GANs are really the biggest innovation that happened to ML in recent years and we're just scratching the surface of what is possible.
But I do have one concern: since images are very powerful, generated images could be used in a manipulative way. If you think about it, it is already possible to manipulate and fake images via Photoshop and the like, but also there GANs could open totally new possibilities.
Yes, it's application in cinema and video games will deliver more life-like images. They can create an artificial actor using this technique. For gaming, the characters will evolve with more realistic looking faces and features, and based on generated images. That way they don't even have to hire an actor.
Downvoting a post can decrease pending rewards and make it less visible. Common reasons:
Submit