[HN Gopher] Voyager: Real-Time Splatting City-Scale 3D Gaussians...
       ___________________________________________________________________
        
       Voyager: Real-Time Splatting City-Scale 3D Gaussians on Your Phone
        
       Author : PaulHoule
       Score  : 40 points
       Date   : 2025-06-17 13:08 UTC (9 hours ago)
        
 (HTM) web link (arxiv.org)
 (TXT) w3m dump (arxiv.org)
        
       | jauntywundrkind wrote:
       | Are there any existing examples of partial render offload to the
       | cloud?
       | 
       | Crazy good insight here: splatting is largely a search problem,
       | and that can be offloaded to the cloud.
       | 
       | > _Specifically, on the cloud side, we propose asynchronous
       | level-of-detail search to identify the necessary Gaussians for
       | the client. On the client side, we accelerate rendering via a
       | lookup table-based rasterization._
        
       | reactordev wrote:
       | Been doing this at Faro Inc since 2023 - I helped build it. The
       | real magic is simply the lookup rasterization on device. Since
       | mobile device GPU's are fast now it fits inside the geometry
       | shader.
        
         | tobinc wrote:
         | Any word if Faro is working on anything like Leica's Powerlock
         | for laser trackers?
        
           | reactordev wrote:
           | Faro does scanning, not tracking. It shoots lasers in all
           | directions while simultaneously taking 360deg imagery,
           | resulting in high density colored point clouds and gaussian
           | splat pre-imagery. I no longer work there as they up rooted
           | their executive team.
        
       | modeless wrote:
       | Is there a demo?
        
         | gbin wrote:
         | Is there code?
        
           | tetris11 wrote:
           | "Code coming soon"
        
         | tetris11 wrote:
         | https://voyager-web.netlify.app/
        
       | ge96 wrote:
       | Why am I seeing "splatting" more often recently thought it was
       | old tech
        
         | nomel wrote:
         | Most tech is "old", with new use cases and accessibility. I
         | think it's most interesting when it jumps into my pocket.
        
         | hirako2000 wrote:
         | If you call a few years, 'old'.
         | 
         | Anyhow the novel approach opened the route for building on top.
         | A paper recently proposed dynamic captures, for real time
         | animated Gaussian Splats.
         | 
         | It will go on there is so much to explore research-wise,
         | optimisation like this innovation along is a large field of
         | efforts.
        
         | littlestymaar wrote:
         | I don't know what was the use of "splatting" before that, but
         | the modern trend has started just two years ago with this
         | paper: https://repo-sam.inria.fr/fungraph/3d-gaussian-
         | splatting/
        
           | corysama wrote:
           | Various forms of point/blob rendering have been around for
           | decades. What has been missing has been good workflows to
           | create the content.
           | 
           | That paper kicked off a rapid stream of a thousand papers by
           | taking a photogrammetry-style workflow and producing better
           | than photogrammetry results by reframing the process as
           | gradient decent on differentiable point samples. This allowed
           | the research to stand on the shoulders of all the work being
           | put into deep learning tech.
        
             | IshKebab wrote:
             | This is like saying the car is nothing new because various
             | forms of wheeled transport have been around for centuries.
             | 
             | Typical HN.
        
       ___________________________________________________________________
       (page generated 2025-06-17 23:01 UTC)