← Back to context

Comment by dmarcos

5 days ago

Yes. We have demos working already. Those 3D gaussian videos (or 4D that some people call) are really big so we're figuring out what's the best way to distribute and make it a great experience.

great to hear as a note, how the heck do they record them is it literally multiple camera points recording many videos and then synced?

  • Most 4DGS reconstruction methods right now are exactly that: setting up many cameras and recording them simultaneously so you can reconstruct each instant in time as a 3DGS. In the future it might be possible to use a single camera and have an AI/ML method figure out how all the 3D gaussians move over time, including parts that are occluded from the single camera!