HeadOn: Real-time Reenactment of Human Portrait Videos
This addresses the need for flexible and realistic video reenactment in applications like entertainment or virtual communication, though it appears incremental by building on existing parametric models and rendering techniques.
The authors tackled the problem of real-time source-to-target reenactment of human portrait videos, enabling transfer of torso and head motion, face expression, and eye gaze, and achieved photo-realistic imagery with significant improvements in flexibility for creating realistic output videos.
We propose HeadOn, the first real-time source-to-target reenactment approach for complete human portrait videos that enables transfer of torso and head motion, face expression, and eye gaze. Given a short RGB-D video of the target actor, we automatically construct a personalized geometry proxy that embeds a parametric head, eye, and kinematic torso model. A novel real-time reenactment algorithm employs this proxy to photo-realistically map the captured motion from the source actor to the target actor. On top of the coarse geometric proxy, we propose a video-based rendering technique that composites the modified target portrait video via view- and pose-dependent texturing, and creates photo-realistic imagery of the target actor under novel torso and head poses, facial expressions, and gaze directions. To this end, we propose a robust tracking of the face and torso of the source actor. We extensively evaluate our approach and show significant improvements in enabling much greater flexibility in creating realistic reenacted output videos.