So do this paper, although they get basically the same result from random initialization. But as mentioned, the point cloud is free since they need the camera poses anyway.

> We initialize our samples either randomly or from point clouds, typically from Structure-from-Motion (SfM) as in 3DGS

> But as mentioned, the point cloud is free since they need the camera poses anyway.

If you have a rigid multi-camera rig, the camera poses might be known from calibration, but then the particular scene shot on such a rig, could be reconstructed without COLMAP or other structure-from-motion tools, if I understand it correctly.

The point cloud is a by-product of of aligning the input images. You essentially get it for free.

The original 3DGS paper relied on some really hand-wavy heuristics to optimice the gaussians' location and size (and yet it worked remarkably well).

The value of the parameter was chosen by I picked it.

Hey guys, I think I found the NSA crypto-saboteur! :p

As someone who works in numerical optimization, this is a dirty little secret of our profession. The optimization algorithms in the literature are great at finding local minima, but often are very sensitive to the initialization as to how small the objective is. Good heuristics for initialization are thus critical for finding a good (small objective) minimizer. Sometimes this gets to the point where the local optimization algorithm does a trivial refinement of the heuristic’s solution.