Comment by redox99
1 day ago
Gaussian splats don't offer the flexibility required for your typical videogame. Since it isn't true PBR its lighting is kind of hardcoded. Rigging doesn't work well with it. And editing would be very hard.
It's good for visualizing something by itself, but not for building a scene out of it.
People are working on recovering PBR properties, rigging, and editing. I think those are all solveable over time. I wouldn't start a big project with it today, but maybe in a couple years.
If you want a real cursed problem for Gaussian splats though: global illumination. People have decomposed splat models into separate global and PBR colors, but I have no clue how you'd figure out where that global illumination came from, let alone recompute it for a new lighting situation.
Some intrepid souls are trying to tackle the global illumination problem! https://arxiv.org/abs/2410.02619
Wow!
Also, since it's slightly hidden in a comment underneath the abstract and easy to miss, here's the link to the paper's project page: https://stopaimme.github.io/GI-GS-site/
Yeah no animation is a pretty big blocker. The tech can handle video clips tho.
I wonder if it's possible to do some kind of blendshape style animation, where you blend between multiple recorded poses.
Early 3D engines and of course all the 16 bit 2D games had “canned animation”. Half Life was an early example I can think of that used real IK rigging. Unreal 1 did not.
For half life it would be FK (forward kinematics). IK I assume was introduced in HL2 (but I don't know for a fact)
2 replies →
It would next extension and extra parameters, but plenty of AAA assets have had their shaders produced by cameras with fancy lighting rigs for many years.