# US 2023/0419580 A1 · Systems and Methods for Implementing a Virtual Avatar Model for a Video Conference Session

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0419580 A1
- Document ID: US20230419580A1
- Status: Published application
- Kind: A1
- Application number: 17/849,955
- Filed: 2022-06-27
- Published: 2023-12-28
- Earliest claimed: 2022-06-27
- Assignees: Verizon Patent and Licensing Inc.
- Applicants: Verizon Patent and Licensing Inc.
- Inventors: Harish Narayan; Sourabh Khire; Gaurav Rihan; Sayali G. Salvi; Omkar Ghodke; Ashish Nagpal
- Web page: https://patentgrep.com/patent/US20230419580A1

## CPC

- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- H04L 12/1827: {Network arrangements for conference optimisation or adaptation}
- H04L 12/1822: {Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission}
- H04N 7/15: Conference systems
- H04N 7/155: {involving storage of or access to video conference sessions (tracking arrangements for later retrieval of a computer conference content or participants activities H04L12/1831)}
- H04N 7/157: {defining a virtual conference space and using avatars or agents (computer conference optimisation or adaptation H04L12/1827)}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## 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.

## Claims

### Claim 1

A system comprising:
a memory that stores instructions; and
a processor communicatively coupled to the memory and configured to execute the instructions to:
process 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;
generate, based on the user image information, a template model that is generic to the plurality of users;
select, from the user image information and based on predefined selection criteria, video frames that depict a user included in the plurality of users; and
generate 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 configured to be used in future video conference sessions in place of a live video image of the user.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processing of the plurality of video conference recordings includes filtering the plurality of video conference recordings based on conference metadata.

### Claim 3 (depends on 1)

The system of claim 1, wherein the template model corresponds to a three-dimensional (3D) template model.

### Claim 4 (depends on 1)

The system of claim 1, wherein the video frames include a plurality of views of a head of the user captured at different image capture angles.

### Claim 5 (depends on 1)

The system of claim 1, wherein the predefined selection criteria include a plurality of metrics to assess whether the video frames are suitable for application to the template model, the plurality of metrics including at least one of a presence factor, a scale factor, a pixel factor, or an occlusion factor.

### Claim 6 (depends on 1)

The system of claim 1, wherein the visual representation of the virtual avatar model is a photorealistic representation of the user.

### Claim 7 (depends on 1)

The system of claim 1, wherein the processor is further configured to execute the instructions to:
detect a user input selecting an option to use the virtual avatar model of the user during a video conference session; and
provide the visual representation of the virtual avatar model for display to other participants during the video conference session in place of the live video image of the user.

### Claim 8 (depends on 7)

The system of claim 7, wherein the processor is further configured to execute the instructions to:
capture images of the user during the video conference session;
analyze the images captured during the video conference session to generate input data for the virtual avatar model;
adjust, based on the input data, at least one of a facial expression, a movement, or a gesture represented by the virtual avatar model; and
animate, based on the adjusting of the at least one of the facial expression, the movement, or the gesture represented by virtual avatar model, the visual representation of the virtual avatar model during the video conference session.

### Claim 9 (depends on 8)

The system of claim 8, wherein the animating of the visual representation of the virtual avatar model includes limiting the animating to only represent facial expressions of the user during the video conference session.

### Claim 10 (depends on 7)

The system of claim 7, wherein the processor is further configured to execute the instructions to animate the visual representation of the virtual avatar model during the video conference session based on at least one of predefined expressions or predefined gestures selected by the user during the video conference session.

### Claim 11

A non-transitory computer-readable medium storing instructions that, when executed, direct at least one processor of a computing device to:
process 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;
generate, based on the user image information, a template model that is generic to the plurality of users;
select, from the user image information and based on predefined selection criteria, video frames that depict a user included in the plurality of users; and
generate 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 configured to be used in future video conference sessions in place of a live video image of the user.

### Claim 12 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the processing of the plurality of video conference recordings includes filtering the plurality of video conference recordings based on conference metadata.

### Claim 13 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the template model corresponds to a three-dimensional (3D) template model.

### Claim 14 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the video frames include a plurality of views of a head of the user captured at different image capture angles.

### Claim 15 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the predefined selection criteria include a plurality of metrics to assess whether the video frames are suitable for application to the template model, the plurality of metrics including at least one of a presence factor, a scale factor, pixel factor, or an occlusion factor.

### Claim 16 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the instructions are further configured to direct the at least one processor of the computing device to:
detect a user input selecting an option to use the virtual avatar model of the user during a video conference session; and
provide the visual representation of the virtual avatar model for display to other participants during the video conference session in place of the live video image of the user.

### Claim 17

A method comprising:
processing, by a virtual avatar processing system, a plurality of video conference recordings generated by a video conference platform to curate user image information associated with a plurality of users that participated in video conference sessions represented in the plurality of video conference recordings;
generating, by the virtual avatar processing system and based on the user image information, a template model that is generic to the plurality of users;
selecting, by the virtual avatar processing system 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, by the virtual avatar processing system, a virtual avatar model of the user by applying the selected video frames to the template model, a visual representation the virtual avatar model configured to be used in future video conference sessions in place of a live video image of the user.

### Claim 18 (depends on 17)

The method of claim 17, further comprising:
detecting, by the virtual avatar processing system, a user input selecting an option to use the virtual avatar model of the user during a video conference session; and
providing, by the virtual avatar processing system and based on the user input, a visual representation of the virtual avatar model for display to other participants during the video conference session in place of a live video image of the user.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
capturing, by the virtual avatar processing system, images of the user during the video conference session;
analyzing, by the virtual avatar processing system, the images captured during the video conference session to generate input data for the virtual avatar model;
adjusting, by the virtual avatar processing system and based on the input data, at least one of a facial expression, a movement, or a gesture represented by the virtual avatar model; and
animating, by the virtual avatar processing system and based on the adjusting of the at least one of the facial expression, the movement, or the gesture represented by virtual avatar model, the visual representation of the virtual avatar model during the video conference session.

### Claim 20 (depends on 18)

The method of claim 18, further comprising animating the visual representation of the virtual avatar model during the video conference session based on at least one of predefined expressions or predefined gestures selected by the user during the video conference session.
