IP Library › Granted Patent US 12,374,014
Granted Patent B2
US 12,374,014 · App. 17/643,065 · Granted Jul 29, 2025

Predicting facial expressions using character motion states

Inventors: Wolfram Sebastian Starke (Edinburgh, GB); Igor Borovikov (Foster City, CA); Harold Henry Chaput (Castro Valley, CA)
Assignee: Electronic Arts Inc.
G06T13/40G06N20/20G06T13/205G06T17/205
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 12,374,014
App. No.
17/643,065
Granted
Jul 29, 2025
Kind
B2
Abstract

Systems and methods for identifying one or more facial expression parameters associated with a pose of a character are disclosed. A system may execute a game development application to identify facial expression parameters for a particular pose of a character. The system may receive an input identifying the pose of the character. Further, the system may provide the input to a machine learning model. The machine learning model may be trained based on a plurality of poses and expected facial expression parameters for each pose. Further, the machine learning model can identify a latent representation of the input. Based on the latent representation of the input, the machine learning model can generate one or more facial expression parameters of the character and output the one or more facial expression parameters. The system may also generate a facial expression of the character and output the facial expression.

Claims (85)

1. A system comprising:

one or more processors; and

a computer-readable storage medium including machine-readable instructions that, when executed by the one or more processors, cause the one or more processors to execute a game development application, the game development application configured to:

receive a first input identifying a character pose of a first virtual character, the character pose of the first virtual character being defined by location information of a plurality of joints of a character skeleton;

apply a first machine learning model to the character pose of the first virtual character, wherein the first machine learning model is configured to generate one or more facial expression parameters of a facial expression of the first virtual character based at least in part on the character pose of the first virtual character, wherein the first machine learning model is trained based on mappings of character pose inputs to facial expression parameter outputs, wherein the game development application is configured to apply the first machine learning model to the character pose of the first virtual character to:

identify a first latent representation of the character pose of the first virtual character in latent space, and

generate the one or more facial expression parameters of the facial expression of the first virtual character based at least in part on the first latent representation of the character pose of the first virtual character; and

output the one or more facial expression parameters of the facial expression of the first virtual character, wherein a pose of a first portion of a character model of the first virtual character comprises the character pose of the first virtual character that is identified based at least in part on the first input, wherein an expression of a second portion of the character model of the first virtual character comprises the facial expression of the first virtual character that is generated based at least in part on the first latent representation of the character pose of the first virtual character, and wherein the first portion of the character model of the first virtual character is separate from the second portion of the character model of the first virtual character.

2. The system of claim 1 , wherein the game development application is further configured to:

receive a second input identifying at least one of image data associated with the first virtual character, audio data associated with the first virtual character, player data of a player associated with the first virtual character, a context of a video game associated with the first virtual character, a genre of the video game associated with the first virtual character, or one or more labels associated with the first virtual character, wherein to apply the first machine learning model to the character pose of the first virtual character, the game development application is further configured to apply the first machine learning model to the character pose of the first virtual character and the second input, wherein the first latent representation of the character pose of the first virtual character is a first latent representation of the character pose of the first virtual character and the second input.

3. The system of claim 1 , wherein the first input comprises at least one of motion capture data associated with a motion capture sensor or key-frame data.

4. The system of claim 1 , wherein the game development application is further configured to:

apply a second machine learning model to the character pose of the first virtual character, wherein the second machine learning model is configured to generate one or more facial expression parameters of a facial pose of a second virtual character based at least in part on the character pose of the first virtual character, wherein the game development application is configured to apply the second machine learning model to the character pose of the first virtual character to:

identify a second latent representation of the character pose of the first virtual character in latent space, and

generate the one or more facial expression parameters of the facial pose of the second virtual character based at least in part on the second latent representation of the character pose of the first virtual character; and

output the one or more facial expression parameters of the facial pose of the second virtual character.

5. The system of claim 1 , wherein the one or more facial expression parameters of the facial expression of the first virtual character comprise one or more labels, each of the one or more facial expression parameters of the facial expression of the first virtual character identifying an emotion of the first virtual character and associated with a particular weight.

6. The system of claim 1 , wherein the game development application is further configured to:

apply a second machine learning model to the character pose of the first virtual character, wherein the second machine learning model is configured to generate one or more facial expression parameters of a facial pose of a second virtual character based at least in part on the character pose of the first virtual character, wherein the game development application is configured to apply the second machine learning model to the character pose of the first virtual character to:

identify a second latent representation of the character pose of the first virtual character in latent space, and

generate the one or more facial expression parameters of the facial pose of the second virtual character based at least in part on the second latent representation of the character pose of the first virtual character;

output the one or more facial expression parameters of the facial pose of the second virtual character;

apply a third machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character, wherein the third machine learning model is configured to generate the facial expression of the first virtual character based at least in part on the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character, wherein the game development application is configured to apply the third machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character to:

identify a latent representation of the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character, and

generate the facial expression of the first virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character; and

output the facial expression of the first virtual character.

