After a bit of research, Newman realized that Bing Maps’ data set essentially covers the entire planet. The only problem? It was all in 2D. After using some of that data to create a flyable 3D version of Seattle, Newman turned to the Azure team to create a machine learning method to transform the entire planet into a giant 3D model.
“AI has grown tremendously over the last few years,” Eric Boyd, CVP of Azure AI, said in an interview. Spectacular where you can come up with algorithms that look now. Use it to identify literally every tree, grass and water, every square kilometer of the earth, and then create 3D models. “
The unification of the Azores is beyond the shape of the world. It also powers flight controller sounds using AI speech generation technology, which sounds almost indistinguishable from humans. It is so natural that many players believe that micro .ft relies solely on voice actors.
Since the company began exploring ways to bring the Azure AI into the game in 2016, Byrd believes machine learning capabilities have also evolved dramatically. “The scope of the AI algorithm has really grown over the last several years,” he said. “And so the vision algorithms, which are heavily used to identify and categorize all these different trees and buildings, have come a long way.”
Since it leans very high on the cloud, Flight simulator Trust is a “live game” in the sense, Newman said. All machine learning algorithms, which depend on the game, will gradually improve over time, as the company eliminates errors and optimizes the engine. (And become more aware of potential issues, such as Typo who built a 212-story tower in Melbourne.) But he points out that algorithms can only be as good as source data, so Microsoft is working hard to improve it. . .
