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 6 hours ago [-]
Any word if Faro is working on anything like Leica's Powerlock for laser trackers?
reactordev 4 hours ago [-]
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.
jauntywundrkind 11 hours ago [-]
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.
ge96 9 hours ago [-]
Why am I seeing "splatting" more often recently thought it was old tech
hirako2000 9 hours ago [-]
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.
nomel 9 hours ago [-]
Most tech is "old", with new use cases and accessibility. I think it's most interesting when it jumps into my pocket.
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 5 hours ago [-]
This is like saying the car is nothing new because various forms of wheeled transport have been around for centuries.
Typical HN.
corysama 34 minutes ago [-]
I think you are reading this much more negatively than I wrote it. I’m very excited about the new research coming out every day on GS.
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.
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.
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.
Typical HN.
https://x.com/janusch_patas publishes a steady stream of it every day on X and at https://radiancefields.com/