7. The system of claim 1 , wherein the game development application is further configured to:

apply a second machine learning model to the character pose of the first virtual character, wherein the second machine learning model is configured to generate one or more facial expression parameters of a facial pose of a second virtual character based at least in part on the character pose of the first virtual character, wherein the game development application is configured to apply the second machine learning model to the character pose of the first virtual character to:

identify a second latent representation of the character pose of the first virtual character in latent space, and

generate the one or more facial expression parameters of the facial pose of the second virtual character based at least in part on the second latent representation of the character pose of the first virtual character;

output the one or more facial expression parameters of the facial pose of the second virtual character;

apply a third machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character, wherein the third machine learning model is configured to generate the facial expression of the first virtual character based at least in part on the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character, wherein the game development application is configured to apply the third machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character and the one or more facial expression parameters of the facial pose of the second virtual character to:

identify a latent representation of the one or more facial expression parameters of the facial expression of the first virtual character and a latent representation of the one or more facial expression parameters of the facial pose of the second virtual character, and

generate the facial expression of the first virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the first virtual character and a facial expression of the second virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial pose of the second virtual character;

determine the facial expression of the first virtual character and the facial expression of the second virtual character are within a particular range of facial expressions; and

output the facial expression of the first virtual character and the facial expression of the second virtual character based at least in part on determining the facial expression of the first virtual character and the facial expression of the second virtual character are within the particular range of facial expressions.

8. The system of claim 1 , wherein the first input is associated with a single frame or a plurality of frames.

9. The system of claim 1 , wherein the game development application is further configured to:

obtain a training data set, wherein the training data set indicates the mappings of the character pose inputs to the facial expression parameter outputs; and

train the first machine learning model using the training data set.

10. The system of claim 1 , wherein the game development application is further configured to:

apply a second machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character, wherein the second machine learning model is configured to generate the facial expression of the first virtual character based at least in part on the one or more facial expression parameters of the facial expression of the first virtual character, wherein the game development application is configured to apply the second machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character to:

identify a latent representation of the one or more facial expression parameters of the facial expression of the first virtual character, and

generate the facial expression of the first virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the first virtual character; and

output the facial expression of the first virtual character, wherein the facial expression of the first virtual character comprises at least one of one or more morph meshes, one or more displacement maps, one or more shader parameters, one or more muscle sets, or one or more labels.

11. The system of claim 1 , wherein the game development application is further configured to:

apply a second machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character, wherein the second machine learning model is configured to generate the facial expression of the first virtual character based at least in part on the one or more facial expression parameters of the facial expression of the first virtual character, wherein the game development application is configured to apply the second machine learning model to the one or more facial expression parameters of the facial expression of the first virtual character to:

identify a latent representation of the one or more facial expression parameters of the facial expression of the first virtual character, and

generate the facial expression of the first virtual character and a probability associated with the facial expression of the first virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the first virtual character; and

output the facial expression of the first virtual character and the probability associated with the facial expression of the first virtual character.

12. The system of claim 1 , wherein the game development application is further configured to:

generate an output by combining the character pose of the first virtual character and the one or more facial expression parameters of the facial expression of the first virtual character; and

provide the output to a computing device.

13. The system of claim 1 , wherein to output the one or more facial expression parameters of the facial expression of the first virtual character, the game development application is further configured to:

output a recommendation that recommends the facial expression of the first virtual character for the first virtual character based at least in part on the one or more facial expression parameters of the facial expression of the first virtual character.

14. A computer-implemented method comprising:

as implemented by an interactive computing system configured with specific computer-executable instructions during runtime of a game development application,

receiving a first input identifying a character pose of a virtual character, the character pose of the virtual character being defined by location information of a plurality of joints of a character skeleton;

applying a first machine learning model to the character pose of the virtual character, wherein the first machine learning model is configured to generate one or more facial expression parameters of a facial expression of the virtual character based at least in part on the character pose of the virtual character, wherein the first machine learning model is trained based on mappings of character pose inputs to facial expression parameter outputs, wherein applying the first machine learning model to the character pose of the virtual character comprises:

identifying a latent representation of the character pose of the virtual character in latent space, and

generating the one or more facial expression parameters of the facial expression of the virtual character based at least in part on the latent representation of the character pose of the virtual character; and

outputting the one or more facial expression parameters of the facial expression of the virtual character, wherein a pose of a first portion of a character model of the virtual character comprises the character pose of the virtual character that is identified based at least in part on the first input, wherein an expression of a second portion of the character model of the virtual character comprises the facial expression of the virtual character that is generated based at least in part on the latent representation of the character pose of the virtual character, and wherein the first portion of the character model of the virtual character is separate from the second portion of the character model of the virtual character.

15. The computer-implemented method of claim 14 further comprising:

applying a second machine learning model to the one or more facial expression parameters of the facial expression of the virtual character, wherein the second machine learning model is configured to generate the facial expression of the virtual character based at least in part on the one or more facial expression parameters of the facial expression of the virtual character, wherein applying the second machine learning model to the one or more facial expression parameters of the facial expression of the virtual character comprises:

identifying a latent representation of the one or more facial expression parameters of the facial expression of the virtual character, and

generating the facial expression of the virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the virtual character; and

outputting the facial expression of the virtual character.

