Fast Bi layer Neural Synthesis of One Shot Realistic Head Avatars

We propose a neural renderingbased system that creates head avatars from a single photograph. Our approach models a person s appearance by decomposing it into two layers. The first layer is a posedependent coarse image that is synthesized by a small neural network. The second layer is defined by a poseindependent texture image that contains highfrequency details. The texture image is generated offline, warped, and added to the coarse image to ensure a high effective resolution of synthesized head views.