Scientists to Create Deepfakes for Dancing

With help of artificial intelligence, fake dancing videos can now be created
28 August 2018   1804

Four scientists from the University of California at Berkeley developed an algorithm that creates on the basis of a video with a dance a fake record on which another person performs the same movements. For deep processing, it requires a twenty-minute shooting at 120 frames per second.

The technology is based on an algorithm on generative-competitive neural networks. A separate subroutine processes pre-recorded video (source and target) and imposes motions on a simple figure - the frame of the human body.

AI Dancing
AI Dancing
AI Dancing
AI Dancing
 

Then the algorithm transfers professional movements to the record of amateur dance and "aligns" the final video so that the figure does not strongly "jerk" from frame to frame and the person was where he was supposed to.

Researchers admit that the synthesized video looks realistic though it is not devoid of artifacts: body parts sometimes tremble or even disappear, and some frames look blurred. In addition, the algorithm does not know how to handle the behavior of the tissue when a person moves, so people on the target video wear tight clothing that almost does not form wrinkles.

This type of video processing is called a "deep fake". In mid-August, 2018, experts from the Carnegie Mellon University presented Recycle-GAN, which is capable of recreating the facial expressions of one person on the face of another, modeling the blossoming of the flower and changing the weather on video recordings. A similar result is provided by the application FakeApp, released in January 2018, as well as the algorithms Face2Face and HeadOn.

Google to Release Teachable Machine 2.0

Teachable Machines 2.0 is a platform where neural networks can be trained without programming
11 November 2019   169

Learning machine learning is now easier than ever. Google is ready to help with this: the company introduced the Teachable Machine 2.0 platform. This is a site where neural networks can be trained in a couple of clicks.

A camera and microphone are enough to make datasets with video or audio recordings on which the neuron network will be trained. You do not need to write code at all. The interface is extremely simple: one button for recording data, another for training the model. If the result does not suit you, you can delve into the advanced settings or refine the data. You can export your achievements to the application, to a third-party site, to your device, or to Google Drive.

The project has a first version. It allowed training neural networks based on images and did not support the export of models. Teachable Machine was used to familiarize students with AI, as well as to develop useful functional tools, for example, applications that help people with speech impairments communicate.

Give it a try now!