Computer technology has come a long way in 20 years. Hollywood special effects that once cost millions to produce can now be recreated with a standard camera.

According to Science, artificial intelligence can now recreate a full 3D model of a human being based on just seconds of video. The effect, as seen below, once required dozens of programmers recreating the person in painstaking detail.

Granted, the resulting graphic “human” barely rival that of the most state-of-the-art in the 1990’s, but that a computer can recreate such an image in just seconds is an astounding achievement. (video below) Such effects typically required a special camera to “detect depth or to view someone from multiple angles,” but that requirement is now rendered moot, thanks to a new algorithm allowing for the image to render completely from just one angle.

Science has more: The system has three stages. First, it analyzes a video a few seconds long of someone moving—preferably turning 360° to show all sides—and for each frame creates a silhouette separating the person from the background.

Based on machine learning techniques—in which computers learn a task from many examples—it roughly estimates the 3D body shape and location of joints. In the second stage, it ‘unposes’ the virtual human created from each frame, making them all stand with arms out in a T shape, and combines information about the T-posed people into one, more accurate model. Read more from…

thumbnail courtesy of