16. The computer-implemented method of claim 14 further comprising:

receiving a second input identifying at least one of image data associated with the virtual character, audio data associated with the virtual character, player data of a player associated with the virtual character, a context of a video game associated with the virtual character, a genre of the video game associated with the virtual character, or one or more labels associated with the virtual character, wherein applying the first machine learning model to the character pose of the virtual character further comprises applying the first machine learning model to the character pose of the virtual character and the second input, wherein the latent representation of the character pose of the virtual character is a latent representation of the character pose of the virtual character and the second input.

17. The computer-implemented method of claim 14 further comprising:

generating an output by combining the character pose of the virtual character and the one or more facial expression parameters of the facial expression of the virtual character; and

providing the output to a computing device.

18. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by one or more computing devices, configure the one or more computing devices to execute a game development application, the game development application configured to:

receive a first input identifying a character pose of a virtual character, the character pose of the virtual character being defined by location information of a plurality of joints of a character skeleton;

apply a first machine learning model to the character pose of the virtual character, wherein the first machine learning model is configured to generate one or more facial expression parameters of a facial expression of the virtual character based at least in part on the character pose of the virtual character, wherein the first machine learning model is trained based on mappings of character pose inputs to facial expression parameter outputs, wherein the game development application is configured to apply the first machine learning model to the character pose of the virtual character to:

identify a latent representation of the character pose of the virtual character in latent space, and

generate the one or more facial expression parameters of the facial expression of the virtual character based at least in part on the latent representation of the character pose of the virtual character; and

output the one or more facial expression parameters of the facial expression of the virtual character, wherein a pose of a first portion of a character model of the virtual character comprises the character pose of the virtual character that is identified based at least in part on the first input, wherein an expression of a second portion of the character model of the virtual character comprises the facial expression of the virtual character that is generated based at least in part on the latent representation of the character pose of the virtual character, and wherein the first portion of the character model of the virtual character is separate from the second portion of the character model of the virtual character.

19. The non-transitory computer-readable medium of claim 18 , wherein the game development application is further configured to:

apply a second machine learning model to the one or more facial expression parameters of the facial expression of the virtual character, wherein the second machine learning model is configured to generate the facial expression of the virtual character based at least in part on the one or more facial expression parameters of the facial expression of the virtual character, wherein the game development application is configured to apply the second machine learning model to the one or more facial expression parameters of the facial expression of the virtual character to:

identify a latent representation of the one or more facial expression parameters of the facial expression of the virtual character, and

generate the facial expression of the virtual character based at least in part on the latent representation of the one or more facial expression parameters of the facial expression of the virtual character; and

output the facial expression of the virtual character.

20. The non-transitory computer-readable medium of claim 18 , wherein the game development application is further configured to:

