DeepFaceDrawing AI Turns Simple Sketches Into Detailed Photo (Video)

Researchers have invented a way to turn simple sketches into photo-realistic facial images with a DeepFaceDrawing app. Developed by an innovative team at the Chinese Academy of Sciences in Beijing, DeepFaceDrawing uses artificial intelligence (AI) to help “users with little training in drawing to produce high-quality images from rough or even incomplete freehand sketches.”

YOU MAY ALSO LIKE: Facebook Issues New Rules To Group Admins For Discussing Racism

But this isn’t the first time we’re seeing this type of tech, remember the horrifying results of Pix2Pix’s autofill tool, but this one is the most advanced you can find around, and it doesn’t require the same level of detail in source sketches as previous iterations have.

This invention works mainly via probability, for example, instead of requiring detailed eyelid or lip shapes, the software refers to a database of faces and facial components and considers how each facial element works with each other, like eyes, nose, mouth, face shape, and hair type and they’re considered separately and then it assembled them all into a single image.

According to the paper, “Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge maps as input.

“To address this issue, our key idea is to implicitly model the shape space of plausible face images and synthesize a face image in this space to approximate an input sketch. Our method essentially uses input sketches as soft constraints and is thus able to produce high-quality face images even from rough and/or incomplete sketches.”

YOU MAY ALSO LIKE: Sony Latest AR App Will Show If A New TV Will Fit Your Room

There was no clue as to how the software will handle race issues. Of the 17,000 sketches and their corresponding photos created so far, most of them have been Caucasian and South American faces.

The technology will be going on show at this year’s virtual SIGGRAPH conference in July. According to the project’s website, code for the software is also “coming soon,” which means we may see its application in the wild next month.

This will not only act as a fun app to play around with but will also potentially help law enforcement, as they will use it to quickly generate images of suspects.