We are scaling a 3D map of the world with drones and dashcams

Everything looks like Tim Burtons bizzaroworld. Same problems as streetview : https://news.ycombinator.com/item?id=24324813#24326803

"Look at 'NY 41 central park west' train wreck. You have >20 good photos to work with, but the end result doesnt even maintain straight windows. Balconies look like Lara Croft breast from first Tomb Raider, not to mention they are all different geometry despite high quality source material showing them being all the same shape. The best data saving option would probably be no additional geometry at all, just a texture."

Now compare to https://i0.wp.com/syncedreview.com/wp-content/uploads/2020/1... from https://syncedreview.com/2020/10/19/google-open-sources-3d-s... Models this is producing are generations ahead of the current glitchy mess.

That sounds cool, trying to think how that works(looks like single camera so not stereo) also I guess assuming you have onboard speed and then trace frames... make the depth?

Oh I guess you could have known 3d shapes, drive a camera towards it/get measurements, train something maybe.

> After uploading video for the tile, the collector earns a financial reward and their username is displayed on the tile

Nice, could people use their phones through an app? That would probably be slow though walking.

To create a fresh and intelligent 3D map of the world, Hivemapper combines a new software approach to making maps, with a mapping network of commodity drones and dashcam to grow and update the map. The global 3D map we are building is scaling and updating four times faster, and at a fraction of the cost, of traditional mapping companies.