Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Real-Time Gaussian Splatting

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 61 posts

Re: Show HN: Real-Time Gaussian Splatting

#41

Post by markisus »

badmonster wrote: post #40

What is the expected frame rate and latency when running on a typical setup with one Realsense camera and an RTX 3060?

I don't have a 3060 at hand so I'm not sure. Ideally someone with that setup will try it out and report back. There is no noticeable latency when comparing visually with standard pointcloud rendering.

With framerate, there are two different frame rates that are important. One is the splat construction framerate, which the speed that an entirely new set of Gaussian's can be constructed. LiveSplat can usually maintain 30fps in this case.

The second important splat rendering framerate. In VR this is important to prevent motion sickness. Even if you have a static set of splats, you need the rendering to react to the user's minor head movements at around 90fps for the best in-headset experience.

All these figures are on my setup with a 4090 but I have gotten close results with a 3080 (maybe 70fps splat rendering instead of 90fps).

Re: Show HN: Real-Time Gaussian Splatting

#42

Post by _verandaguy »

markisus wrote: post #13
_verandaguy wrote: post #7

Earlier quoted context omitted.

I know enough about 3D rendering to know that Gaussian splatting's one of the Big New Things in high-performance rendering, so I understand that this is a big deal -- but I can't quantify why, or how big a deal it is. Could you or someone else wise in the ways of graphics give me a layperson's rundown of how this works, why it's considered so important, and what the technical challenges are given that an RGB+D(epth?)…

Gaussian Splatting allows you to create a photorealistic representation of an environment from just a collection of images. Philosophically, this is a form of geometric scene understanding from raw pixels, which has been a holy grail of computer vision since the beginning. Usually creating a Gaussian splat representation takes a long time and uses an iterative gradient-based optimization procedure. Using RGBD helps m…

Thanks! That makes a lot of sense, I might dig into this after work some more.

By "big deal," I meant more for people specializing around computer graphics, computer vision, or even narrower subfields of either of those two -- a big deal from an academic interest perspective.

Sure, this might also have implications in society and business, but I'm a nerd, and I appreciate a good nerding out over something cool, niche, and technically impressive.

Re: Show HN: Real-Time Gaussian Splatting

#43

Post by smusamashah »

The demo video does not show constructing 3d from input. Is it possible to do something like that with this? Take a continus feed of a static scene and keep improving the 3D view?

This is what I thought from the title, but the demo video is just a conitnuously changing stream of points/splats with the video.

Re: Show HN: Real-Time Gaussian Splatting

#44

Post by dang »

kookamamie wrote: post #29

[flagged]

Whoa—please don't be a jerk on HN and especially not when discussing other people's work.

You broke the site guidelines badly here (https://news.ycombinator.com/newsguidelines.html), and the Show HN guidelines even more so (https://news.ycombinator.com/showhn.html).

If you wouldn't mind reviewing those links and sticking to the rules when posting to HN, we'd appreciate it.

Re: Show HN: Real-Time Gaussian Splatting

#46

Post by drewbeck »

imo this is a key component of a successful VR future for live events. Many cameras at a venue, viewers strap on a headset at home and get to sit/stand anywhere in the room and see the show.

Also I love the example video. Folks could make some killer music videos with this tech.

Re: Show HN: Real-Time Gaussian Splatting

#47

Post by markisus »

smusamashah wrote: post #43

The demo video does not show constructing 3d from input. Is it possible to do something like that with this? Take a continus feed of a static scene and keep improving the 3D view? This is what I thought from the title, but the demo video is just a conitnuously changing stream of points/splats with the video.

If the scene is static, the normal Gaussian splatting pipeline will give much better results. You take a bunch of photos and then let the optimizer run for a while to create the scene.
Post reply on HN