Gaussian Point Splatting

(momentsingraphics.de)

48 points | by ibobev 1 hour ago

8 comments

  • keyle 30 minutes ago
    It will be interesting to see the first AAA game that uses these methods instead of rendering a 3D world. Even if made from CGI worlds, it would be a very interesting approach and with somewhat predictable performances.

    Reminds me of Ecstatica [1], a 1994 game that had intense visuals with a very odd/different rendering engine made of 3D ellipsoids; in a way really crude splats in gouraud shading.

    [1] https://ecstatica.fandom.com/wiki/Ecstatica

    • avaer 24 minutes ago
      This is "rendering a 3D world". It's basically the exact same techniques that traditional rendering uses, just with a different primitive that's not triangles. Everything else pretty much carries over.

      If you mean the technique of splatting specifically, Dreams for PS4 [1] is prior art.

      If you mean pre-rendering, there's Myst and games like the original FF7 for PS1.

      [1] https://en.wikipedia.org/wiki/Dreams_(video_game)

  • HexDecOctBin 35 minutes ago
    Can someone point to a resource/tutorial for learning point splatting (the 90s rendering technique)? Gaussian Splatting has completely over taken the search results, and the original technique is now near impossible to find.
    • cubefox 21 minutes ago
      It's going to be even more impossible to find now because the present paper introduces "Gaussian point splatting".
  • cyber_kinetist 25 minutes ago
    Really nice idea for 3DGS rendering - though the main problem is the noise (an unfortunate issue for all Monte-Carlo based methods).

    I think future papers would probably continue improving on this method and focus on how to sample the points more efficiently while being unbiased (similar to how ray-tracing solved their performance issues). Or maybe... we can just add a deep-learning based denoiser and call it a day!

  • lucamark 47 minutes ago
    This feels like Monte Carlo rendering applied to rasterization. I'm wondering if it's a brand-new or a well established methodology
    • avaer 19 minutes ago
      Monte Carlo in 3dgs is established enough that Spark [1] has been doing it for a while in the browser.

      https://github.com/sparkjsdev/spark

    • pixelesque 44 minutes ago
      It's not new - that was sort of my point with my other comment.

      At least if it's progressive (so refines and resolves over time), this has been done with pointclouds in the VFX industry in GPU shaders for years in terms of stochastically drawing different points so eventually the whole point set gets rasterised to a fidelity threshold.

      • lucamark 36 minutes ago
        ookay, thanks for the clarification! So, the interesting part here seems to be the 3DGS-specific opacity correction and GPU workload mapping. Am I wrong?
  • phrotoma 35 minutes ago
    I love this site design. It uses the entire width of the monitor rather than a slender column of pixels down the middle with large blocks of unused space on either side, with a font for my old man eyes.

    <3

    • simonklitj 17 minutes ago
      Imo they need to pad it just a bit. My scrollbar overlaps.
    • docheinestages 13 minutes ago
      Maybe use Tampermonkey?
    • zokier 26 minutes ago
      > It uses the entire width of the monitor rather than a slender column of pixels down the middle with large blocks of unused space on either side

      Umm on my machine it has 560px margin on both sides with the content being only 474px sliver in the middle?

  • praveen9920 1 hour ago
    Sorting the gaussians is the compute heavy part in gaussian splatting. So, Im guessing this will give only marginal improvement in terms rendering speed.
    • xyzsparetimexyz 52 minutes ago
      I'm not sure it does a sort. Each group of threads only handles a select number of gaussians
      • zokier 25 minutes ago
        Yea, I think avoiding sorting is kinda the whole point here
  • cubefox 24 minutes ago
    Their point splatting method is orthogonal to level-of-detail rendering (they reference a few papers which try to do this), so both point splatting and LoD could be combined in the future for an even greater performance gain during rendering. They already implement occlusion and frustum culling.

    Point splatting does introduce a lot of noise though, and their denoiser introduces ghosting, but they say a more sophisticated denoiser would give considerably better quality.

  • pixelesque 1 hour ago
    > millions of threads

    Really?! What OSs can handle that many native threads?

    Also, this seems quite similar to stochastic progressive drawing of pointclouds for realtime that has been done for > 15 years in the VFX industry with GPU shaders in a tiled/bucketed fashion, unless this isn't progressive maybe? (The fact it's been accepted for Siggraph likely indicates it's slightly different).

    • Calavar 1 hour ago
      I believe they mean GPU threads. Plenty of cuda files in their repository.
      • pixelesque 46 minutes ago
        Fair enough, but that's then only absolutely max 1024 threads per SM, which wouldn't get anywhere near 1 million, given 5090 only has 192 SMs...

        Future proofing I guess...

        • cyber_kinetist 31 minutes ago
          You can launch much more logical threads than the available physical threads. The GPU scheduler will automatically dispatch the work to the SMs.
        • zipy124 17 minutes ago
          I guess they never say that they execute at the same time technically haha