Training is the final step: it turns the sparse model from Alignment into a Gaussian splat you can view and share. For the short version, see the First Run walkthrough.

What alignment hands off

A finished alignment is a sparse COLMAP model — camera poses plus a sparse point cloud — ready to be handed to a 3D Gaussian-splatting trainer. Nothing about the reconstruction is baked in yet; the trainer builds the actual splat from these camera positions and your masked frames.

Choosing a trainer

Any standard 3DGS trainer that reads a COLMAP dataset will work. Common choices:

Trainer	Notes
Postshot	Easy GUI, monthly subscription
LichtFeld Studio	One-time payment, or free build from source
Brush	Free and open source — build from source or download a build

After training

The trainer produces a .ply (or its own splat format) that you can view in any Gaussian-splat viewer, embed on the web, or bring into other 3D tools.

You'll find the .ply next to the input video, in <name of clip folder>/training_output.