IP Library › Granted Patent US 12,725,341
Granted Patent B2
US 12,725,341 · App. 18/795,814 · Granted Sep 1, 2026

Generating a background that allows a first avatar to take part in an activity with a second avatar

Inventors: Ayla Mandel (Los Angeles, CA); David Mandel (Los Angeles, CA); Stephen D. Williams (Sunnyvale, CA)
Assignee: IMPLEMENTATION APPS LLC
G06T13/40G06N5/02G06N5/04G06T13/80
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 12,725,341
App. No.
18/795,814
Filed
Aug 6, 2024
Granted
Sep 1, 2026
Kind
B2
Art Unit
2612
USPC
345/474
Abstract

A user may create an avatar and/or animated sequence illustrating a particular object or living being performing a certain activity, using images of portions of the object or living being extracted from a still image or set of still images of the object or living being.

Claims (54)

1 . A method comprising:

in a device:

receiving input from a user;

generating a first avatar depicting the user, wherein the generating comprises mapping texture information extracted from a composite image of the user onto a movable model having predefined reference points corresponding to anatomical features;

adjusting appearance aspects and motion aspects of the first avatar, wherein the motion aspects are controlled using a motion template comprising a time-ordered set of positional data for the predefined reference points;

generating a second avatar; and

generating a background for the first avatar and the second avatar, wherein:

the background comprises a first element that enables the first avatar to take part in an activity with the second avatar,

the background comprises a second element, different than the first element, that is selected from a plurality of images according to the input from the user,

the plurality of images are associated with a theme, and

the device animates the first avatar by moving the predefined reference points according to the motion template and rendering updated positions of the mapped texture information.

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

in the device:

configuring a movement of one or more reference points in the first avatar via a motion template.

3 . The method of claim 2 , wherein the movement is described according to adjacent video frames in a sequence of video frames provided by the user.

4 . The method of claim 2 , wherein the movement is described according to a time ordered list of distance vectors.

5 . The method of claim 2 , wherein the movement is described according to a mathematical formula that determines a position, of the one or more reference points, over time.

6 . The method of claim 2 , wherein the movement is in three dimensions.

7 . The method of claim 1 , wherein the second avatar depicts a public personality.

8 . The method of claim 1 , wherein the activity is a show.

9 . The method of claim 1 , wherein the activity comprises the first avatar talking with the second avatar.

10 . The method of claim 1 , wherein the input from the user comprises one or more of a subject matter, a level of importance, a timeliness and a classification of geographic relevance.

11 . The method of claim 1 , wherein the composite image comprises a plurality of objects or living beings and prior to the mapping, an object recognition algorithm is configured to identify portions of the composite image corresponding to the user.

12 . The method of claim 1 , wherein the predefined reference points correspond to joints or endpoints of skeletal elements of a human body.

13 . The method of claim 1 , wherein the motion template comprises a time-ordered list of vectors defining movement of the predefined reference points.

14 . The method of claim 1 , wherein the motion template comprises a function that determines positions of the predefined reference points over time.

15 . The method of claim 1 , wherein the mapping comprises applying the texture information to a surface of a three-dimensional model.

16 . The method of claim 1 , wherein the animating comprises generating visual features based on relative motion of the predefined reference points.

17 . The method of claim 1 , wherein the composite image is selected from a plurality of stored images based on a match to the user.

18 . A system comprising:

a device operable to:

receive input from a user;

generate a first avatar depicting the user, wherein the generating comprises mapping texture information extracted from a composite image of the user onto a movable model having predefined reference points corresponding to anatomical features;

adjust appearance aspects and motion aspects of the first avatar, wherein the motion aspects are controlled using a motion template comprising a time-ordered set of positional data for the predefined reference points;

generate a second avatar; and

generate a background for the first avatar and the second avatar, wherein:

the background comprises a first element that enables the first avatar to take part in an activity with the second avatar,

the background comprises a second element, different than the first element, that is selected from a plurality of images according to the input from the user,

the plurality of images are associated with a theme, and

the device is operable to animate the first avatar by moving the predefined reference points according to the motion template and rendering updated positions of the mapped texture information.