receive a second input identifying at least one of image data associated with the virtual character, audio data associated with the virtual character, player data of a player associated with the virtual character, a context of a video game associated with the virtual character, a genre of the video game associated with the virtual character, or one or more labels associated with the virtual character, wherein to apply the first machine learning model to the character pose of the virtual character, the game development application is further configured to apply the first machine learning model to the character pose of the virtual character and the second input, wherein the latent representation of the character pose of the virtual character is a latent representation of the character pose of the virtual character and the second input.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 1, 2025
From: STARKE, WOLFRAM SEBASTIAN; BOROVIKOV, IGOR; CHAPUT, HAROLD HENRY
To: ELECTRONIC ARTS INC.
Reel/Frame 070999/0707 →
Continuity (1)
Related Publication 20230177755A1 · Jun 8, 2023
References Cited (276)
US 5274801A · Gordon · 1993 [cited by applicant]
US 5548798A · King · 1996 [cited by applicant]
US 5982389A · Guenter et al. · 1999 [cited by applicant]
US 5999195A · Santangeli · 1999 [cited by applicant]
US 6064808A · Kapur et al. · 2000 [cited by applicant]
US 6088040A · Oda et al. · 2000 [cited by applicant]
US 6253193B1 · Ginter et al. · 2001 [cited by applicant]
US 6556196B1 · Blanz et al. · 2003 [cited by applicant]
US 6961060B1 · Mochizuki et al. · 2005 [cited by applicant]
US 7006090B2 · Mittring · 2006 [cited by applicant]
US 7403202B1 · Nash · 2008 [cited by applicant]
US 7415152B2 · Jiang et al. · 2008 [cited by applicant]
US 7944449B2 · Petrovic et al. · 2011 [cited by applicant]
US 8100770B2 · Yamazaki et al. · 2012 [cited by applicant]
US 8142282B2 · Canessa et al. · 2012 [cited by applicant]
US 8154544B1 · Cameron et al. · 2012 [cited by applicant]
US 8207971B1 · Koperwas et al. · 2012 [cited by applicant]
US 8267764B1 · Aoki et al. · 2012 [cited by applicant]
US 8281281B1 · Smyrl et al. · 2012 [cited by applicant]
US 8395626B2 · Millman · 2013 [cited by applicant]
US 8398476B1 · Sidhu et al. · 2013 [cited by applicant]
US 8406528B1 · Hatwich · 2013 [cited by applicant]
US 8540560B2 · Crowley et al. · 2013 [cited by applicant]
US 8599206B2 · Hodgins et al. · 2013 [cited by applicant]
US 8624904B1 · Koperwas et al. · 2014 [cited by applicant]
US 8648863B1 · Anderson et al. · 2014 [cited by applicant]
US 8860732B2 · Popovic et al. · 2014 [cited by applicant]
US 8914251B2 · Ohta · 2014 [cited by applicant]
US 9001132B1 · Wooley · 2015 [cited by applicant]
US 9117134B1 · Geiss et al. · 2015 [cited by applicant]
US 9256973B2 · Koperwas et al. · 2016 [cited by applicant]
US 9317954B2 · Li et al. · 2016 [cited by applicant]
US 9483860B2 · Hwang et al. · 2016 [cited by applicant]
US 9616329B2 · Szufnara et al. · 2017 [cited by applicant]
US 9652879B2 · Aguado · 2017 [cited by applicant]
US 9741146B1 · Nishimura · 2017 [cited by applicant]
US 9811716B2 · Kim et al. · 2017 [cited by applicant]
US 9826898B1 · Jin et al. · 2017 [cited by applicant]
US 9858700B2 · Rose et al. · 2018 [cited by applicant]
US 9861898B2 · Miura et al. · 2018 [cited by applicant]
US 9947123B1 · Green · 2018 [cited by applicant]
US 9984658B2 · Bonnier et al. · 2018 [cited by applicant]
US 9990754B1 · Waterson et al. · 2018 [cited by applicant]
US 9996940B1 · Yamasaki · 2018 [cited by examiner]
US 10022628B1 · Matsumiya et al. · 2018 [cited by applicant]
US 10096133B1 · Andreev · 2018 [cited by applicant]
US 10118097B2 · Stevens · 2018 [cited by applicant]
US 10198845B1 · Bhat et al. · 2019 [cited by applicant]
US 10314477B1 · Goodsitt et al. · 2019 [cited by applicant]
US 10388053B1 · Carter, Jr. et al. · 2019 [cited by applicant]
US 10403018B1 · Worsham · 2019 [cited by applicant]
US 10440443B2 · Casey et al. · 2019 [cited by applicant]
US 10535174B1 · Rigiroli et al. · 2020 [cited by applicant]
US 10726611B1 · Court · 2020 [cited by applicant]
US 10733765B2 · Andreev · 2020 [cited by applicant]
US 10755466B2 · Chamdani et al. · 2020 [cited by applicant]
US 10792566B1 · Schmid · 2020 [cited by applicant]
US 10825220B1 · Chang et al. · 2020 [cited by applicant]
US 10856733B2 · Anderson et al. · 2020 [cited by applicant]
US 10860838B1 · Elahie et al. · 2020 [cited by applicant]
US 10878540B1 · Stevens · 2020 [cited by applicant]
US 10902618B2 · Payne et al. · 2021 [cited by applicant]
US 10986400B2 · Hua et al. · 2021 [cited by applicant]
US 11017560B1 · Gafni et al. · 2021 [cited by applicant]
US 11403513B2 · Hasenclever et al. · 2022 [cited by applicant]
