You can do it with cameras. But they have to be set up with overlapping field of views. And these semanticus while very valuable and can make a really important contribution to depth measurement, are never going to be accurate enough for what we think is a safety critical application. The reason that tesla didn't invest in multiview geometry techniques back then was because there was no solution. There was no technology that was really credible, that could actually solve the problem that we've solved in real time on a vehicle.
The asinine "camera vs lidar" debates are blown apart into several, far more interesting pieces in this week's episode, as the gang is joined by longtime friend of the show Tarani Duncan and Jason Devitt, co-founder and CEO of Compound Eye. Discussion covers the multiple approaches to camera-based depth perception, the evolutionary vs ground-up approaches to autonomous vehicles, and a little lidar shade as a treat.