Sure, but they're not getting that 3d map from binocular vision. The forward camera sensors are within a few mm of each other and different focal lengths.
And the tweet thread you linked confirms it's a ML depth map:
> Well, the cars actually have a depth perceiving net inside indeed.
My speculation was that a binocular system might be less prone to error than the current net.
And the tweet thread you linked confirms it's a ML depth map:
> Well, the cars actually have a depth perceiving net inside indeed.
My speculation was that a binocular system might be less prone to error than the current net.