US 11562523B1 · Starke et al. · 2023 [cited by applicant]
US 11670030B2 · Shi et al. · 2023 [cited by applicant]
US 11830121B1 · Starke et al. · 2023 [cited by applicant]
US 11995754B2 · Starke et al. · 2024 [cited by applicant]
US 12138543B1 · Starke et al. · 2024 [cited by applicant]
US 12205214B2 · Starke et al. · 2025 [cited by applicant]
US 20020054054A1 · Sanbe · 2002 [cited by applicant]
US 20020089504A1 · Merrick et al. · 2002 [cited by applicant]
US 20020180739A1 · Reynolds et al. · 2002 [cited by applicant]
US 20030038818A1 · Tidwell · 2003 [cited by applicant]
US 20040027352A1 · Minakuchi · 2004 [cited by applicant]
US 20040227760A1 · Anderson et al. · 2004 [cited by applicant]
US 20040227761A1 · Anderson et al. · 2004 [cited by applicant]
US 20050237550A1 · Hu · 2005 [cited by applicant]
US 20060036514A1 · Steelberg et al. · 2006 [cited by applicant]
US 20060149516A1 · Bond et al. · 2006 [cited by applicant]
US 20060217945A1 · Leprevost · 2006 [cited by applicant]
US 20060262114A1 · Leprevost · 2006 [cited by applicant]
US 20070085851A1 · Muller et al. · 2007 [cited by applicant]
US 20070097125A1 · Xie et al. · 2007 [cited by applicant]
US 20080049015A1 · Elmieh et al. · 2008 [cited by applicant]
US 20080111831A1 · Son et al. · 2008 [cited by applicant]
US 20080152218A1 · Okada · 2008 [cited by applicant]
US 20080268961A1 · Brook · 2008 [cited by applicant]
US 20080273039A1 · Girard · 2008 [cited by applicant]
US 20080316202A1 · Zhou et al. · 2008 [cited by applicant]
US 20090066700A1 · Harding et al. · 2009 [cited by applicant]
US 20090195544A1 · Wrinch et al. · 2009 [cited by applicant]
US 20090315839A1 · Wilson et al. · 2009 [cited by applicant]
US 20100134501A1 · Lowe et al. · 2010 [cited by applicant]
US 20100251185A1 · Pattenden · 2010 [cited by applicant]
US 20100277497A1 · Dong et al. · 2010 [cited by applicant]
US 20110012903A1 · Girard · 2011 [cited by applicant]
US 20110074807A1 · Inada et al. · 2011 [cited by applicant]
US 20110086702A1 · Borst et al. · 2011 [cited by applicant]
US 20110119332A1 · Marshall et al. · 2011 [cited by applicant]
US 20110128292A1 · Ghyme et al. · 2011 [cited by applicant]
US 20110164831A1 · Van Reeth et al. · 2011 [cited by applicant]
US 20110187731A1 · Tsuchida · 2011 [cited by applicant]
US 20110269540A1 · Gillo et al. · 2011 [cited by applicant]
US 20110292055A1 · Hodgins et al. · 2011 [cited by applicant]
US 20120029699A1 · Jing · 2012 [cited by applicant]
US 20120083330A1 · Ocko · 2012 [cited by applicant]
US 20120115580A1 · Hornik et al. · 2012 [cited by applicant]
US 20120220376A1 · Takayama et al. · 2012 [cited by applicant]
US 20120244941A1 · Ostergren et al. · 2012 [cited by applicant]
US 20120275521A1 · Cui et al. · 2012 [cited by applicant]
US 20120303343A1 · Sugiyama et al. · 2012 [cited by applicant]
US 20120313931A1 · Matsuike et al. · 2012 [cited by applicant]
US 20130050464A1 · Kang · 2013 [cited by applicant]
US 20130063555A1 · Matsumoto et al. · 2013 [cited by applicant]
US 20130120439A1 · Harris et al. · 2013 [cited by applicant]
US 20130121618A1 · Yadav · 2013 [cited by applicant]
US 20130222433A1 · Chapman et al. · 2013 [cited by applicant]
US 20130235045A1 · Corazza et al. · 2013 [cited by applicant]
US 20130263027A1 · Petschnigg et al. · 2013 [cited by applicant]
US 20130311885A1 · Wang et al. · 2013 [cited by applicant]
US 20140002463A1 · Kautzman et al. · 2014 [cited by applicant]
US 20140198106A1 · Sumner et al. · 2014 [cited by applicant]
US 20140198107A1 · Thomaszewski et al. · 2014 [cited by applicant]
US 20140285513A1 · Aguado · 2014 [cited by applicant]
US 20140327694A1 · Cao et al. · 2014 [cited by applicant]
US 20150113370A1 · Flider · 2015 [cited by applicant]
US 20150126277A1 · Aoyagi · 2015 [cited by applicant]
US 20150187113A1 · Rubin et al. · 2015 [cited by applicant]
US 20150235351A1 · Mirbach et al. · 2015 [cited by applicant]
US 20150243326A1 · Pacurariu et al. · 2015 [cited by applicant]
US 20150381925A1 · Varanasi et al. · 2015 [cited by applicant]
US 20160026926A1 · Yeung et al. · 2016 [cited by applicant]
US 20160042548A1 · Du et al. · 2016 [cited by applicant]
US 20160071470A1 · Kim et al. · 2016 [cited by applicant]
US 20160217723A1 · Kim et al. · 2016 [cited by applicant]
US 20160243699A1 · Kim · 2016 [cited by applicant]
US 20160307369A1 · Freedman et al. · 2016 [cited by applicant]
US 20160314617A1 · Forster et al. · 2016 [cited by applicant]
US 20160354693A1 · Yan et al. · 2016 [cited by applicant]
US 20170132827A1 · Tena et al. · 2017 [cited by applicant]
US 20170221250A1 · Aguado · 2017 [cited by applicant]
US 20170301310A1 · Bonnier et al. · 2017 [cited by applicant]
US 20170301316A1 · Farell · 2017 [cited by applicant]
