IP Library Granted Patent US 12,400,401
Granted Patent B2
US 12,400,401 · App. 17/920,716 · Granted Aug 26, 2025

Measurement space deformation interpolation

Inventor: Dmitriy Vladlenovich Pinskiy (Woodland Hills, CA)
Assignee: SpreeAI Corporation
G06T17/20G06T13/40G06T15/04G06T19/20G06T2210/16G06T2219/2021
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 12,400,401
App. No.
17/920,716
Granted
Aug 26, 2025
Kind
B2
Abstract

Computer implemented measurement space deformation method and apparatus. A method embodiment comprises defining a measurement space as a multi-dimensional space, populating the measurement space with a set of pre-computed example avatars, searching the measurement space for a subset of example avatars, and interpolating between the example avatars of the subset.

Claims (31)

1. A computer implemented measurement space deformation method for generating an electronic animation of a representation of a user, said method comprising the steps of:

defining a multi-dimensional measurement space, each dimension of the multi-dimensional measurement space corresponding to at least one body measurement category of a human body;

populating the multi-dimensional measurement space with a set of pre-computed example avatars, each example avatar in the set having dimensions corresponding to multiple body measurement categories of the human body, the multiple body measurement categories including at least two of hip length, hip width, bust length, bust width, arm length, leg length, or body height;

searching the measurement space for a subset of example avatars having avatar dimension values near user dimension values of the user for the multiple body measurement categories, the user dimension values being obtained from physical measurements of a body of the user, each example avatar in the subset having a subset of the avatar dimension values within a predetermined threshold of the user dimension values of the user for at least one body measurement category of the human body; and

interpolating between the subset of the avatar dimension values of the example avatars of the subset, body measurement category by body measurement category, based upon the user dimension values of the user for the multiple measurement categories of the human body, to generate a frame of the electronic animation that represents a physical appearance of the user, the electronic animation usable to simulate how one or more garments appear on the body of the user.

2. The method of claim 1 , wherein the interpolating comprises constructing a dependency graph of body measurement category dependencies to facilitate a determination of an order in which the avatar dimension values are to be interpolated based on the multiple body measurement categories.

3. The method of claim 1 , wherein the populating comprises placing the set of pre-computed example avatars in the multi-dimensional measurement space based upon the avatar dimension values of the example avatars, each body measurement within each body measurement category being assigned a weight that indicates how much the avatar dimension values influence mesh vertices on the frame of the electronic animation.

4. The method of claim 1 , wherein the user is garmented.

5. The method of claim 4 , wherein the method further comprises presenting different sizes of a garment on the electronic animation.

6. The method of claim 1 , wherein one or more first body measurements of at least one body measurement category of the multi-dimensional measurement space depend on one or more second body measurements, the one or more first body measurements being interpolated after interpolation of the one or more second body measurements.

7. The method of claim 1 , wherein the interpolating comprises interpolating between the avatar dimension values of a first pair of example avatars for a first body measurement category and interpolating between the avatar dimension values of a second pair of example avatars for a second body measurement category, the first body measurement category including one or more length measurements and the second body measurement category including one or more width measurements.

8. An apparatus configured to generate an electronic animation of a representation of a user, said apparatus comprising:

a multi-dimensional measurement space based upon body measurement categories of a human body, each dimension of the multi-dimensional measurement space corresponding to at least one body measurement category of a human body;

coupled to the measurement space, a computational module for computing a set of example avatars, each example avatar in the set having dimensions corresponding to multiple body measurement categories of the human body, the multiple body measurement categories including at least two of hip length, hip width, bust length, bust width, arm length, leg length, or body height; and

coupled to the computational module, an interpolation module configured to interpolate between a subset of avatar dimension values of example avatars, body measurement category by body measurement category, based upon user dimension values of the user for multiple measurement categories, to generate a frame of an electronic animation of the user representation that represents a physical appearance of the user, the electronic animation usable to simulate how one or more garments appear on the body of the user, the user dimension values being obtained from physical measurements of a body of the user, each example avatar in the subset having a subset of the avatar dimension values within a predetermined threshold of the user dimension values of the user for at least one body measurement category of the human body.

