[perching_aix]

That's kinda what NERFs are (neural radience fields). They actually preceeded this Gaussian story, with Gaussians coming in and outperforming them. Maybe they'll merge later for something even better, I don't know enough about them.

[cubefox]

NERFs have significantly higher image quality than 3D Gaussian Splatting or more recent similar techniques, though they are much slower to render.

[thrownthatway]

This one month old video did a reasonable job of getting my entirely ignorant self relatively up to day on NERFs and Gaussian Splats:

https://youtu.be/X8yRlA7jqEQ

[MattCruikshank]

Sure, but NERFs were trying to match your input photos and poses, not some arbitrary prompt, if I understand correctly.

[Lerc]

Yes they are image generators. You want image generator generators.

A diffusion style process generating gausians instead of pixels. You could possibly do nerfs that way, but it would be effectively generating a trained network. If you managed to do that it would have broad application throughout the field of AI.

[dpoloncsak]

What would this look like in practice? A net that outputs weights for a new net to use?

[xigoi]

Couldn’t you “uncurry” such a process to have only a single network?

[dpoloncsak]

Probably? I'm no expert, just a SysAdmin trying to keep up really... but in my head it's would look like a form of MoE that would gen the 'Expert' model on demand instead of having a variety baked in.

That's assuming you could even reasonably train a neural net to output viable weights, of course.