←back to thread

145 points jasondavies | 2 comments | | HN request time: 0s | source
Show context
S0y ◴[] No.41368437[source]
This is really awesome. A question for someone who knows more about this: How much harder would it be to make this work using any number of photos? I'm assuming this is the end goal for a model like this.

Imagine being able to create an accurate enough 3D rendering of any interior with just a bunch of snapshots anyone can take with their phone.

replies(2): >>41368608 #>>41368627 #
dagmx ◴[] No.41368608[source]
That’s already how Gaussian splats work.

They’re novelty of splattr (though I contest that they’re the first to do so) is that they need fewer images than usual.

replies(2): >>41368661 #>>41368790 #
1. Arkanum ◴[] No.41368661[source]
I think the novelty is that they don't have to optimise the splats at all, they're directly predicted in a single forward pass.
replies(1): >>41372531 #
2. dagmx ◴[] No.41372531[source]
That’s not really novel either imho, though google search is escaping me on the specific papers I saw at siggraph.

Imho it’s an interesting combination of technologies but not novel in an off itself.