Scalable avatar messaging

Patent metadata

Field	Value
Publication number	US-10044849-B2
Application number	US-201313976037-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Mar 15, 2013
Publication date	Aug 7, 2018
Grant date	Aug 7, 2018

Abstract

Technologies for distributed generation of an avatar with a facial expression corresponding to a facial expression of a user include capturing real-time video of a user of a local computing device. The computing device extracts facial parameters of the user's facial expression using the captured video and transmits the extracted facial parameters to a server. The server generates an avatar video of an avatar having a facial expression corresponding to the user's facial expression as a function of the extracted facial parameters and transmits the avatar video to a remote computing device.

First claim

The invention claimed is:

1. A server comprising:
a communication module to receive, from a first computing device, determined facial parameters of a facial expression represented in captured video of a user of the first computing device; and
a video module to generate, as a function of the determined facial parameters, an avatar video of an avatar having a facial expression corresponding to the users facial expression, wherein to generate the avatar comprises to (i) generate a plurality of modified avatar frames, each modified avatar frame representative of a corresponding frame in the captured video, (ii) generate a snapshot of an animated avatar in each modified avatar frame, and (iii) combine each generated snapshot,
the communication module further to (i) transmit, after receipt of the facial parameters, the avatar video to the first computing device and to a second computing device different from the first computing device and (ii) receive an indication from the first computing device of a switch from the avatar video to a remote avatar generated by the server for display on the first computing device.

2. The server of claim 1 , wherein the video module is to extract second facial parameters of a second facial expression of the user, different from the determined facial parameters, represented in the captured video in response to receipt of the captured video from the first computing device and generate a second avatar video, as a function of the second facial parameters, of the avatar having a second facial expression corresponding to the second facial expression of the user.

3. The server of claim 1 , wherein the communication module is further to (i) receive, from the second computing device, a remote avatar video of a facial expression of a user of the second computing device and (ii) transmit the remote avatar video to the first computing device.

4. The server of claim 1 , wherein the communication module is further to receive, from the second computing device, second facial parameters of a facial expression of a user of the second computing device; and
the video module is to generate, as a function of the second facial parameters, a remote avatar video of a remote avatar having a facial expression corresponding to the facial expression of the user of the second computing device, and
wherein the communication module is further to transmit the remote avatar video to the first computing device.

5. One or more machine-readable storage media comprising a plurality of instructions stored thereon that, in response to execution by a computing device, cause the computing device to:
receive, from a first computing device, determined facial parameters of a facial expression corresponding to a captured video of a user of the first computing device;
generate, as a function of the determined facial parameters, an avatar video of an avatar having a facial expression corresponding to the user's facial expression, wherein to generate the avatar video comprises to: (i) generate a plurality of modified avatar frames, each modified avatar frame representative of a corresponding frame in the captured video, (ii) generate a snapshot of an animated avatar in each modified avatar frame, and (iii) combine each generated snapshot;
transmit, after receipt of the facial parameters, the avatar video to the first computing device and to a second computing device different from the first computing device; and
receive an indication from the first computing device of a switch from the avatar video to a remote avatar generated by the computing device for display on the first computing device.

6. The one or more machine-readable storage media of claim 5 , wherein the plurality of instructions further cause the computing device to:
receive, from the first computing device, the captured video of the user; and
extract second facial parameters of a second facial expression of the user, different from the determined facial parameters, represented in the captured video in response, and
generate, as a function of the second facial parameters, a second avatar video of the avatar having a second facial expression corresponding to the second facial expression of the user.

7. The one or more machine-readable storage media of claim 5 , wherein the plurality of instructions further cause the computing device to:
receive, from the second computing device, a remote avatar video of a facial expression of a user of the second computing device; and
transmit the remote avatar video to the first computing device.

8. The one or more machine-readable storage media of claim 5 , wherein the plurality of instructions further cause the computing device to:
receive, from the second computing device, second facial parameters of a facial expression of a user of the second computing device;
generate, as a function of the second facial parameters, a remote avatar having a facial expression corresponding to the facial expression of the user of the second computing device; and
transmit the remote avatar video to the first computing device.

9. A computing device comprising:
a display;
a camera to capture video of a facial expression of a user of the computing device;
a video module extract facial parameters of the facial expression using the captured video; and
a communication module to (i) transmit the extracted facial parameters of the facial expression to a server and (ii) receive, from the server, a local avatar video generated as a function of the facial parameters of the facial expression, a generation of a plurality of modified avatar frames, each modified avatar frame representative of a corresponding frame in the captured video, a generation of a snapshot of an animated avatar in each modified avatar frame, and a combination of each generated snapshot,
wherein the video module is further to (i) permit the user to change the local avatar video and (ii) permit the user to switch between the local avatar video and a remote avatar for display on the display of the computing device.

10. The computing device of claim 9 , wherein to extract facial parameters of the user's facial expression comprises to perform a facial analysis of the captured video of the user's facial expression.

11. The computing device of claim 9 , wherein the communication module is to transmit the captured video of the user's facial expression to the server.

12. The computing device of claim 9 , wherein the communication module is to receive a remote avatar video corresponding to a facial expression of a user of a remote computing device.

13. The computing device of claim 12 , wherein the video module is further to:
display the local avatar video on the display in response to a selection by the user to display the local avatar video; and
display the remote avatar video on the display in response to a selection by the user to display the remote avatar video.

14. The computing device of claim 9 , wherein the video module is further to contemporaneously display a new local avatar and a current local avatar on the display in response to a selection by the user to change the local avatar.

15. The computing device of claim 14 , wherein the video module is to contemporaneously display each of the new local avatar and the current local avatar with facial expressions that correspond to a current facial expression of the user.

16. The computing device of claim 9 , wherein the video module is to indicate on the display that real-time facial parameters of the user's facial expression are extracted in response to the extraction of the facial parameters.

Assignees

• Intel Corp

Inventors

• Li Wenlong
• Tong Xiaofeng
• Du Yangzhou
• Sachson Thomas
• Zhang Yimin

Classifications

• H04N7/141

  between two video terminals, e.g. videophone (telephonic communication systems combined with television receiver for reception of entertainment or information matter H04M11/085) · CPC title

• H04N7/157 Primary

  defining a virtual conference space and using avatars or agents (computer conference optimisation or adaptation H04L12/1827) · CPC title

• H04M1/72544 Primary

  Electricity · mapped topic

• G06K9/00315

  Physics · mapped topic

• G06V40/176

  Dynamic expression · CPC title