9. The apparatus of claim 8 , wherein the interpolation module is configured to interpolate by constructing a dependency graph of body measurement category dependencies to facilitate a determination of an order in which the avatar dimension values are to be interpolated based on the multiple body measurement categories.

10. The apparatus of claim 8 , wherein the computational module is further configured to populate the multi-dimensional space by placing a set of pre-computed example avatars in the multi-dimensional measurement space based upon the avatar dimension values of the example avatars, each body measurement within each body measurement category being assigned a weight that indicates how much the avatar dimension values influence mesh vertices on the frame of the electronic animation.

11. The apparatus of claim 8 , wherein the user is garmented.

12. The apparatus of claim 11 , wherein the computational module is further configured to present different sizes of a garment on the electronic animation.

13. The apparatus of claim 8 , wherein one or more first body measurements of at least one body measurement category of the multi-dimensional measurement space depend on one or more second body measurements, the one or more first body measurements being interpolated after interpolation of the one or more second body measurements.

14. The apparatus of claim 8 , wherein the interpolation module is further configured to interpolate between the avatar dimension values of a first pair of example avatars for a first body measurement category and interpolate between the avatar dimension values of a second pair of example avatars for a second body measurement category, the first body measurement category including one or more length measurements and the second body measurement category including one or more width measurements.

15. One or more non-transitory computer-readable storage media storing instructions that, responsive to execution by a processing device, cause the processing device to:

define a multi-dimensional measurement space, with each dimension of the multi-dimensional measurement space corresponding to at least one body measurement category of a human body;

populate the multi-dimensional measurement space with a set of pre-computed example avatars, each example avatar in the set having dimensions corresponding to multiple body measurement categories of the human body, the multiple body measurement categories including at least two of hip length, hip width, bust length, bust width, arm length, leg length, or body height;

search the measurement space for a subset of example avatars having avatar dimension values near user dimension values of the user for the multiple body measurement categories, the user dimension values being obtained from physical measurements of a body of the user, each example avatar in the subset having a subset of the avatar dimension values within a predetermined threshold of the user dimension values of the user for at least one body measurement category of the human body; and

interpolate between the subset of the avatar dimension values of the example avatars of the subset, body measurement category by body measurement category, based upon the user dimension values of the user for the multiple measurement categories of the human body, to generate a frame of the electronic animation that represents a physical appearance of the user, the electronic animation usable to simulate how one or more garments appear on the body of the user.

16. The one or more non-transitory computer-readable storage media of claim 15 , wherein the user is garmented.

17. The one or more non-transitory computer-readable storage media of claim 16 , wherein the one or more computer-readable storage media store additional instructions that, responsive to execution by the processing device, cause the processing device to present different sizes of a garment on the electronic animation.

18. The one or more non-transitory computer-readable storage media of claim 15 , wherein the one or more computer-readable storage media store additional instructions that, responsive to execution by the processing device, cause the processing device to interpolate by constructing a dependency graph of body measurement category dependencies to facilitate a determination of an order in which the avatar dimension values are to be interpolated based on the multiple body measurement categories.

19. The one or more non-transitory computer-readable storage media of claim 15 , wherein the one or more computer-readable storage media store additional instructions that, responsive to execution by the processing device, cause the processing device to populate the multi-dimensional space by placing a set of pre-computed example avatars in the multi-dimensional measurement space based upon the avatar dimension values of the example avatars, each body measurement within each body measurement category being assigned a weight that indicates how much the avatar dimension values influence mesh vertices on the frame of the electronic animation.

20. The one or more non-transitory computer-readable storage media of claim 15 , wherein the one or more computer-readable storage media store additional instructions that, responsive to execution by the processing device, cause the processing device to interpolate between the avatar dimension values of a first pair of example avatars for a first body measurement category and interpolate between the avatar dimension values of a second pair of example avatars for a second body measurement category, the first body measurement category including one or more length measurements and the second body measurement category including one or more width measurements.

