Comment by data-ottawa

But the mesh is itself an abstraction, you just need to build that bridge.

We've been leaning away from pure polygons for decades, anyway. Vertex skinning, SDFs, volumetrics, simulation, and a lot more.

The meshes in a From Software game are for exmple hilariously simple, most of the animation is force simulation to make the famous "frizzles" that they like.

I don’t know. Maybe today, but tomorrow?

If you can sample points inside a volume, in theory you could do that with splat geometry. If someone figures out a way to pass in animation time to a sampler, sample along geometry/wireframe or something else, and keep it from overly twinkling it might change everything.

I’m hand waving all the complexity into “if done one figures out”, of course.

I just don’t see why this method can’t evolve in the way diffusion models have evolved (knowing very little of the geberative mechanics of splats).

It’s easy but a bit data intensive. Take two 3D splat images at different times, optimize them, then interpolate from the first to the second. Repeat at intervals. Now you have a video. A full moving subject is about 500Mbps, although it depends a lot on the quality of the source images that you make the 3D splats from and how detailed the output image is. Search for “4D gaussian splats” to find references.

You pretty much just need a representation that can be constructed reasonably and interpolated.