Hacker News new | ask | show | jobs
by KaiserPro 18 days ago
> Could I use GS to render my living room as a digital playground to train my vision models in?

Yes, its what the autonomous car people are doing.

However you might want to do photogrammetry first (https://github.com/alicevision/meshroom opensource) as that produces a mesh which you can use to detect collisions easier. The downside is that transparent objects render really badly. but it is a lot faster to render

1 comments

Ehhh if it's just for looking and you don't have anything lidar just go for splats they're way better behaved, mostly because they don't need to understand a concept of "surface" they just understand "splat with spherical harmonics of view-dependant color".
true, for visual only stuff they do work really well.