IP Library › Patent Application 17539036
Patent Application
App. No. 17/539,036

GENERATING AN AVATAR OF A PARTICIPANT OF A THREE DIMENSIONAL (3D) VIDEO CONFERENCE

Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US None
App. No.
17/539,036
Abstract

A method for generating an avatar of a participant of a three dimensional (3D) video conference, the method may include acquiring visual information, by a camera of a participant; generating an avatar of the participant as seen from a point of view of a virtual camera that is virtually located at a physical location of the camera; comparing between the avatar and the visual information to provide a comparison result; and amending the avatar or at least one building block of the avatar to compensate for one or more differences between the avatar and the visual information when the comparison results is indicative of the one or more differences.

Claims (33)

1 . A method for generating an avatar of a participant of a three dimensional (3D) video conference, the method comprises:

acquiring visual information, by a camera of a participant;

generating an avatar of the participant as seen from a point of view of a virtual camera that is virtually located at a physical location of the camera;

comparing between the avatar and the visual information to provide a comparison result; and

amending the avatar or at least one building block of the avatar to compensate for one or more differences between the avatar and the visual information when the comparison results is indicative of the one or more differences.

2 . The method according to claim 1 wherein the at least one building block of the avatar is a 3D model of the participant.

3 . The method according to claim 1 wherein avatar is rendered based on a 3D model of the participant and one or more 2D texture maps of the participant.

4 . The method according to claim 3 wherein the amending comprises amending at least one of the one or more 2D texture maps.

5 . The method according to claim 3 wherein the amending comprises amending the 3D model.

6 . The method according to claim 1 wherein the amending of the avatar or the at least one building block is executed by a machine learning process.

7 . The method according to claim 1 wherein the amending of the avatar or the at least one building block is executed by a supervised neural network.

8 . A non-transitory computer readable medium for generating an avatar of a participant of a three dimensional (3D) video conference, the non-transitory computer readable medium stores instructions for:

acquiring visual information, by a camera of a participant;

generating an avatar of the participant as seen from a point of view of a virtual camera that is virtually located at a physical location of the camera;

comparing between the avatar and the visual information to provide a comparison result; and

amending the avatar or at least one building block of the avatar to compensate for one or more differences between the avatar and the visual information when the comparison results is indicative of the one or more differences.

9 . The non-transitory computer readable medium according to claim 8 wherein the at least one building block of the avatar is a 3D model of the participant.

10 . The non-transitory computer readable medium according to claim 8 wherein avatar is rendered based on a 3D model of the participant and one or more 2D texture maps of the participant.

11 . The non-transitory computer readable medium according to claim 10 wherein the amending comprises amending at least one of the one or more 2D texture maps.

12 . The non-transitory computer readable medium according to claim 10 wherein the amending comprises amending the 3D model.

13 . The non-transitory computer readable medium according to claim 8 wherein the amending of the avatar or the at least one building block is executed by a machine learning process.

14 . The non-transitory computer readable medium according to claim 8 wherein the amending of the avatar or the at least one building block is executed by a supervised neural network.

15 . A system for generating an avatar of a participant of a three dimensional (3D) video conference, the system comprises a processor that is configured to:

receive visual information that is acquired by a camera of a participant;

generate an avatar of the participant as seen from a point of view of a virtual camera that is virtually located at a physical location of the camera;

compare between the avatar and the visual information to provide a comparison result; and

amend the avatar or at least one building block of the avatar to compensate for one or more differences between the avatar and the visual information when the comparison results is indicative of the one or more differences.

16 . The system according to claim 15 wherein the at least one building block of the avatar is a 3D model of the participant.

17 . The system according to claim 15 wherein avatar is rendered based on a 3D model of the participant and one or more 2D texture maps of the participant.

18 . The system according to claim 17 wherein the amending comprises amending at least one of the one or more 2D texture maps.

19 . The system according to claim 17 wherein the amending comprises amending the 3D model.

20 . The system according to claim 15 wherein the amending of the avatar or the at least one building block is executed by a machine learning process.

21 . The system according to claim 15 wherein the amending of the avatar or the at least one building block is executed by a supervised neural network.