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 66 days ago [-]
Any word if Faro is working on anything like Leica's Powerlock for laser trackers?
reactordev 66 days 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 66 days 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 66 days ago [-]
Why am I seeing "splatting" more often recently thought it was old tech
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 66 days ago [-]
This is like saying the car is nothing new because various forms of wheeled transport have been around for centuries.
Typical HN.
corysama 66 days 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.
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.
boulos 66 days ago [-]
You're not wrong.
The early 2000s splatting from point-based rendering is what George Drettakis and his students realized could be applied in this new NeRF domain.
Basically, all the reasons that point splats didn't work for regular surface rendering nearly 25 years ago (holes, inefficient, can't edit them like meshes) are less of an issue in a light field capture setup.
nomel 66 days ago [-]
Most tech is "old", with new use cases and accessibility. I think it's most interesting when it jumps into my pocket.
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.
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/
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.
The early 2000s splatting from point-based rendering is what George Drettakis and his students realized could be applied in this new NeRF domain.
Basically, all the reasons that point splats didn't work for regular surface rendering nearly 25 years ago (holes, inefficient, can't edit them like meshes) are less of an issue in a light field capture setup.
>This site was suspended as it reached the limits of the Free plan