Most of the examples they've chosen seem.. not good? What an odd mix of bad game engine and AI slop. I can't imagine that this stuff makes good training data for real-world applications.
These demos honestly look pretty good to me. But it is objectively true that this and similar technologies are used at huge scale by every leading autonomous vehicle manufacturer, so we can inductively reason that it _is_ good enough for that use-case. I don't work on Cosmos, but I am currently working on a superficially similar non-open technology at Nvidia used by many of these leaders which, in my opinion, produces similar quality. Some of the open research for it is here:
https://github.com/nv-tlabs/3dgrut/
https://github.com/NVIDIA/harmonizer
https://github.com/NVIDIA/instant-nurec
https://github.com/nvidia/ncore
Nvidia also is integrating Gsplat into at least what I work on and contributing upstream.
https://github.com/nerfstudio-project/gsplat