This is fantastic.

I've been trying to build something myself for biological and heritage captures. Could you elaborate at all on the JS decoder method used or resources that ended up enabling you to make it?

I've been playing with Playcanvas React for the past week, would your method integrate with their platform?

We're trying to get this upstreamed so I actually expect PlayCanvas to talk about it in the future. Here's the reference (cpu) decoder: https://github.com/vincentwoo/blog/blob/master/3d/sutro_towe..., as well as a gpu one: https://github.com/vincentwoo/blog/blob/master/3d/sutro_towe....

For more information on the format itself you can look at https://github.com/nerfstudio-project/gsplat/blob/main/gspla....

This application was built on PlayCanvas Web Components: https://github.com/playcanvas/web-components/

It's very similar to PlayCanvas React, but with a fully Web Components-based architecture. You can use the same scripts interchangeably between both frameworks.

I'm assuming you started working on this before their React release, or was Web Components chosen for a specific reason?

I'm trying to make something that can take in real-time data and also handle some XR/AR if possible as well, but I am pretty ignorant beyond html/css/js.