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

Show HN: Turning a Gaussian Splat into a videogame

blog.playcanvas.com

Post reply on HN
Print view View original

41–50 of 67 posts

Re: Show HN: Turning a Gaussian Splat into a videogame

#41

Post by make3 »

cyber_kinetist wrote: post #21
reactordev wrote: post #18

Earlier quoted context omitted.

There’s some movement in this area to be able to surface quantize the splats but you are right, right now it’s simply just visual language and isn’t useful in the pipeline.

Extracting a surface mesh is possible, but the result is going to be really ugly (like the high-poly meshes from generative AI that are useless to artists)! Mesh processing is a very difficult research domain in computer graphics that has been iterated for several decades, and we still don't have a good automated solution for retopology (Partly because the problem is hard to define in a mathematical way, but also sin…

With things like the latest dlss (extremely high quality run time .. reinterpretation), I wonder how precise mesh etc has to be now.

1. extract even a super approximate (meaning, like square edges, with some visual details) mesh from gen ai or a scan as a starting point,

2. move things around and define volumes for gameplay needs,

3. name things ("this is a Victorian house in a surprisingly good condition compared to the neighborhood it's in"), have human guided gen ai polish the things a bit more from the labels within the bounds of the gameplay required volumes,

4. let run time dlss fix the lighting etc from the rough geometry

Re: Show HN: Turning a Gaussian Splat into a videogame

#43

Post by zokier »

bane wrote: post #29

Question for those making Splats...how do you get such large environments? I've been playing around with them a bit and I'm finding I'm running out of memory with surprisingly little built even on an RTX6000. Any tips or ideas would be awesome!

I saw a comment by the author that they did it as 9 scans with Reality Capture which presumably then were combined with some post-processing.

Re: Show HN: Turning a Gaussian Splat into a videogame

#44

Post by jayd16 »

reactordev wrote: post #9
sev_verso wrote: post #2

Plays decently smooth on my M4 Max. It's probably still a long way from being a production-ready replacement for meshed environments, but I could imagine a hybrid mode where certain elements like grass and shrubbery are drawn with gaussians, perhaps with support for basic procedural animation. Great work with the playable demo!

For me, the biggest issue this solves is the blank canvas paralysis problem. Artists are visual thinkers and need a little nudge in the right (art) direction. This is a great way to fill that blank sheet of paper with something that they can take and run with.

I mean... Just take a source photo and over paint it? Splats don't really get you closer to a workable model than concept art.

Re: Show HN: Turning a Gaussian Splat into a videogame

#46

Post by yak32 »

andai wrote: post #34
sev_verso wrote: post #2

Plays decently smooth on my M4 Max. It's probably still a long way from being a production-ready replacement for meshed environments, but I could imagine a hybrid mode where certain elements like grass and shrubbery are drawn with gaussians, perhaps with support for basic procedural animation. Great work with the playable demo!

It runs kinda well on the best computer in the world, yeah? :) I have another data point: my ten year old ThinkPad. I get about 10 FPS. Lowering the quality doesn't seem to increase performance. But I am amazed by what I am seeing, and amazed it runs at all! I think it won't be long before the whole world is mapped, and "playable".

tbh I haven't yet approached optimisation for this, i am pretty sure it's possible to improve it further. It runs on my 2020 iphone, but not super smooth though

Re: Show HN: Turning a Gaussian Splat into a videogame

#47

Post by yak32 »

marlburrow wrote: post #36

Really cool. Out of curiosity, what's the per-frame cost of rendering the splat scene compared to an equivalent triangle-mesh approximation? I've been wondering when (if ever) splatting becomes the default for web-delivered 3D content vs. just a research/SIGGRAPH-paper toy. Browser support and file-size feel like the two big walls.

i think splats are good for browsers as it's just a render call with relatively simple shader - imagine modern traditional rendering pipeline, where it's thousands of different passes + post processing, shadows etc. Effective splat sorting is a different story in browsers though

Re: Show HN: Turning a Gaussian Splat into a videogame

#48

Post by yak32 »

fho wrote: post #37

"Back in the day" people were afraid that pupils would create CS (beta 6.5) maps of their schools. Gaussian Splatting would have been very convenient for that :-)

you would need a professional artist, several days and professional expensive equipment. It's not an easy task.
Post reply on HN