News for hackers. Stuff that matters.

A comment on The Waymo World Model: A New Frontier for Autonomous Driving Simulation. Parent comment

Re:The Waymo World Model: A New Frontier for Autonomous Driv... by smallmancontrov on Friday February 06, 2026 @05:21PM (#46918938)
It was spectacularly good before 2021, 2021 is just when I noticed that it had become spectacularly good. 7.5 billion miles later, this appears to have been the correct call.
[ Parent | on HN ]
Re:The Waymo World Model: A New Frontier for Autonomous Driv... by quanto on Saturday February 07, 2026 @11:35AM (#46925140)
What are the techniques (and the papers thereof) that you consider to be spectacularly good before 2021 for depth estimation, monocular or not?

I do some tangent work from this field for applications in robotics, and I would consider (metric) depth estimation (and 3D reconstruction) starting to be solved only by 2025 thanks to a few select labs.

Car vision has some domain specificity (high similarity images from adjacent timestamps, relatively simpler priors, etc) that helps, indeed.

[ Parent | on HN ]