The novel aspect here seems to be 3D LiDAR output from 2D video using post-training. As far as I'm aware, no other video world models can do this.

IMO, access to DeepMind and Google infra is a hugely understated advantage Waymo has that no other competitor can replicate.

▲

codexb 4 hours ago | parent | next [-]

3d from moving 2d images has been a thing for decades.

▲

ra7 4 hours ago | parent [-]

This is 3D LiDAR output (multimodal) from 2D images.

	▲	promiseofbeans 3 hours ago \| parent [-]
		LiDAR is the technology used to do spatial capture. The output is just point clouds of surfaces. So they’re generating surface point clouds from video

▲

moffkalast 44 minutes ago | parent | prev [-]

It's not unheard of, there are a handful [0] of metric monodepth methods that output data that's not unlike a really inaccurate 3D lidar, though theirs certainly looks SOTA.

[0] https://github.com/YvanYin/Metric3D