IST Lunch Bunch

The age of social media and immersive technologies has created a growing need for processing detailed visual representations of ourselves.  With recent advancements in graphics, we can now generate highly realistic digital characters for games, movies, and virtual reality. However, creating compelling digital content is still associated with a complex and manual workflow.  While cutting-edge computer vision algorithms can detect and recognize humans reliably, obtaining functional digital models and their animations automatically still remains beyond reach.  Such models are not only visually pleasing but would also bring semantical structure into the captured data, enabling new possibilities such as intuitive data manipulation and machine perception.  With the democratization of 3D sensors, many difficult vision problems can be turned into geometric ones, where effective data-driven solutions exist.  My research aims at pushing the boundaries of data-driven digitization of humans and developing frameworks that are accessible to anyone.  Such system should be fully unobtrusive and operate in fully unconstrained environments.  With these goals in mind, I will showcase several highlights of our current research efforts from dynamic shape reconstruction, human body scanning, facial capture, and the digitization of human hair.  By the end of this decade, our homes will be equipped with 3D sensors that digitally monitor our actions, habits, and health.  These advances will help machines understand our appearances and movements, revolutionizing the way we interact with computers, and developing new forms of live communication through compelling virtual avatars.