the major contribution seems to be putting the silhouettes in a common reference frame. I sincerely hope sciencemag isn’t putting ML in the title purely to jump on the bandwagon.

[eclee2]

What a farce. The use of the ML for background subtraction is almost inconsequential to the contribution of the paper and the result.

[utkarshsinha]

It's someone standing in front of a green screen. You don't need ML to find a person's silhouette.

[seandougall]

To be fair, they do have examples that aren’t chroma keyed; they just lead with one that is.

Which is not to say that ML is necessary for this sort of computer vision task, but I wonder if it yields better or sharper results than other techniques?

[extralego]

Same. As someone who has spent an embarrassing amount of time keying and tracking video footage over the years, I’m surprised ML isn’t being used for this more often in studios by now.