US 20180122125A1 · Brewster · 2018 [cited by applicant]
US 20180165864A1 · Jin et al. · 2018 [cited by applicant]
US 20180211102A1 · Alsmadi · 2018 [cited by applicant]
US 20180239526A1 · Varanasi et al. · 2018 [cited by applicant]
US 20180293736A1 · Rahimi et al. · 2018 [cited by applicant]
US 20190073826A1 · Bailey et al. · 2019 [cited by applicant]
US 20190147224A1 · Li et al. · 2019 [cited by applicant]
US 20190228316A1 · Felsen et al. · 2019 [cited by applicant]
US 20190295305A1 · Yang et al. · 2019 [cited by applicant]
US 20190303658A1 · Ando et al. · 2019 [cited by applicant]
US 20190340803A1 · Comer · 2019 [cited by applicant]
US 20190392587A1 · Nowozin et al. · 2019 [cited by applicant]
US 20200005138A1 · Wedig et al. · 2020 [cited by applicant]
US 20200035009A1 · Comer et al. · 2020 [cited by applicant]
US 20200035010A1 · Kim · 2020 [cited by applicant]
US 20200058148A1 · Blaylock et al. · 2020 [cited by applicant]
US 20200222757A1 · Yang et al. · 2020 [cited by applicant]
US 20200294299A1 · Rigiroli et al. · 2020 [cited by applicant]
US 20200353311A1 · Ganguly et al. · 2020 [cited by applicant]
US 20200388065A1 · Miller, IV et al. · 2020 [cited by applicant]
US 20200402284A1 · Saragih · 2020 [cited by examiner]
US 20210019916A1 · Andreev · 2021 [cited by applicant]
US 20210166459A1 · Miller, IV · 2021 [cited by applicant]
US 20210217184A1 · Payne et al. · 2021 [cited by applicant]
US 20210220739A1 · Zinno et al. · 2021 [cited by applicant]
US 20210292824A1 · Zhang et al. · 2021 [cited by applicant]
US 20210312689A1 · Akhoundi et al. · 2021 [cited by applicant]
US 20210335004A1 · Zohar et al. · 2021 [cited by applicant]
US 20210375021A1 · Starke et al. · 2021 [cited by applicant]
US 20210383585A1 · Zhao et al. · 2021 [cited by applicant]
US 20210406765A1 · Zhang et al. · 2021 [cited by applicant]
US 20220035443A1 · Winold et al. · 2022 [cited by applicant]
US 20220068000A1 · Herman et al. · 2022 [cited by applicant]
US 20220076472A1 · Bocquelet et al. · 2022 [cited by applicant]
US 20220101646A1 · McDonald · 2022 [cited by examiner]
US 20220148335A1 · Liu · 2022 [cited by applicant]
US 20220215232A1 · Pardeshi et al. · 2022 [cited by applicant]
US 20220230376A1 · Rozantsev et al. · 2022 [cited by applicant]
US 20220254157A1 · Fu et al. · 2022 [cited by applicant]
US 20220292751A1 · Kimura · 2022 [cited by examiner]
US 20220319087A1 · Zhang · 2022 [cited by examiner]
US 20220379167A1 · Lee · 2022 [cited by applicant]
US 20230010480A1 · Li et al. · 2023 [cited by applicant]
US 20230123820A1 · Wang · 2023 [cited by applicant]
US 20230186541A1 · Starke et al. · 2023 [cited by applicant]
US 20230186543A1 · Starke et al. · 2023 [cited by applicant]
US 20230237724A1 · Starke et al. · 2023 [cited by applicant]
US 20230267668A1 · Starke et al. · 2023 [cited by applicant]
US 20230300667A1 · Baek · 2023 [cited by applicant]
US 20230306667A1 · Hopkins · 2023 [cited by applicant]
US 20230310998A1 · Starke et al. · 2023 [cited by applicant]
US 20230326113A1 · Hellge · 2023 [cited by applicant]
US 20230334744A1 · Liu · 2023 [cited by applicant]
US 20230394735A1 · Shi et al. · 2023 [cited by applicant]
US 20240257429A1 · Starke et al. · 2024 [cited by applicant]
US 20240307779A1 · Wu · 2024 [cited by applicant]
US 20240331293A1 · Borovikov et al. · 2024 [cited by applicant]
CN 102509272A · 2012 [cited by applicant]
CN 103546736A · 2014 [cited by applicant]
CN 105405380A · 2016 [cited by applicant]
CN 105825778A · 2016 [cited by applicant]
CN 110039546A · 2019 [cited by applicant]
JP 2018520820A · 2018 [cited by applicant]
JP 2019162400A · 2019 [cited by applicant]
WO WO2019184633A1 · 2019 [cited by applicant]
WO WO2020204948A1 · 2020 [cited by examiner]
Anagnostopoulos et al., “Intelligent modification for the daltonization process,” International Conference on Computer Vision, Published in 2007 by Applied Computer Science Group of digitized paintings. [cited by applicant]
Andersson et al., “Virtual Texturing with WebGL,” Master's thesis, Chalmers University of Technology, Gothenburg, Sweden (2012). [cited by applicant]
Avenali, “Color Vision Deficiency and Video Games,” The Savannah College of Art and Design, Mar. 2013. [cited by applicant]
Badlani et al., “A Novel Technique for Modification of Images for Deuteranopic Viewers,” May 2016. [cited by applicant]
Belytschko et al., “Assumed strain stabilization of the eight node hexahedral element,” Computer Methods in Applied Mechanics and Engineering, vol. 105(2), pp. 225-260 (1993), 36 pages. [cited by applicant]
Belytschko et al., “Nonlinear Finite Elements for Continua and Structures,” Second Edition, Wiley (Jan. 2014), 727 pages (uploaded in 3 parts). [cited by applicant]
