IP Library Granted Patent US 11,354,844
Granted Patent B2
US 11,354,844 · App. 17/288,477 · Granted Jun 7, 2022

Digital character blending and generation system and method

Inventors: Mark Andrew Sagar (Auckland, NZ); Tim Szu-Hsien Wu (Auckland Central, NZ); Werner Ollewagen (Auckland, NZ); Xiani Tan (Auckland, NZ)
Assignee: Soul Machines Limited
G06T13/40G06T15/04G06T15/503G06T19/20G06T2219/2021
View Patent ↗
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 11,354,844
App. No.
17/288,477
Granted
Jun 7, 2022
Kind
B2
Abstract

A method for creating a model of a virtual object or digital entity is described, the method comprising receiving a plurality of basic shapes for a plurality of models; receiving a plurality of specified modification variables specifying a modification to be made to the basic shapes; and applying the specified modification(s) to the plurality of basic shapes to generate a plurality of modified basic shapes for at least one model.

Claims (34)

1. A method for creating a model of a virtual object or digital entity,

the method comprising:

receiving a plurality of human body portion models, wherein each respective human body portion model has a plurality of basic shapes, each basic shape comprising one or more regions and a set of muscle deformation descriptors influencing animation of a sequence of events within the respective basic shape according to corresponding muscle action units, wherein the plurality of basic shapes is a part of a face;

categorizing the muscle deformation descriptors according to groups based on a region influenced (“region of influence”) by the muscle action units of categorized muscle deformation descriptors;

generating at least one region masks for each basic shape based on the region of influence;

receiving a plurality of specified demographic prediction modifications to be made to one or more of the basic shapes of at least one human body portion model; and

generating at least one modified basic shape by blending at least two of the specified demographic prediction modifications together at a respective region mask, further comprising: generating at least one modified basic shape that corresponds to one of: an eyeball asset, a cornea asset, a teeth asset, a tongue asset and a skull asset.

2. The method of claim 1 , wherein generated the region mask comprises:

generating the region mask based on at least one deformation gradients relative to a shape of undeformed muscles corresponding to the muscle action units of categorized muscle deformation descriptors.

3. The method of claim 1 , wherein the demographic prediction modifications include preserve variables to preserve selected features.

4. The method of claim 1 , wherein the plurality of basic shapes belong to one of: a body shape, a partial body shape, an upper body shape, a face shape and part of a partial face shape.

5. The method of claim 4 , wherein the plurality of the specified demographic prediction modifications includes at least one of: an ageing prediction modification, a gender prediction modification, an ethnicity prediction modification and a physique prediction modification.

6. A system comprising one or more processors, and a non-transitory computer-readable medium including one or more sequences of instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

receiving a plurality of human body portion models, wherein each respective human body portion model has a plurality of basic shapes, each basic shape comprising one or more regions and a set of muscle deformation descriptors influencing animation of a sequence of events within the respective basic shape according to corresponding muscle action units, wherein the plurality of basic shapes is a part of a face;

categorizing the muscle deformation descriptors according to groups based on a region influenced (“region of influence”) by the muscle action units of categorized muscle deformation descriptors;

generating at least one region masks for each basic shape based on the region of influence;

receiving a plurality of specified demographic prediction modifications to be made to one or more of the basic shapes of at least one human body portion model; and

generating at least one modified basic shape by blending at least two of the specified demographic prediction modifications together at a respective region mask, further comprising: generating at least one modified basic shape that corresponds to one of: an eyeball asset, a cornea asset, a teeth asset, a tongue asset and a skull asset.

7. The system of claim 6 , wherein generate the region mask comprises:

generate the region mask based on at least one deformation gradients relative to a shape of undeformed muscles corresponding to the muscle action units of categorized muscle deformation descriptors.

8. The system of claim 6 wherein the demographic prediction modifications include preserve variables to preserve selected features.

9. The system of claim 6 , wherein the plurality of basic shapes belong to one of: a body shape, a partial body shape, an upper body shape, a face shape and part of a partial face shape.

10. The system of claim 6 , wherein the plurality of the specified demographic prediction modifications includes at least one of: an ageing prediction modification, a gender prediction modification, an ethnicity prediction modification and a physique prediction modification.

11. A computer program product comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions for:

receiving a plurality of human body portion models, wherein each respective human body portion model has a plurality of basic shapes, each basic shape comprising one or more regions and a set of muscle deformation descriptors influencing animation of a sequence of events within the respective basic shape according to corresponding muscle action units, wherein the plurality of basic shapes is a part of a face;

categorizing the muscle deformation descriptors according to groups based on a region influenced (“region of influence”) by the muscle action units of categorized muscle deformation descriptors;

generating at least one region masks for each basic shape based on the region of influence;

receiving a plurality of specified demographic prediction modifications to be made to one or more of the basic shapes of at least one human body portion model; and

generating at least one modified basic shape by blending at least two of the specified demographic prediction modifications together at a respective region mask, further comprising: generating at least one modified basic shape that corresponds to one of: an eyeball asset, a cornea asset, a teeth asset, a tongue asset and a skull asset.

12. The computer program product of claim 11 , wherein generated the region mask comprises:

generating the region mask based on at least one deformation gradients relative to a shape of undeformed muscles corresponding to the muscle action units of categorized muscle deformation descriptors.

13. The computer program product of claim 11 , wherein the demographic prediction modifications include preserve variables to preserve selected features.

14. The computer program product of claim 11 , wherein the plurality of basic shapes belong to one of: a body shape, a partial body shape, an upper body shape, a face shape and part of a partial face shape.

15. The computer program product of claim 11 , wherein the plurality of the specified demographic prediction modifications includes at least one of: an ageing prediction modification, a gender prediction modification, an ethnicity prediction modification and a physique prediction modification.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 24, 2026
From: SOUL MACHINES LIMITED
To: APPDIRECT, INC.
Reel/Frame 076058/0831 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 10, 2023
From: SAGAR, MARK ANDREW; WU, TIM SZU-HSIEN; TAN, XIANI; OLLEWAGEN, WERNER
To: SOUL MACHINES LIMITED
Reel/Frame 063592/0379 →
Priority Claims (1)
NZ 747626 · Oct 26, 2018 · national
Continuity (1)
Related Publication 20210390751A1 · Dec 16, 2021
Cited By (2)
US 12,524,965 US 12,586,285