Niantic has announced It is building a new “large geospatial model” (LGM) that combines millions of scans taken from players' smartphones. pokemon go And other Niantic products. This AI model could allow computers and robots to understand and interact with the world in new ways, the company said in a blog post. Viewed by trash day,
LGM's “spatial intelligence” is built on neural networks developed as part of Niantic's visual positioning system. The blog post explains that “Over the past five years, Niantic has focused on building our Visual Positioning System (VPS), which uses a 3D map built from people scanning interesting locations to determine their position and orientation.” To do this uses an image from a phone. Our games and scaniverse,” and “This data is unique because it is taken from a pedestrian perspective and includes locations inaccessible to cars.”
Niantic's chief scientist Victor Prisakariu was more specific 2022 question and answersaying, “Our users like to use uploaded data when playing games Entry And pokemon goWe created high-fidelity 3D maps of the world that incorporate both 3D geometry (or the shape of things) and semantic understanding (what things are in the map, such as ground, sky, trees, etc.).
As 404 media Tells, there is no one to download pokemon go May predicted in 2016 that their data would “one day fuel this type of AI product.”