Avatar-based video encoding

A system comprising:

• a video device configured to record video;
• an imaging and audio framework module configured to receive and interpret video input from the video device;
• a face detection module operatively coupled with the imaging and audio framework module and configured to detect a face within the video input and to track changes in facial characteristics of the detected face, wherein the face detection module is further configured to track changes in facial characteristics at least in part by categorizing a first movement of the face as a head rigid movement, categorizing a second movement of the face as a facial expression movement, and processing the second movement as a facial expression in response to categorizing the second movement;
• an avatar database having one or more avatars stored therein, including at least one avatar provided by an avatar model constructed from the detected face;
• and
• an avatar control module configured to animate a selected avatar using changes in facial characteristics of the detected face, as tracked by the face detection module, in reconstruction of the video as an avatar-based video.

A system comprising:

• a mobile computing device configured to:
• record a video;
• detect a face within the video;
• track changes in facial characteristics of the detected face;
• and
• reconstruct the recorded video as an avatar-based video using an avatar that is animated using the tracked changes in facial characteristics of the detected face, wherein to reconstruct comprises to categorize a first movement of the user in the recorded video as a head rigid movement, to categorize a second movement of the user in the recorded video as a facial expression movement, and to process the second movement as a facial expression in response to categorizing the second movement;
• and
• an avatar database having one or more avatars stored therein, including at least one avatar provided by an avatar model constructed from the detected face.