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

Turn a single image into a navigable 3D Gaussian Splat with depth

lab.revelium.studio

Post reply on HN
Print view View original

11–20 of 43 posts

Re: Turn a single image into a navigable 3D Gaussian Splat with depth

#11

Post by riotnrrd »

Johnny_Bonk wrote: post #8

Cool, is there a way to upload several photos of a room from different angles to fuse it all together? Is there an api?

That's a pretty well-solved problem at this point, if you want to do it yourself. You'll want some kind of NeRF tool and a way to calculate the camera poses of the photos you took. COLMAP is the tool most people use for the latter.

I'd recommend trying Instant Neural Graphics Primitives (https://github.com/NVlabs/instant-ngp) from NVIDIA. It's a couple years old, so not state-of-the-art, but it runs on just about anything and is extremely fast.

Re: Turn a single image into a navigable 3D Gaussian Splat with depth

#17

Post by shermantanktop »

causal wrote: post #4
xnx wrote: post #3

Or one-click install on your own device: https://pinokio.co/item.html?uri=https%3A%2F%2Fgithub.com%2F...

What is Pinokio? The website just says "Your PC is the Cloud" - what?

Not sure I would name a product after a legendary liar...

But sure, click that download link, what's the worst that could happen? Get turned into a donkey and swallowed by a whale?

Re: Turn a single image into a navigable 3D Gaussian Splat with depth

#18

Post by smusamashah »

If this model is so good at estimating depth from single image, shouldn't it also be able to take multiple images as input and estimate even better? But searching a bit it looks like this is supposed to be a single image to 3D only. I don't understand why it does not (can not?) work with multiple images.

Re: Turn a single image into a navigable 3D Gaussian Splat with depth

#19

Post by voodooEntity »

Its funny, always stucks on 90% till it fails with the error that another big image may be keeping the server busy.

I mean ok its a "demo" tho the funny thing is if you actually check the cli and requests, you clearly can see that the 3 stages the images walks through on "processing" are fake, its just doing 1 post request in the backend that runs while it traverses through the states, and at 90% it stops until (in theory) the request ends.

Re: Turn a single image into a navigable 3D Gaussian Splat with depth

#20

Post by shrinks99 »

smusamashah wrote: post #18

If this model is so good at estimating depth from single image, shouldn't it also be able to take multiple images as input and estimate even better? But searching a bit it looks like this is supposed to be a single image to 3D only. I don't understand why it does not (can not?) work with multiple images.

I'm going to guess this is because the image to depth data, while good, is not perfectly accurate and therefore cannot be a shared ground truth between multiple images. At that point what you want is a more traditional structure from motion workflow, which already exists and does a decent job.
Post reply on HN