Blanz et al., “A morphable model for the synthesis of 3D faces,” In Proceedings of the 26th annual conference on Computer graphics and interactive techniques Jul. 1, 1999 (pp. 187-194). ACM Press/Addison-Wesley Publishi… [cited by applicant]
Blanz et al., “Reanimating Faces in Images and Video,” Sep. 2003, vol. 22, No. 3, pp. 641-650, 10 pages. [cited by applicant]
Chao et al., “A Simple Geometric Model for Elastic Deformations,” 2010, 6 pgs. [cited by applicant]
Clavet, “Motion matching and the road to next-gen animation,” In Proc. of GDC. 2016 (Year: 2016). [cited by applicant]
Cook et al., “Concepts and Applications of Finite Element Analysis,” 1989, Sections 6-11 through 6-14. [cited by applicant]
Cournoyer et al., “Massive Crowd on Assassin's Creed Unity: AI Recycling,” Mar. 2, 2015, 55 pages. [cited by applicant]
Dick et al., “A Hexahedral Multigrid Approach for Simulating Cuts in Deformable Objects,” IEEE Transactions on Visualization and Computer Graphics, vol. X, No. X, Jul. 2010, 16 pgs. [cited by applicant]
Diziol et al., “Robust Real-Time Deformation of Incompressible Surface Meshes,” to appear in Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (2011), 10 pgs. [cited by applicant]
Dudash, “Skinned instancing,” NVidia white paper(2007). [cited by applicant]
Fikkkan, “Incremental loading of terrain textures,” MS thesis. Institutt for datateknikk og informasjonsvitenskap, 2013. [cited by applicant]
Geijtenbeek et al., “Interactive Character Animation using Simulated Physics,” Games and Virtual Worlds, Utrecht University, The Netherlands, The Eurographics Association 2011, 23 pgs. [cited by applicant]
Geijtenbeek et al. “Interactive Character Animation Using Simulated Physics: A State-of-the-Art Review,” Computer Graphics forum, vol. 31, 2012 (Year: 2012), 24 pgs. [cited by applicant]
Georgii et al., “Corotated Finite Elements Made Fast and Stable,” Workshop in Virtual Reality Interaction and Physical Simulation VRIPHYS (2008), 9 pgs. [cited by applicant]
Habbie et al., “A Recurrent Variational Autoencoder for Human Motion Synthesis,” 2017, in 12 pages. [cited by applicant]
Halder et al., “Image Color Transformation for Deuteranopia Patients using Daltonization,” IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) vol. 5, Issue 5, Ver. I (Sep.-Oct. 2015), pp. 15-20. [cited by applicant]
Han et al., “On-line Real-time Physics-based Predictive Motion Control with Balance Recovery,” Eurographics, vol. 33(2), 2014, 10 pages. [cited by applicant]
Hernandez et al., “Simulating and visualizing real-time crowds on GPU clusters,” Computacion y Sistemas 18.4 (2014): 651-664. [cited by applicant]
Holden et al., “Phase-functioned neural networks for character control,” ACM Transactions on Graphics (TOG). Jul. 20, 2017;36(4): 1-3. (Year: 2017). [cited by applicant]
Hu et al., “Face recognition by an albedo based 3D morphable model,” In Biometrics (IJCB), 2014 IEEE International Joint Conference on Sep. 29, 2014 (pp. 1-8). IEEE. [cited by applicant]
Hu, “Face Analysis using 3D Morphable Models,” Ph.D. Thesis, University of Surrey, Apr. 2015, pp. 1-112. [cited by applicant]
Irving et al., “Invertible Finite Elements for Robust Simulation of Large Deformation,” Eurographics/ACM SIGGRAPH Symposium on Computer Animation (2004), 11 pgs. [cited by applicant]
Kaufmann et al., “Flexible Simulation of Deformable Models Using Discontinuous Galerkin FEM,” Oct. 1, 2008, 20 pgs. [cited by applicant]
Kavan et al., “Skinning with Dual Quaternions,” 2007, 8 pgs. [cited by applicant]
Kim et al., “Long Range Attachments—A Method to Simulate Inextensible Clothing in Computer Games,” Eurographics/ACM SIGGRAPH Symposium on Computer Animation (2012), 6 pgs. [cited by applicant]
Klein, “Rendering Textures Up Close in a 3D Environment Using Adaptive Micro-Texturing,” Diss. Mills College, 2012. [cited by applicant]
Komura et al., “Animating reactive motion using momentum-based inverse kinematics,” Computer Animation and Virtual Worlds, vol. 16, pp. 213-223, 2005, 11 pages. [cited by applicant]
Lee, Y. et al., “Motion Fields for Interactive Character Animation,” University of Washington, Bungie, Adobe Systems, 8 pgs, obtained Mar. 20, 2015. [cited by applicant]
Levine, S. et al., “Continuous Character Control with Low-Dimensional Embeddings,” Stanford University, University of Washington, 10 pgs, obtained Mar. 20, 2015. [cited by applicant]
Macklin et al., “Position Based Fluids,” to appear in ACM TOG 32(4), 2013, 5 pgs. [cited by applicant]
McAdams et al., “Efficient Elasticity for Character Skinning with Contact and Collisions,” 2011, 11 pgs. [cited by applicant]
McDonnell et al., “Clone attack! perception of crowd variety,” ACM Transactions on Graphics (TOG). vol. 27. No. 3. ACM, 2008. [cited by applicant]
