Hacker News Reader

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.

View on HN

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.

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.

The novelty here is that it does work on uncalibrated images.

Not really, it is using Mast3r to determine camera poses.

A lot of splats systems do work on uncalibrated images so that’s not novel either. They all just do a camera solve, which arguable isn’t terrible for a stereo pair with low divergence.

Reply on news.ycombinator.com