The Pros and Cons of Image Simulation in Remote Sensing

In order to train deep learning algorithms, we need lots of data. GANS and this kind of generative models can generate realistic data that you can use to train your deep learning algorithms for remote sensing. This is a very interesting application, of course. We want to make measurements of the Earth have that be as close as possible to the reality. And perhaps a use case for things like super resolution, for GANS, for plausible images as society are using synthetic data as training data.

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app