Sketch selection for rendering 3D model avatar

• US 9,824,502 B2
• Filed: 12/23/2014
• Issued: 11/21/2017
• Est. Priority Date: 12/23/2014
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Tong, Xiaofeng, Li, Qiang Eric, Du, Yangzhou, Li, Wenlong
• Primary Examiner(s): Du, Haixia
• Application Number:
  US14/779,491
• Publication Number:
  US 20160328886A1
• Time in Patent Office: 1,064 Days
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/04815 Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/04845 for image manipulation, e.g. dragging, rotation, expansion or change of colour
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

Examples of systems and methods for three-dimensional model customization for avatar animation using a sketch image selection are generally described herein. A method for rendering a three-dimensional model may include presenting a plurality of sketch images to a user on a user interface, and receiving a selection of sketch images from the plurality of sketch images to compose a face. The method may include rendering the face as a three-dimensional model, the three-dimensional model for use as an avatar.

Claims

1. A system for rendering a three-dimensional model, the system comprising:

a display screen including a user interface to present a plurality of two-dimensional facial feature sketch images to a user, each two-dimensional facial feature sketch image of the two-dimensional facial feature sketch images mapped to a corresponding three-dimensional shape using three-dimensional parameters; and

a processor to;

receive a selection of two-dimensional facial feature sketch images from the plurality of two-dimensional facial feature sketch images to compose a face;

compare the selection of two-dimensional facial feature sketch images to a predetermined set of essential facial features that define a composed face;

determine a subset of the predetermined set of essential facial features missing from the selection of two-dimensional facial feature sketch images;

select two-dimensional facial feature sketch images from a default set of facial feature sketch images and corresponding to the subset of the set of essential facial features as system selected two-dimensional facial feature sketch images; and

render the face as a three-dimensional model based on the composed face comprising the selection of two-dimensional facial feature sketch images and the system selected two-dimensional facial feature sketch images, using the corresponding three-dimensional shape for each of the two-dimensional facial feature sketch images, wherein the three-dimensional model is an avatar.

2. The system of claim 1, wherein the processor is to receive user input to modify a base version of a facial feature of the face.

3. The system of claim 2, wherein to receive user input to modify the base version of the facial feature, the processor is to receive a weighting value for the facial feature.

4. The system of claim 1, wherein the display screen is a capacitive touch screen and to receive the selection of two-dimensional sketch images the processor is to receive an indication from the capacitive touch screen.

5. The system of claim 1, further comprising:

an image capture device to capture a series of images of a user, wherein the processor is to compute facial motion data for each of the images in the series of images, and

wherein the processor is further to animate the avatar using the facial motion data.

6. The system of claim 5, wherein to render the face as a three-dimensional model, the processor is to render specific points for animation on the three-dimensional model.

7. The system of claim 6, wherein the processor is to animate the specific points.

8. The system of claim 5, wherein the processor is to:

receive a selection of a two-dimensional facial feature accessory sketch image;

render the two-dimensional facial feature accessory sketch image as a three-dimensional facial feature accessory connected to a corresponding three-dimensional facial feature of the avatar.

9. The system of claim 8, wherein the processor is further to animate the three-dimensional facial feature accessory to move independently of the three-dimensional model.

10. The system of claim 1, wherein the processor is to receive a request to edit the three-dimensional model.

11. The system of claim 10, wherein the user interface is to present the selection of two-dimensional facial feature sketch images and the plurality of two-dimensional facial feature sketch images to the user for editing in response to the request to edit the three-dimensional model.

12. The system of claim 1, wherein the selection of two-dimensional facial feature sketch images includes a selection of a base shape for a facial feature of the face.

13. The system of claim 12, wherein the selection of two-dimensional facial feature sketch images includes a selection of a size for the base shape.

14. The system of claim 13, wherein the base shape corresponds to an eigen-vector and the size for the base shape corresponds to an eigen-value for the eigen-vector.

15. At least one non-transitory machine-readable medium including instructions for receiving information, which when executed by a machine, cause the machine to:

cause a plurality of two-dimensional facial feature sketch images to be presented to a user on a user interface of a display screen, each two-dimensional facial feature sketch image of the two-dimensional facial feature sketch images mapped to a corresponding three-dimensional shape using three-dimensional parameters;

receive a selection of two-dimensional facial feature sketch images from the plurality of two-dimensional facial feature sketch images to compose a face;

compare the selection of two-dimensional facial feature sketch images to a predetermined set of essential facial features that define a composed face;

determine a subset of the predetermined set of essential facial features missing from the selection of two-dimensional facial feature sketch images;

select two-dimensional facial feature sketch images from a default set of facial feature sketch images and corresponding to the subset of the set of essential facial features as system selected two-dimensional facial feature sketch images; and

render the face as a three-dimensional model based on the composed face comprising the selection of two-dimensional facial feature sketch images and the system selected two-dimensional facial feature sketch images, using the corresponding three-dimensional shape for each of the two-dimensional facial feature sketch images, wherein the three-dimensional model is an avatar.

16. The at least one machine-readable medium of claim 15, wherein the display screen is a capacitive touch screen and the operations to receive the selection of two-dimensional sketch images include operations to receive an indication from the capacitive touch screen.

17. The at least one machine-readable medium of claim 15, further comprising operations to:

capture a series of images of a user at an image capture device, compute facial motion data for each of the images in the series of images; and

animate the avatar using the facial motion data.

18. The at least one machine-readable medium of claim 17, wherein operations to render the face as a three-dimensional model include operations to render specific points for animation on the three-dimensional model.

19. The at least one machine-readable medium of claim 17, further comprising operations to:

receive a selection of a two-dimensional facial feature accessory sketch image;

render the two-dimensional facial feature accessory sketch image as a three-dimensional facial feature accessory connected to a corresponding three-dimensional facial feature of the avatar.

20. The at least one machine-readable medium of claim 19, further comprising operations to animate the three-dimensional facial feature accessory to move independently of the three-dimensional model.

21. The at least one machine-readable medium of claim 15, further comprising operations to receive a request to edit the three-dimensional model.

22. The at least one machine-readable medium of claim 21, further comprising operations to present the selection of two-dimensional facial feature sketch images and the plurality of two-dimensional facial feature sketch images to the user for editing in response to the request to edit the three-dimensional model.

23. A method for rendering a three-dimensional model, the method comprising:

presenting a plurality of two-dimensional facial feature sketch images to a user on a user interface on a display screen, each two-dimensional facial feature sketch image of the two-dimensional sketch images mapped to a corresponding three-dimensional shape using three-dimensional parameters;

receiving, at a processor, a selection of two-dimensional facial feature sketch images from the plurality of two-dimensional facial feature sketch images to compose a face;

comparing the selection of two-dimensional facial feature sketch images to a predetermined set of essential facial features that define a composed face;

determining a subset of the predetermined set of essential facial features missing from the selection of two-dimensional facial feature sketch images;

selecting two-dimensional facial feature sketch images from a default set of facial feature sketch images and corresponding to the subset of the set of essential facial features as system selected two-dimensional facial feature sketch images; and

rendering, using the processor, the face as a three-dimensional model using the composed face comprising the selection of two-dimensional facial feature sketch images and the system selected two-dimensional facial feature sketch images, using the corresponding three-dimensional shape for each of the two-dimensional facial feature sketch images, wherein the three-dimensional model is an avatar.

24. The method of claim 23, further comprising receiving user input to modify a base version of a facial feature of the face.

25. The method of claim 24, wherein receiving user input to modifying the base version of the facial feature includes receiving a weighting value for the facial feature.