公开(公告)号：US12056803B2

公开(公告)日：2024-08-06

申请号：US17849955

申请日：2022-06-27

Applicant: Verizon Patent and Licensing Inc.

Inventor： Harish Narayan ,  Sourabh Khire ,  Gaurav Rihan ,  Sayali G. Salvi ,  Omkar Ghodke ,  Ashish Nagpal

IPC: G06T13/40 ,  H04L12/18 ,  H04N7/15

CPC classification number: G06T13/40 ,  H04L12/1822 ,  H04N7/15

Abstract: An exemplary method includes processing, by a virtual avatar processing system, a plurality of video conference recordings generated by a video conference platform to select user image information associated with a plurality of users that participated in video conference sessions represented in the plurality of video conference recordings. The exemplary method further includes generating, based on the user image information, a template model that is generic to a plurality of users, selecting, from the user image information and based on predefined selection criteria, video frames that depict a user included in the plurality of users, and generating a virtual avatar model of the user by applying the selected video frames to the template model. A visual representation of the virtual avatar model may be configured to be used in future video conference sessions in place of a live video image of the user.

公开(公告)号：US20230419580A1

公开(公告)日：2023-12-28

申请号：US17849955

申请日：2022-06-27

Applicant: Verizon Patent and Licensing Inc.

Inventor： Harish Narayan ,  Sourabh Khire ,  Gaurav Rihan ,  Sayali G. Salvi ,  Omkar Ghodke ,  Ashish Nagpal

IPC: G06T13/40 ,  H04L12/18 ,  H04N7/15

CPC classification number: G06T13/40 ,  H04L12/1822 ,  H04N7/15

Abstract: An exemplary method includes processing, by a virtual avatar processing system, a plurality of video conference recordings generated by a video conference platform to select user image information associated with a plurality of users that participated in video conference sessions represented in the plurality of video conference recordings. The exemplary method further includes generating, based on the user image information, a template model that is generic to a plurality of users, selecting, from the user image information and based on predefined selection criteria, video frames that depict a user included in the plurality of users, and generating a virtual avatar model of the user by applying the selected video frames to the template model. A visual representation of the virtual avatar model may be configured to be used in future video conference sessions in place of a live video image of the user.