Avatar facial expression animations with head rotation

Patent metadata

Field	Value
Publication number	US-9761032-B2
Application number	US-201414443339-A
Country	US
Kind code	B2
Filing date	Jul 25, 2014
Priority date	Jul 25, 2014
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

Apparatuses, methods and storage medium associated with animating and rendering an avatar are disclosed herein. In embodiments, In embodiments, an apparatus may include an avatar animation engine configured to receive a plurality of facial motion parameters and a plurality of head gestures parameters, respectively associated with a face and a head of a user. The plurality of facial motion parameters may depict facial action movements of the face, and the plurality of head gesture parameters may depict head pose gestures of the head. Further, the avatar animation engine may be configured to drive an avatar model with facial and skeleton animations to animate an avatar, using the facial motion parameters and the head gestures parameters, to replicate a facial expression of the user on the avatar that includes impact of head post rotation of the user. Other embodiments may be described and/or claimed.

First claim

What is claimed is:

1. An apparatus for rendering an avatar, comprising:
one or more processors; and
an avatar animation engine, to be operated by the one or more processors, to receive a plurality of facial motion parameters and a plurality of head gestures parameters, respectively associated with a face and a head of a user, and drive an avatar model with facial and skeleton animations to animate an avatar, employing at least a head bone and a torso bone connected at a joint and using the facial motion parameters and the head gestures parameters, to replicate a facial expression of the user on the avatar, that includes impact of head post rotation of the user;
wherein the plurality of facial motion parameters depict facial action movements of the face, and the plurality of head gestures parameters depict head pose gestures of the head;
wherein the avatar animation engine is to apply head rotation impact weights when driving the avatar model with facial and skeleton animations; and
wherein the avatar animation engine is to apply head rotation impact weights from a head rotation impact weight map pre-generated employing the at least a head bone and a torso bone connected at a joint.

2. The apparatus of claim 1 , wherein the joint is disposed at a neck.

3. The apparatus of claim 1 , wherein the head rotation impact weight map is in gray scale with lighter gray values depicting greater impact from head rotation.

4. The apparatus of claim 1 , wherein the head rotation impact weight map has a layout that includes a section for the face, a section for eyeballs of the face, a section for a neck of the user, a section for a tongue of the face, a section for teeth of the face or a section for a body or clothing of the user.

5. The apparatus of claim 1 , wherein the avatar animation engine is to further employ a 2-dimensional texture map, and the head rotation impact weight map has layout or dimensions that correspond to the 2-dimensional texture map; and wherein the animation engine is to retrieve an impact weight for a vertex from the head rotation impact weight map, using corresponding coordinates of the vertex in the 2-dimensional texture map.

6. The apparatus of claim 1 , wherein the avatar animation engine is to blend a plurality of pre-defined blend shapes when driving the avatar model with facial animation, and apply the head rotation impact weights to a result of the facial animation to drive the avatar model with skeleton simulation.

7. The apparatus of claim 6 , wherein to blend a plurality of pre-defined blend shapes when driving the avatar model with facial animation comprises:
determine a position offset in each of the plurality of pre-defined blend shapes;
apply corresponding blend shape weights to the position offsets determined;
sum the blend shape weighted position offsets for all blend shapes; and
add the sum to a position offset of a vertex in a base model.

8. The apparatus of claim 1 , wherein head rotation comprises yaw, pitch or tilt.

9. The apparatus of claim 1 further comprising a facial mesh tracker, operated by the one or more processors, to receive a plurality of image frames, detect, through the plurality of image frames, facial action movements of the face of the user and head pose gestures of the head of the user, and output the plurality of facial motion parameters to depict facial action movements detected, and the plurality of head gestures parameters to depict head pose gestures detected, all in real time;
wherein detection of facial action movements and head pose gestures includes detection of inter-frame differences for a mouth and an eye on the face, and the head, based on pixel sampling of the image frames.

10. The apparatus of claim 9 further comprising an avatar rendering engine coupled with the avatar animation engine and operated by the one or more processors to draw the avatar as animated by the avatar animation engine.

11. A method for rendering an avatar, comprising:
receiving, by a computing device, a plurality of facial motion parameters and a plurality of head gestures parameters, respectively associated with a face and a head of a user; and
driving an avatar model with facial and skeleton animations to animate the avatar, employing at least a head bone and a torso bone connected at a joint and using the facial motion parameters and the head gestures parameters to replicate a facial expression of the user on the avatar, that includes impact of head post rotation of the user;
wherein the plurality of facial motion parameters depict facial action movements of the face, and the plurality of head gestures parameters depict head pose gestures of the head;
wherein driving comprises applying head rotation impact weights while driving the avatar model with facial and skeleton animations; and
wherein applying comprises applying head rotation impact weights from a head rotation impact weight may pre-generated employing the at least a head bone and a torso bone connected at a joint.

12. A non-transitory computer-readable medium comprising instructions to cause a computing device, in response to execution of the instructions, to:
receive a plurality of facial motion parameters and a plurality of head gestures parameters, respectively associated with a face and a head of a user; and
drive an avatar model with facial and skeleton animations to animate the avatar, employing at least a head bone and a torso bone connected at a joint and using the facial motion parameters and the head gestures parameters to replicate a facial expression of the user on the avatar, that includes impact of head post rotation of the user;
wherein the plurality of facial motion parameters depict facial action movements of the face, and the plurality of head gestures parameters depict head pose gestures of the head;
wherein to drive comprises application of head rotation impact weights while driving the avatar model with facial and skeleton animations; and
wherein application comprises application of head rotation impact weights from a head rotation impact weight map pre-generated employing the at least a head bone and a torso bone connected at a joint.

13. The computer-readable medium of claim 12 , wherein the joint is disposed at a neck.

14. The computer-readable medium of claim 12 , wherein the head rotation impact weight map is in gray scale with lighter gray values depicting greater impact from head rotation.

15. The computer-readable medium of claim 12 , wherein the head rotation impact weight map has a layout that includes a section for the face, a section for eyeballs of the face, a section for a neck of the user, a section for a tongue of the face, a section for teeth of the face or a section for a body or clothing of the user.

16. The computer-readable medium of claim 12 , wherein to drive comprises employment of a 2-dimensional texture map; wherein the head rotation impact weight map has layout or dimensions that correspond to the 2-dimensional texture map; wherein application comprises retrieval of an impact weight for a vertex from the head rotation impact weight map, using corresponding coordinates of the vertex in the 2-dimensional texture map.

17. The computer-readable medium of claim 12 , wherein to drive comprises to blend a plurality of pre-defined blend shapes while driving the avatar model with facial animation, and to apply the head rotation impact weights to a result of the facial animation to drive the avatar model with skeleton simulation.

18. The computer-readable medium of claim 17 , wherein to blend a plurality o

Assignees

• Intel Corp

Inventors

• Tong Xiaofeng
• Li Qiang
• Sachson Thomas
• Li Wenlong

Classifications

• A63F2300/6607

  for animating game characters, e.g. skeleton kinematics · CPC title

• A63F2300/5553

  user representation in the game field, e.g. avatar · CPC title

• G06T13/40 Primary

  of characters, e.g. humans, animals or virtual beings · CPC title

• G06T15/503

  Blending, e.g. for anti-aliasing · CPC title

• G06T15/04

  Texture mapping · CPC title