Muller et al., “Meshless Deformations Based on Shape Matching,” SIGGRAPH 2005, 29 pgs. [cited by applicant]
Muller et al., “Adding Physics to Animated Characters with Oriented Particles,” Workshop on Virtual Reality Interaction and Physical Simulation VRIPHYS (2011), 10 pgs. [cited by applicant]
Muller et al., “Real Time Dynamic Fracture with Volumetric Approximate Convex Decompositions,” ACM Transactions of Graphics, Jul. 2013, 11 pgs. [cited by applicant]
Muller et al., “Position Based Dynamics,” VRIPHYS 2006, 2014.10.21, Computer Graphics, Korea University, 23 pgs. [cited by applicant]
Musse et al., “Hierarchical model for real time simulation of virtual human crowds,” IEEE Transactions on Visualization and Computer Graphics 7.2 (2001): 152-164. [cited by applicant]
Nguyen et al., “Adaptive Dynamics With Hybrid Response,” 2012, 4 pages. [cited by applicant]
O'Brien et al., “Graphical Modeling and Animation of Brittle Fracture,” GVU Center and College of Computing, Georgia Institute of Technology, Reprinted from the Proceedings of ACM SIGGRAPH 99, 10 pgs, dated 1999. [cited by applicant]
Orin et al., “Centroidal dynamics of a humanoid robot,” Auton Robot, vol. 35, pp. 161-176, 2013, 18 pages. [cited by applicant]
Parker et al., “Real-Time Deformation and Fracture in a Game Environment,” Eurographics/ACM SIGGRAPH Symposium on Computer Animation (2009), 12 pgs. [cited by applicant]
Pelechano et al., “Controlling individual agents in high-density crowd simulation,” Proceedings of the 2007 ACM SIGGRAPH/Eurographics symposium on Computer animation. Eurographics Association, 2007. APA. [cited by applicant]
Rivers et al., “FastLSM: Fast Lattice Shape Matching for Robust Real-Time Deformation,” ACM Transactions on Graphics, vol. 26, No. 3, Article 82, Publication date: Jul. 2007, 6 pgs. [cited by applicant]
Ruiz, “Reducing memory requirements for diverse animated crowds,” Proceedings of Motion on Games. ACM, 2013. [cited by applicant]
Rungjiratananon et al., “Elastic Rod Simulation by Chain Shape Matching with Twisting Effect,” SIGGRAPH Asia 2010, Seoul, South Korea, Dec. 15-18, 2010, ISBN 978-1-4503-0439-9/10/0012, 2 pgs. [cited by applicant]
Seo et al., “Compression and Direct Manipulation of Complex Blendshape Models,” In ACM Transactions on Graphics (TOG) Dec. 12, 2011 (vol. 30, No. 6, p. 164). ACM. (Year: 2011), 10 pgs. [cited by applicant]
Sifakis, Eftychios D., “FEM Simulations of 3D Deformable Solids: A Practioner's Guide to Theory, Discretization and Model Reduction. Part One: The Classical FEM Method and Discretization Methodology,” SIGGRAPH 2012 Cour… [cited by applicant]
Starke et al., “Local motion phases for learning multi-contact character movements,” ACM Transactions on Graphics (TOG). Jul. 8, 2020;39(4):54-1 (Year: 2020). [cited by applicant]
Stomakhin et al., “Energetically Consistent Invertible Elasticity,” Eurographics/ACM SIGRAPH Symposium on Computer Animation (2012), 9 pgs. [cited by applicant]
Thalmann et al., “Crowd rendering,” Crowd Simulation. Springer London, 2013. 195-227. [cited by applicant]
Thalmann et al., “Modeling of Populations,” Crowd Simulation. Springer London, 2013. 31-80. [cited by applicant]
Treuille, A. et al., “Near-optimal Character Animation with Continuous Control,” University of Washington, 2007, 7 pgs. [cited by applicant]
Ulicny et al., “Crowd simulation for interactive virtual environments and VR training systems,” Computer Animation and Simulation 2001 (2001 ): 163-170. [cited by applicant]
Vaillant et al., “Implicit Skinning: Real-Time Skin Deformation with Contact Modeling,” (2013) ACM Transactions on Graphics, vol. 32 (n° 4). pp. 1-11. ISSN 0730-0301, 12 pgs. [cited by applicant]
Vigueras et al. “A distributed visualization system for crowd simulations,” Integrated Computer-Aided Engineering 18.4 (2011 ): 349-363. [cited by applicant]
Wu et al., “Goal-Directed Stepping with Momentum Control,” Eurographics/ ACM SIGGRAPH Symposium on Computer Animation, 2010, 6 pages. [cited by applicant]
Zhang et al., “Mode-adaptive neural networks for quadruped motion control. ACM Transactions on Graphics (TOG),” Jul. 30, 2018;37(4): 1-1. (Year: 2018). [cited by applicant]
Min et al., “Interactive Generation of Human Animation with Deformable Motion Models” ACM Transactions on Graphics, vol. 29, Issue 1, (Year: 2009), 12 pgs. [cited by applicant]
Shikai, “Method, Device, Equipment and Storage for generating walking animation of Virtual Character”, English Translation of CN 202111374361.9, Nov. 19, 2021 (Year: 2021). [cited by applicant]
Yamane, et al., “Natural Motion Animation through Constraining and Deconstraining at Will” (Year: 2003). [cited by applicant]