The tech evolution train is on and its moving full steam ahead. AI is coming and it is gradually changing our world drastically, one step at a time. Microsoft has recently developed an AI that would draw entirely original images based on nothing more than text. You don't have to do anything other than type what you are thinking, and the system does the rest.
Already Researchers have developed it to the extent that it can come out with pretty accurate results if you feed it with well detailed information like like "a red bird with white background and a short beak". All this is achieved through the use of a Neural Network called an Attentional Generative Adversarial Network (AttnGAN).
This creates the image pixel by pixel, and just like an Human Painter, it can do both broad strokes and fine details, though in layers.
This is not just the only groundbreaking product that the Deep Learning Group at Microsoft has created. In short, this Drawing AI is the final part of a 3 part AI project being developed within the group. The others are a Caption Bot, which provides text descriptions for images and another which provides audio answers to questions about images.
They all use complex techniques like computer vision and natural language processing. The end goal is to teach machines how to understand humans and the world the same way we do. Xiaodong He, an AI research manager with the group, said in a Microsoft blog post: " it’s amazing to think we’re on the cusp of a world where, potentially, designers will rely solely on human imagination and artificial intelligence — not computer skills and software training".
Disclaimer: Comments and opinions expressed are solely the rights of the user and not a representation for TechSledge. Report