[jorgemf]

Basically you train a model per each set of images. The model is a neural network able to render the final image. Different images will require different trained models. Initial gaussian splatting models took hours to train, last year models took minutes to train. I am not sure how much this one takes, but it should be between minutes and hours (and probably more close to minutes than hours).

[tomp]

No, what you're describing is NeRF, the predecessor technology.

The output of Gaussian Splat "training" is a set of 3d gaussians, which can be rendered very quickly. No ML involved at all (only optimisation)!

They usually require running COLMAP first (to get the relative location of camera between different images), but NVIDIA's InstantSplat doesn't (it however does use a ML model instead!)

[dagmx]

Nit: splats are significantly older than NeRFs. They just had a resurgence after nerfs.

We’ve been using pretty similar technology for decades in areas like Renderman radiance caches before RIS.

[petargyurov]

Thank you, that explains it.