The neural network was taught to draw missing details on the photos of people.

Projects that are based on neural networks are not uncommon. They appear every day. Someone sorts cucumbers, someone paints pictures or composes fake news texts, but someone recovers the missing details in photos of people.

A new project, which, by the way, has already been posted on GutHub , allows you to restore parts that are missing from the photo for one reason or another. By the way, some of the details may be the “fantasy” of the program itself. For example, it is a haircut for a bald man, or a smile on a photo where it was not.

The basis of the project is the generative-competitive neural network SC-FEGAN. Networks of this type work in many similar (and not very projects). Usually they consist of two parts. This project is no exception. The first part is Unet-like, an image generator. The second is the discriminator SN-pachGAN. The generator creates images (which is logical), the discriminator cuts off the failed generations and "accepts" the decision that should appear in the photo.
')
The service works simply - the user needs to upload a photo of a person and create new image details. It can be hair, facial expressions, jewelry. If you wish, you can try to remove some details from the photo by changing the color of the hair or eyes along the way. As mentioned above, it is possible for a bald person to add hair, it all looks quite organic.

For only to use the service, you must follow the instructions of the developer. It is not so simple, but nothing super-complicated is required. Authors of the development plan to make it part of any commercial applications, including mobile software or web services.