Assignments (2)
CHANGE OF NAME Recorded Nov 29, 2023
From: SPREE3D CORPORATION
To: SPREEAI CORPORATION
Reel/Frame 065714/0419 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 27, 2022
From: PINSKIY, DMITRIY VLADLENOVICH
To: SPREE3D CORPORATION
Reel/Frame 061565/0517 →
Continuity (3)
Continuation 17357394 · Jun 24, 2021
Provisional Application 63132173 · Dec 30, 2020
Related Publication 20230169726A1 · Jun 1, 2023
References Cited (73)
US 6466215B1 · Matsuda et al. · 2002 [cited by applicant]
US 6546309B1 · Gazzuolo · 2003 [cited by applicant]
US 6731287B1 · Erdem · 2004 [cited by applicant]
US 10255681B2 · Price et al. · 2019 [cited by applicant]
US 10936853B1 · Sethi et al. · 2021 [cited by applicant]
US 20070091085A1 · Wang et al. · 2007 [cited by applicant]
US 20070188502A1 · Bishop · 2007 [cited by applicant]
US 20090066700A1 · Harding et al. · 2009 [cited by applicant]
US 20100030578A1 · Siddique · 2010 [cited by examiner]
US 20100111370A1 · Black · 2010 [cited by examiner]
US 20100306082A1 · Wolper · 2010 [cited by examiner]
US 20110292034A1 · Corazza · 2011 [cited by examiner]
US 20130100140A1 · Ye et al. · 2013 [cited by applicant]
US 20130314412A1 · Gravois et al. · 2013 [cited by applicant]
US 20140176565A1 · Adeyoola · 2014 [cited by examiner]
US 20160163084A1 · Corazza et al. · 2016 [cited by applicant]
US 20160247017A1 · Sareen et al. · 2016 [cited by applicant]
US 20160284018A1 · Adeyoola et al. · 2016 [cited by applicant]
US 20170004657A1 · Zagel et al. · 2017 [cited by applicant]
US 20170080346A1 · Abbas · 2017 [cited by applicant]
US 20180047200A1 · O'Hara et al. · 2018 [cited by applicant]
US 20180197347A1 · Tomizuka · 2018 [cited by applicant]
US 20180240280A1 · Chen et al. · 2018 [cited by applicant]
US 20180240281A1 · Vincelette · 2018 [cited by applicant]
US 20190122424A1 · Moore · 2019 [cited by examiner]
US 20190130649A1 · O'brien et al. · 2019 [cited by applicant]
US 20190266806A1 · Aluru · 2019 [cited by examiner]
US 20190287301A1 · Colbert · 2019 [cited by applicant]
US 20190371032A1 · Scapel et al. · 2019 [cited by applicant]
US 20200126316A1 · Sharma et al. · 2020 [cited by applicant]
US 20200234508A1 · Shaburov et al. · 2020 [cited by applicant]
US 20200258280A1 · Park et al. · 2020 [cited by applicant]
US 20200294294A1 · Petriv et al. · 2020 [cited by applicant]
US 20200306640A1 · Kolen et al. · 2020 [cited by applicant]
US 20200320769A1 · Chen et al. · 2020 [cited by applicant]
US 20200334867A1 · Chen et al. · 2020 [cited by applicant]
US 20200346420A1 · Friedrich · 2020 [cited by applicant]
US 20200364533A1 · Sareen et al. · 2020 [cited by applicant]
US 20200364945A1 · Lin · 2020 [cited by examiner]
US 20200402307A1 · Tanwer et al. · 2020 [cited by applicant]
US 20210049811A1 · Fedyukov et al. · 2021 [cited by applicant]
US 20210150187A1 · Karras et al. · 2021 [cited by applicant]
US 20210303919A1 · Niu · 2021 [cited by applicant]
CN 110930500A · 2020 [cited by applicant]
WO 2014161429A1 · 2014 [cited by applicant]
WO 2017029488A2 · 2017 [cited by applicant]
WO 2017143392A1 · 2017 [cited by applicant]
WO 2018089039A1 · 2018 [cited by applicant]
WO 2018154331A1 · 2018 [cited by applicant]
WO 2019050808A1 · 2019 [cited by applicant]
WO 2019164266A1 · 2019 [cited by applicant]
WO 2020038254A1 · 2020 [cited by applicant]
WO 2020104990A1 · 2020 [cited by applicant]
WO 2022221398A1 · 2022 [cited by applicant]
Burkov, “Neural Head Reenactment with Latent Pose Descriptors”, Procedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, pp. 13766-13795; Oct. 30, 2020. https://arxiv.org/pdf/2004.12… [cited by applicant]
