Gaussian Splats part 3: There's always a bigger scene

Re:Gaussian Splats part 3: There's always a bigger scene by slimbuck on Wednesday October 28, 2026 @01:59PM (#50278087)

I had no idea SOG was being used this way, so cool! I'm busy working on V3 if there's anything you think we should include.

https://github.com/playcanvas/splat-transform/issues/362

[ Parent | on HN ]

Re:Gaussian Splats part 3: There's always a bigger scene by slimbuck on Wednesday October 28, 2026 @02:02PM (#50278140)

The biggest update is adding alpha compensation (alpha > 1). With this in place we can addresses the gaps that appear after performing many rounds of decimation.

[ Parent | on HN ]

Re:Gaussian Splats part 3: There's always a bigger scene by w-m on Wednesday October 28, 2026 @06:54PM (#50282103)

Hey Donovan, keep up the great work :)

That reminds we, we had really weird results with splat-transform .sog output, when measuring the references for KISS-GS a couple months back. Why is the .sog curve dipping in quality when adding more primitives?

It's the "POPSpa + .sog" curve here, in the first Figure: https://arxiv.org/html/2608.26948v1

Always wanted to go back and measure with the latest splat-transform and find whats going on there.

[ Parent | on HN ]

Re:Gaussian Splats part 3: There's always a bigger scene by slimbuck on Thursday October 29, 2026 @06:02AM (#50286697)

Hi Wieland and congrats on your paper!

The issue you saw had been addressed in 1.7.0. We were generating codebooks for color and scale using k-means, which would result in bad values sometimes for the extremes. In 1.7.0 we switched to an optimal quantiser with outlier handling. It was actually surprisingly hard to get this right.

I just got opus to valid this now and it found another issue with our scale codebook gen, which I will fix now. Huzzzah!

[ Parent | on HN ]