Published 18:22 IST, December 24th 2018
Moving photographs from Harry Potter novels may not be far from reality, thanks to AI
Harry Potter moving photographs to be a reality: Thanks to Chung-Yi Weng and the team at the University of Washington in Seattle. They have built an AI-powered software called Photo Wake-Up. It can create 3D animations from still images.
Advertisement
In what could be exciting news for Harry Potter fans out re, those magical, moving photos in J.K.Rowling's vels may t be far from reality. Magical photos in magical world of Hogwarts School of Witchcraft and Wizardry are perfectly rmal except that characters in those photos smile, wave and some cases, disappear. Those things must be imaginary for ordinary muggles, isn’t it? Well, t anymore.
Thanks to Chung-Yi Weng and team at University of Washington in Seattle. y have built an AI-powered software called Photo Wake-Up. It can create 3D animations from still ims. In a nutshell, articulating a 3D human pose from a 2D im is t easy for machine vision and deep-learning algorithms. Experts and computer science teams across world have often faced difficulties in this area in past.
Advertisement
To deal with Human Pose Estimation, Weng and team use SMPL, a program developed by Microsoft in association with Max Planck Institute for Intelligent Systems in Germany. In this process, a 3D skeleton is superimposed on a 2D cutout of a human body. sense of movement is created using animation, which essentially solves problem of pose estimation to some extent.
Advertisement
It can handle simple movements if t complex ones due to certain limitations. Still, this process cant create a realistic animation. That’s where Weng and team come into picture. ir main focus is to tweak 2D cutouts in such a way that produces realistic 3D animations. ir focus remains on he, right arm, right leg, left arm, left leg, and torso.
Advertisement
Here is what Weng and team have to say:
“We believe method t only enables new ways for people to enjoy and interact with photos, but also suggests a pathway to reconstructing a virtual avatar from a single im while providing insight into state of art of human modelling from a single photo.”
Advertisement
18:19 IST, December 24th 2018