A team of teachers from the University of Washington has developed a new algorithm for transforming two-dimensional static images into three-dimensional moving models. The source material is the photographs that the “Photo Wake-Up” technology makes “come to life”, in front of the viewer, leave the frame and start performing different movements in the surrounding world. Development will certainly be a breakthrough in the field of augmented reality.

To work, the algorithm needs a picture in which you can more or less clearly highlight the object of animation. It is not so important whether it is a real photo, a children's doodle, a frame from an anime or even a Picasso canvas, the main thing is the presence of a humanoid object. The algorithm recognizes parts of the body, isolates them from the overall composition, based on proportions, models the 3D skeleton and mounts for it a 2D texture, copying the original drawing.

Further, with such a model, you can perform arbitrary procedures, for example, give the command to run to another picture in the gallery and switch places with the character from there. It looks like magic or, more precisely, as a bright and visual application of augmented reality technology. Unlike its predecessors, the authors of this algorithm managed to achieve unprecedented accuracy in recognizing and copying parts of the original image. And so the viewer easily believes in the illusion.

techcult.ru