In Brief A new image generator created as part of the pix2pix project can transform a crude doodle of a face into a more realistic looking image. It's powered by a next-level machine learning technique called generative adversarial networks, which could help us create machines that have a better understanding of the world. Ugly Doodles <\/p>\n
Machine learning is, perhaps, the most common platform for existing artificial intelligence (AI) networks. The basic idea is that an AI can be taught to reach its own decisions throughexposure to usually huge datasets. Its similar to how we canlearn something by seeing it again and again. <\/p>\n
While machine learning does an almost perfect job of classifying images, it seems to fumble a bit with generating them. The latest example is an image generator shared as part of the pix2pix project. Itsrecently been making the rounds on social media, sowe tried it out, and heres the result: <\/p>\n<\/p>\n
The end results of the generator are either abstract or hideous, depending on your perspective. But it is undeniably able toturn a simple and arguably poor doodle into afar more realistic-looking image. <\/p>\n
Like so much of the internet, the pix2pix projectstarted with cats. The same mechanics applied: a user drew an image, and the algorithm transformedit into a (relatively) more realistic-looking cat. <\/p>\n
For their generators, the developers used a next-generation machine learning technique called generative adversarial networks (GANs). Essentially, the system determines whether its own generated output (in this case, the realistic face) is real (looks like one of the images of actual faces from the dataset used to train it) or fake. If the answer is fake, it then repeats the generation process until an outputted image passes for a real one. <\/p>\n
The pix2pix projects image generator is able to take the random doodles and pick out the facial features it recognizes using a machine learning model. Granted, the images the system currently generates arent perfect, but a person could look at them and recognize an attempt at a human face. <\/p>\n
Obviously, the system will require more training to generate picture perfect images, but the transition from cats to human facesreveals an already considerable improvement. Eventually, generative networks could be usedto create realistic-looking images or even videos from crude input. They could pave the way for computers that better understand the real world and how to contribute to it. <\/p>\n
<\/p>\n
Read this article:<\/p>\n
Draw a Doodle of a Face, and Watch This AI Image Generator Make It Look More Human - Futurism<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" In Brief A new image generator created as part of the pix2pix project can transform a crude doodle of a face into a more realistic looking image. It's powered by a next-level machine learning technique called generative adversarial networks, which could help us create machines that have a better understanding of the world Continue reading