←back to thread

Niantic announces “Large Geospatial Model” trained on Pokémon Go player data

(nianticlabs.com)
383 points bookstore-romeo | 1 comments | 19 Nov 24 20:02 UTC | HN request time: 0s | source
Show context
krick ◴[21 Nov 24 02:10 UTC] No.42200358[source]▶
I still don't get what LGM is. From what I understood, it isn't actually about any "geospatial" data at all, is it? It is rather about improving some vision models to predict how the backside of a building looks, right? And training data isn't of people walking, but from images they've produced while catching pokemons or something?

P.S.: Also, if that's indeed what they mean, I wonder why having google street view data isn't enough for that.

replies(3): >>42200597 #>>42200944 #>>42201334 #
1. virodoran ◴[21 Nov 24 05:10 UTC] No.42201334[source]▶
> And training data isn't of people walking, but from images they've produced while catching pokemons or something?

Training data is people taking dedicated video of locations. Only ARCore supported devices can submit data as well. So I assume along with the video they're also collecting a good chunk of other data such as depth maps, accelerometer, gyrometer, magnetometer data, GPS, and more.