Hacker News new | past | comments | ask | show | jobs | submit
wartywhoa23 | on: Pokémon Go Scans Trained the Navigation Tech for Military Drones
Well if such a conspiracy crackhead like me somehow happened to reach ranks of Niantic team, I'd totally make sure that there is a decoy "huge data upload point with explicit consent" to shift focus from covert data channels that slowly transmit all else using some custom image compression, maybe just some very small fraction of original data that by the mass nature of acquisition would mathematically still reconstruct the original data, or the fraction of that data that is enough to build a world model.
BoppreH | parent
Videos are inherently large. There are better compression algorithms than what phone cameras generate by default, but video reencoding is slow, and the results still too large for "covert data channels".

Normal players would have noticed the bandwidth and CPU usage, and volunteers have already agreed to data sharing, so there's no point in keeping secrets. Same as claims that the Facebook app listens to people talk: someone would have caught it by now.

Also, AR capture was never very popular, mostly a gimmick for new players. The game was already a battery and power hog even without it.

wartywhoa23 | root | parent
Why videos though? Photogrammetry is about still images. You don't need ALL angles of a target from a single user. Other users pile the needed data up, guided by their own pokemon locations.
5- | root | parent | next
and photogrammetry from crowd-sourced disparate still images was the biggest, flashiest "public" display of the technology: https://www.ted.com/talks/blaise_aguera_y_arcas_how_photosyn...
BoppreH | root | parent
Good point, maybe that could be done. But that's not what TFA is about, so you're not vindicated yet.
skew-aberration | root | parent
Yeah and for niantic to achieve good photogrammetry with their random collection of photos taken from different angles, on different days, etc they would need some kind of ground truth to train on, which is implausible. You'd need to collect a parallel dataset of high-quality videos for traditional photogrammetry and .. hang on.
wartywhoa23 | root | parent | next
I don't understand why you insist on videos.

I was able to create a full 3d model of my window plant almost free of obscured areas from a few dozens still photos taken all around it, back in 2018, using the Capturing Reality photogrammetry app on a mobile i7-3610QM CPU with 8Gb RAM, in about 40-60 minutes.

And that's pretty mundane general public software, do we know for sure which algorithms are used by Niantic?

mschuster91 | root | parent
> and for niantic to achieve good photogrammetry with their random collection of photos taken from different angles, on different days, etc they would need some kind of ground truth to train on, which is implausible.

I'd say... the versatility of photos provides the "ground truth" on its own when combined to one single dataset. Say you want to program a guided drone shooting through urban areas, you want it to work under all sorts of conditions - day, night, rain, snow, the sun visible from all possible angles and throwing shadows.

A dataset that you can get from something like Street View? You can at best generate that once a year at enormous expense. Still valuable because a Street View car likely has a multitude of highest-quality GNSS receivers and possibly RTK navigation aids, but to make the dataset usable for 24/7/365 navigation you absolutely need a huge, huge amount of backfill.