This site may earn affiliate commissions from the links on this page. Terms of employ.

mirror

Google has invested heavily in artificial intelligence to ability products like Google Photos and Google Banana. These applications are impressive in their ain right, but they're not exactly "fun." Google has just rolled out a new AI experiment that is geared entirely toward fun. The new Mirror Move experiment can place your pose and friction match information technology to more than 80,000 images of other people to show you someone in a similar stance. Why? So you can brand GIFs, of course.

While this specific Google experiment doesn't accept a practical apply, it's a tour de force of technology buzzwords. Mirror Move utilizes AI, car learning, neural networks, augmented reality, and more. You lot can effort information technology right now equally long as your estimator has a webcam. Just head over to the Motion Mirror site linked to a higher place and grant the folio access to your camera to get started.

Mirror Move works best if you stand far enough abroad from your computer that all your joints are in the frame. It'south as well limited to a unmarried person at a time. Equally you move, the AI scans your body and estimates where your joints are. Information technology then matches your poses to a catalog of 80,000 photos of people. So, your live camera feed is on ane side of the screen, and Mirror Move populates the other with matching pictures in real time. Y'all can even create a GIF of this process to share on the internet.

This is all just for fun, simply the engineering science behind Mirror Motility could accept many applications. Google calls it PoseNet, and you tin learn more about the details in a Medium post from before this yr. Like many Google technologies, PoseNet is powered by a convolutional neural network. The camera feed gets piped into the network, which identifies people and maps 17 tracking points on the image. The network matches those points to its catalog of lxxx,000 images, and yous get the output.

PoseNet works in both single-person and multiple person detection modes. At that place's a separate demo that shows how well this works, but all you get is the 17-point detection wireframe. Mirror Move is an implementation of the single-person version because information technology'south faster and the image library consists of individual people.

PoseNet could eventually find use in games, fitness tracking, and fifty-fifty interactive art installations. This is not a tool for recognizing who people are, so information technology's less of a privacy business organization than tools that can recognize and recollect faces.