Dynamic transition from video to personalized photorealistic facial representations in digital communications

A computing system, comprising:

• a memory;
• and
• one or more processor devices coupled to the memory configured to:
• receive, from a computing device, video data that depicts a face of a particular user associated with the computing device;
• determine that the computing device has ceased transmission of video data responsive to a network performance metric associated with a network connection of the computing device;
• receive, from the computing device, motion capture information indicative of facial motion of the face of the particular user of the computing device, wherein the motion capture information is derived by the computing device from video data that depicts the facial motion of the face of the particular user;
• and
• generate second video data that depicts a photorealistic three-dimensional representation of the face of the particular user, wherein the photorealistic three-dimensional representation of the face of the particular user is animated to perform the facial motion based on the motion capture information.

A non-transitory computer-readable storage medium that includes executable instructions configured to cause one or more processor devices of a computing device to:

• obtain video data that depicts a facial motion of a face of a particular user of the computing device;
• make a determination that a network performance metric for a network connection of the computing device is less than a threshold network performance metric;
• responsive to the determination, determine motion capture information based on the video data, wherein the motion capture information is indicative of the facial motion of the face of the particular user;
• and
• transmit the motion capture information to the computing system for animation of a photorealistic three-dimensional representation of the face of the particular user.

A computing device, comprising:

• a memory;
• and
• one or more processor devices coupled to the memory configured to:
• obtain video data that depicts a facial motion of a face of a particular user of the computing device;
• make a determination that a network performance metric for a network connection of the computing device is less than a threshold network performance metric;
• responsive to the determination, determine motion capture information based on the video data, wherein the motion capture information is indicative of the facial motion of the face of the particular user;
• and
• transmit the motion capture information to a computing system for animation of a photorealistic three-dimensional representation of the face of the particular user.

A method, comprising:

• receiving, by a computing system comprising one or more processor devices from a computing device, video data that depicts a face of a particular user associated with the computing device;
• determining, by the computing system, that the computing device has ceased transmission of video data responsive to a network performance metric associated with a network connection of the computing device;
• receiving, by the computing system from the computing device, motion capture information indicative of facial motion of the face of the particular user of the computing device, wherein the motion capture information is derived by the computing device from video data that depicts the facial motion of the face of the particular user;
• and
• generating, by the computing system, second video data that depicts a photorealistic three-dimensional representation of the face of the particular user, wherein the photorealistic three-dimensional representation of the face of the particular user is animated to perform the facial motion based on the motion capture information.

A non-transitory computer-readable storage medium that includes executable instructions configured to cause one or more processor devices of a computing system to:

• receive, from a computing device, video data that depicts a face of a particular user associated with the computing device;
• determine that the computing device has ceased transmission of video data responsive to a network performance metric associated with a network connection of the computing device;
• receive, from the computing device, motion capture information indicative of facial motion of the face of the particular user of the computing device, wherein the motion capture information is derived by the computing device from video data that depicts the facial motion of the face of the particular user;
• and
• generate second video data that depicts a photorealistic three-dimensional representation of the face of the particular user, wherein the photorealistic three-dimensional representation of the face of the particular user is animated to perform the facial motion based on the motion capture information.