News for hackers. Stuff that matters.
Re:Gaussian Splatting is pretty cool by eloop on Thursday September 07, 2023 @04:41AM (#37416274)
Splatting for volume rendering is quite old - Westover, Lee Alan (July 1991). "SPLATTING: A Parallel, Feed-Forward Volume Rendering Algorithm"
Re:Gaussian Splatting is pretty cool by andybak on Thursday September 07, 2023 @05:20AM (#37416522)
Are you saying there's nothing new in this or that it's building on an already established approach? I think the latter is not something anyone is trying to hide - while the former doesn't seem correct.
Re:Gaussian Splatting is pretty cool by corysama on Thursday September 07, 2023 @11:07AM (#37420019)
What’s new in the paper is the technique to generate the gaussians from photos. The output that is used to render uses a technique that is a decade or three old, but not terribly practical until recently.

For me, a rendering guy, that’s great! The data used at render time is very simple and flexible. Simpler than triangles even when you get into non-trivial operations.

Re:Gaussian Splatting is pretty cool by andybak on Thursday September 07, 2023 @11:59AM (#37420932)
Is the decades-old type of splatting view-dependent still?
Re:Gaussian Splatting is pretty cool by corysama on Thursday September 07, 2023 @03:13PM (#37424101)
The view-dependent bit reflects the simplicity of the data. The data is similar to an oriented, stretchy box that you interpret as an oriented, stretchy, fuzzy ball (the Gaussian field). What you do from there is up to you.

Classically, researchers were interested in just using the splats at all. So, they just assigned a single color to each one.

This paper assigns a spherical harmonic-based color sphere instead. That gives it the view angle -> color function.

There is a second paper focused on moving splats. It just uses solid colored splats.

You could instead associate albedo/specular/roughness from real time materials and do real time lighting. But, you’d have to figure out how to generate/capture those values.

Re:Gaussian Splatting is pretty cool by nsajko on Thursday September 07, 2023 @08:16AM (#37417826)
Yeah, it seems like the authors of the new paper may have missed much relevant existing research?
Re:Gaussian Splatting is pretty cool by tayistay on Thursday September 07, 2023 @03:13PM (#37424092)
They haven't. You can't get a paper into SIGGRAPH that misses relevant existing research.
Re:Gaussian Splatting is pretty cool by mikhailfranco on Thursday September 07, 2023 @10:42AM (#37419605)
Yes, I used to think of it as throw Gaussian snowballs at the window and see what sticks.

P.S. Not sure where the insight came from, but I was living near Boston at the time, and had young children :)