Deng, “Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning”, Computer Vision Foundation Conference, Procedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition … [cited by applicant]
Tripathy, “ICface: Interpretable and Controllable Face Reenactment Using GANs”, Procedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2020, pp. 3385-3394; Jan. 17, 2020. https://arxiv.or… [cited by applicant]
Huang, “Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment”, Procedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020, pp. 7084-7092, 2020, open access v… [cited by applicant]
Thies, “Face2Face: Real-Time Face Capture and Reenactment of RGB Videos”, Jul. 29, 2020; abstract of this paper published in 2016 by IEEE at https://ieeexplore.ieee.org/document/7780631. [cited by applicant]
Zhao, “Joint face alignment and segmentation via deep multi-task learning”, published in Multimedia Tools and Applications 78, 13131-13148 (2019), published by Springer Nature, 1 New York Plaza, Suite 4600, New York, NY… [cited by applicant]
Li, “FaceShifter: Towards High Fidelity and Occlusion Aware Face Swapping”, Peking University and Microsoft Research, Sep. 15, 2020. [email protected] and [email protected]; pdf version availab… [cited by applicant]
Nirkin, “FSGAN: Subject Agnostic Face Swapping and Reenactment”, Computer Vision Foundation, ICCV 2019, open access version, Aug. 2019, https://arxiv.org/pdf/1908.05932.pdf ; also published in Proceedings of the IEEE In… [cited by applicant]
Naruniec, “High-Resolution Neural Face Swapping for Visual Effects”, Eurographics Symposium on Rendering 2020, vol. 39 (2020), No. 4. https://studios.disneyresearch.com/wp-content/uploads/2020/06/High-Resolution-Neural-… [cited by applicant]
Wawrzonowski et al. “Mobile devices' GPUs in cloth dynamics simulation”, Proceedings of the Federated Conference on Computer Science and Information Systems, Prague, Czech Republic, 2017, pp. 1283-1290. Retrieved on Feb… [cited by applicant]
“Goes, F. et al., ““Garment Refitting for Digital Characters””, SIGGRAPH '20 Talks, Aug. 17, 2020, Virtual Event, USA; 2 pages. ACM ISBN 978-1-4503-7971-7/20/08. https://doi.org/10.1145/3388767.3407348”. [cited by applicant]
Lewis et al., “Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation”, SIGGRAPH 2000, New Orleans, Louisiana, USA, pp. 165-172. [cited by applicant]
Neophytou et al., “Shape and Pose Space Deformation for Subject Specific Animation”, Centre for Vision Speech and Signal Processing (CVSSP), University of Surrey, Guildford, United Kingdom; IEEE Conference Publication, … [cited by applicant]
Pose space deformation, article in Wikipedia, downloaded Jul. 29, 2022, 2 pages. [cited by applicant]
Kim et al., “Deep Video Portraits”, ACM Trans. Graph, vol. 37, No. 4, Article 163; published online May 29, 2018, pp. 163:1-14; Association for Computing Machinery, U.S.A. https://arxiv.org/pdf/1805.11714.pdf. [cited by applicant]
“Extended European Search Report”, European Application No. 22788638.9, Dec. 13, 2024, 7 pages. [cited by applicant]
“Extended European Search Report”, EP Application No. 22746447.6, Dec. 16, 2024, 6 pages. [cited by applicant]
“EP Search Report”, EP Application No. 22788848.4, Jan. 20, 2025, 6 pages. [cited by applicant]
Lewis, et al., “Vogue: Try-On by StyleGAN Interpolation Optimization”, Cornell University Library, Ithaca NY, Jan. 6, 2021, 15 pages. [cited by applicant]