[heliophobicdude]

Thank you so much for open sourcing this!

I've started a project to initialize each pixel in an image into a mesh of GS. I used a depth map to unproject them into space.

I've been very curious what a few training iterations would do to optimize my scenes. The original 3DGS implementation is not accessible on my hardware at the moment! I really look forward to your training implementation!

[0x02A]

That's super interesting. Are you trying to do single-view image to 3D?

[heliophobicdude]

Kinda! My ultimate goal is to be able to join multiple 3D reconstructions from a set of iPhones all in different positions! Like hemisphere. The single-view image to 3D is pretty accurate but across lots of iPhones.

[0x02A]

Does colmap fail on your dataset?

[heliophobicdude]

I honestly haven't tried! I'm trying to do this per frame of a live video. I had not considered COLMAP for performance reasons.

[pierotofy]

For training you can also try https://github.com/pierotofy/opensplat