19 . The system of claim 18 , wherein the device is operable to:

configure a movement of one or more reference points in the first avatar via a motion template.

20 . The system of claim 19 , wherein the movement is described according to adjacent video frames in a sequence of video frames provided by the user.

21 . The system of claim 19 , wherein the movement is described according to a time ordered list of distance vectors.

22 . The system of claim 19 , wherein the movement is described according to a mathematical formula that determines a position, of the one or more reference points, over time.

23 . The system of claim 19 , wherein the movement is in three dimensions.

24 . The system of claim 18 , wherein the second avatar depicts a public personality.

25 . The system of claim 18 , wherein the activity is a show.

26 . The system of claim 18 , wherein the activity comprises the first avatar talking with the second avatar.

27 . The system of claim 18 , wherein the input from the user comprises one or more of a subject matter, a level of importance, a timeliness and a classification of geographic relevance.

28 . The system of claim 18 , wherein the device is operable to identify portions of the composite image corresponding to the user using an object recognition algorithm prior to mapping.

29 . The system of claim 18 , wherein the predefined reference points correspond to anatomical joints of a human model.

30 . The system of claim 18 , wherein the motion template comprises a time-ordered list of vectors or a function defining movement of the predefined reference points.

31 . The system of claim 18 , wherein the device is operable to render the first avatar by updating mapped texture information in response to movement of the predefined reference points.

