[HN Gopher] 3D Gaussian Ray Tracing: Fast Tracing of Particle Sc...
       ___________________________________________________________________
        
       3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
        
       Author : smusamashah
       Score  : 77 points
       Date   : 2024-07-10 11:30 UTC (3 days ago)
        
 (HTM) web link (gaussiantracer.github.io)
 (TXT) w3m dump (gaussiantracer.github.io)
        
       | billconan wrote:
       | can this relight the existing scene?
        
         | vessenes wrote:
         | I don't think this offers anything new on relighting -- this is
         | literally just adding the ability to sample a splat during a
         | raytracing render step; nothing about changing a splat's color
         | / illuminance / whatever. That said, you could turn on, say,
         | reflections for parts of a splat scene subject to whatever
         | rules you wanted.
         | 
         | Maybe you could get relighting here of a sort, by computing
         | some sort of normal to each individual splat as you hit it, and
         | checking light values. That said, the splats don't (as far as I
         | know) approximate geometry, so normals on them may not be
         | (won't be?) what you'd expect from actual geometry.
         | 
         | I'd say this would be worth a try, it might turn out to work
         | okay, and would be nearly free in the rendering pipeline they
         | describe.
        
       | vessenes wrote:
       | This looks pretty interesting, for a few reasons: it can fit into
       | existing ray tracing rendering pipelines, and you get most of the
       | ray tracing benefits (reflection, shadows from geometry,
       | refraction, depth of field, camera geometry) along with it. These
       | are both pretty big.
       | 
       | Render quality is high / equivalent to MipNeRF (or however it's
       | capitalized). PSNR is equivalent or better, and the rendered
       | output can be denoised with, say OptiX.
       | 
       | Some downsides/caveats -- it works best if you retrain a little,
       | so you won't get the best quality if you're pulling over mipnerf
       | trained Gaussians, it's slower to render than a straight
       | rasterizer, like 50% slower, and of course these splats still
       | don't have geometry to them, as is much discussed elsewhere.
       | 
       | They spent a lot of work optimizing doing this for Nvidia's RTX
       | series, and the raytracing task is a little different than the
       | typical one, which is to say it's rare in 'normal' raytracing
       | that you're adding up the colors of 100s of transmissive, semi-
       | transparent colors/radiances to get a single pixel; usually the
       | bulk of the color from a raytraced scene comes from a smaller
       | number of rays. If this method becomes popular, then NVIDIA could
       | no doubt optimize the raytracing architectures further in the
       | future and you'd get back some of that speed.
       | 
       | All this to say, I hope this gets rolled into existing engines,
       | it's practical engineering that would add a lot of options to
       | workflows, and pretty neat!
        
       | echelon wrote:
       | "Anonymous authors"?
        
       | robinhouston wrote:
       | I'm intrigued by the anonymity of the author(s). I'm sure they
       | have reasons for wanting to remain anonymous, but I can't imagine
       | what they might be.
        
         | w-m wrote:
         | You can find their names here: https://arxiv.org/abs/2407.07090
         | 
         | The anonymity on the web page may be due to requirements of the
         | venue where the paper is currently under review. Sometimes
         | there are rules against advertising preprints under review. Or
         | maybe they have a link to the web page in the submission and
         | want to keep it double blind this way.
        
           | robinhouston wrote:
           | Ah, thank you! That makes sense.
        
       ___________________________________________________________________
       (page generated 2024-07-13 23:01 UTC)