Continuity (7)
Continuation 18137163 · Apr 20, 2023
Continuation 18098214 · Jan 18, 2023
Continuation 17314348 · May 7, 2021
Continuation 15231137 · Aug 8, 2016
Continuation 14178525 · Feb 12, 2014
Continuation 13963940 · Aug 9, 2013
Related Publication 20240394948A1 · Nov 28, 2024
References Cited (60)
US 6052123A · Lection et al. · 2000 [cited by applicant]
US 6466213B2 · Bickmore et al. · 2002 [cited by applicant]
US 6697072B2 · Russell et al. · 2004 [cited by applicant]
US 7468729B1 · Levinson · 2008 [cited by applicant]
US 7707520B2 · Ashtekar et al. · 2010 [cited by applicant]
US 7859551B2 · Bulman et al. · 2010 [cited by applicant]
US 8130225B2 · Sullivan et al. · 2012 [cited by applicant]
US 8144153B1 · Sullivan et al. · 2012 [cited by applicant]
US 8502825B2 · Zalewski et al. · 2013 [cited by applicant]
US 8681158B1 · Sullivan et al. · 2014 [cited by applicant]
US 9177410B2 · Mandel et al. · 2015 [cited by applicant]
US 9412192B2 · Mandel et al. · 2016 [cited by applicant]
US 10155168B2 · Blackstock et al. · 2018 [cited by applicant]
US 11127183B2 · Mandel et al. · 2021 [cited by applicant]
US 11600033B2 · Mandel et al. · 2023 [cited by applicant]
US 11670033B1 · Mandel · 2023 [cited by examiner]
US 12094045B2 · Mandel · 2024 [cited by examiner]
US 20030038800A1 · Kawahara · 2003 [cited by applicant]
US 20050223328A1 · Ashtekar et al. · 2005 [cited by applicant]
US 20070168863A1 · Blattner et al. · 2007 [cited by applicant]
US 20070245881A1 · Egozy · 2007 [cited by examiner]
US 20080225044A1 · Huang et al. · 2008 [cited by applicant]
US 20090079743A1 · Pearson · 2009 [cited by examiner]
US 20090257576A1 · Wellard et al. · 2009 [cited by applicant]
US 20100083324A1 · Smith et al. · 2010 [cited by applicant]
US 20100309226A1 · Quack et al. · 2010 [cited by applicant]
US 20110007079A1 · Perez · 2011 [cited by examiner]
US 20110148857A1 · Krupka et al. · 2011 [cited by applicant]
US 20110228976A1 · Fitzgibbon · 2011 [cited by examiner]
US 20110239147A1 · Shim et al. · 2011 [cited by applicant]
US 20110292051A1 · Nelson et al. · 2011 [cited by applicant]
US 20110305376A1 · Neff · 2011 [cited by applicant]
US 20120130717A1 · Xu et al. · 2012 [cited by applicant]
US 20130086519A1 · Fino · 2013 [cited by applicant]
US 20130159228A1 · Meijer et al. · 2013 [cited by applicant]
US 20130243245A1 · Bill · 2013 [cited by applicant]
US 20130266927A1 · Mann · 2013 [cited by examiner]
US 20130275352A1 · Servi et al. · 2013 [cited by applicant]
US 20130287365A1 · Basapur et al. · 2013 [cited by applicant]
US 20140160149A1 · Blackstock et al. · 2014 [cited by applicant]
US 20140229850A1 · Makofsky · 2014 [cited by examiner]
US 20140313208A1 · Filev et al. · 2014 [cited by applicant]
US 20210243503A1 · Kotsopoulos et al. · 2021 [cited by applicant]
US 20230133976A1 · Nims · 2023 [cited by examiner]
JP 3859020B2 · 2006 [cited by examiner]
KR 101270151B1 · 2013 [cited by examiner]
Vasalou et. al., “Me, myself and I: The role of interactional context on self-presentation through avatars” Computers in human behavior 25.2 (2009): 510-520. (Year: 2009). [cited by examiner]
Souppouris, A., Put Your Face on a Vampire Hunter With Square Enix's 'Bloodmasque,' dated Jul. 25, 2013, http://www.theverge.com/2013/7/25/4555622/bloodmasque-ios-square-enix-hands-on, 2 pages, (retrieved Nov. 8, 2013). [cited by applicant]
A New Physical Model with Multilayer Architecture for Facial Expression Animation Using Dynamic Adaptive Mesh by Yu Zhang pp. 339-352 May/Jun. 2004 IEEE Transactions on Visualization and Computer Graphics, Appendix pp. … [cited by applicant]
“Textons, the elements of texture perception, and their interactions” by B. Julesz, Nature, 290(5802):91-97, Mar. 1981. [cited by applicant]
“Contour and Texture Analysis for Image Segmentation” by Malik, et al., International Journal of Computer Vision, 43 (1):7-27, Jun. 2001. [cited by applicant]
Lubomir Bourdev, PhD., “Poselets and Their Applications in High-Level Computer Vision”, a Thesis of Lubomir Bourdev, University of California, Berkeley, Spring, 2011, pp. 1-66, found at <www.eecs.berkeley.edu/~Ibourdev/… [cited by applicant]
Carl Yuheng Ren, et al., “gSLIC—a real-time implementation of SLIC superpixel segmentation,” Jun. 28, 2011, pp. 1-6, University of Oxford, Department of Engineering Science, Oxford, UK, found at <http://www.robots.ox.ac… [cited by applicant]
Bo Wu, et al., “Simultaneous Object Detection and Segmentation by Boosting Local Shape Feature based Classifier,” 2007, 8 pages, IEEE Conference on Computer Vision and Pattern Recognition 2007 (CPVR '07), Found at <http… [cited by applicant]
Jamie Shotton, et al., “TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context,” Jul. 2, 2007, pp. 1-30, Jamie Shotton (Machine Intelligence… [cited by applicant]
Hyung Il Koo, et al., “Boosting Image Segmentation,” 2008, pp. 3192-3195, 15th IEEE Conference on Image Processing 2008 (ICIP 2008), School of Electrical Engineering, Seoul National University, Seoul 151-744 Korea, foun… [cited by applicant]
Huynh Thi Thanh Binh, et al., “Improving image segmentation using genetic algorithm,” 2012, pp. 18-23, Huynh Thi Thanh Binh and Mai Dinh Loi (School of Information and Communication Technology) and Nguyen, Thi Thuy (Dep… [cited by applicant]
Brian Holt, et al., “Putting the Pieces Together: Connected Poselets for Human Pose Estimation,” 6 p. 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (CVSSP), University of Surrey, Guild… [cited by applicant]
Song-Chun Zhu, et al., “What Are Textons?,” European Conference on Computer Vision (ECCV) 2002, vol. 4, LNCS 2353, Copyright 2002, Springer-Verlag Berlin Heidelberg, pp. 793-807. [cited by applicant]
Chai et al. “Vision-based control for 3D facial animation”, published 2003. [cited by applicant]