IP Library › Granted Patent US 12,456,259
Granted Patent B2
US 12,456,259 · App. 18/181,232 · Granted Oct 28, 2025

Editing three-dimensional models utilizing implicit function handles

Inventors: Uday Kusupati (Laussanne, CH); Jean Thiery (Paris, FR); Adrien Kaiser (Lyons, FR)
Assignee: Adobe Inc.
G06T17/205
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 12,456,259
App. No.
18/181,232
Granted
Oct 28, 2025
Kind
B2
Abstract

Methods, systems, and non-transitory computer readable media are disclosed for transferring modifications or deformations from a three-dimensional model of one type to a three-dimensional model of another type. In some embodiments, the disclosed systems receive an indication of a user interaction defining a modification to a three-dimensional model. In some cases, the disclosed systems modify an implicit function corresponding to the three-dimensional model in response to the user interaction. In certain embodiments, the disclosed systems generate a modified three-dimensional model by transferring the modification from the implicit function to the three-dimensional model. Further, in some embodiments, the disclosed systems provide the modified three-dimensional model for display on a client device.

Claims (52)

1. A method comprising:

fitting an implicit function to a three-dimensional mesh associated with a three-dimensional model;

receiving an indication of a user interaction defining a modification to thea three-dimensional model;

in response to the user interaction, generating a modified implicit function by modifying the implicit function corresponding to the three-dimensional model according to the modification;

determining implicit function gradients and implicit function values based on comparing the implicit function and the modified implicit function;

based on preserving the implicit function gradients and implicit function values, generating a modified three-dimensional model by transferring the modification from the implicit function to the three-dimensional model; and

providing the modified three-dimensional model for display on a client device.

2. The method of claim 1 , wherein implicit function values reflect distances of initial points of the implicit function and corresponding nearest points of the modified implicit function.

3. The method of claim 1 , wherein implicit function gradients reflect directions of initial points of the implicit function and corresponding nearest points on the modified implicit function.

4. The method of claim 1 , wherein generating the modified three-dimensional model comprises transferring the modification from the implicit function to the three-dimensional mesh associated with the three-dimensional model.

5. The method of claim 1 , wherein:

the implicit function is modifiable in a first parameter space; and

the three-dimensional mesh associated with the three-dimensional model is modifiable by moving its set of vertices while preserving their connectivity.

6. The method of claim 1 , wherein receiving the indication of the user interaction defining the modification comprises receiving, from a client device, an indication of an adjustment to a handle for adjusting a semantic parameter associated with the implicit function within a model manipulation interface.

7. A system comprising:

a memory component; and

one or more processing devices coupled to the memory component, the one or more processing devices to perform operations comprising:

fitting an implicit function to a three-dimensional mesh associated with a three-dimensional model;

receiving an indication of a user interaction defining a modification to thea three-dimensional model;

in response to the user interaction, generating a modified implicit function by modifying the implicit function corresponding to the three-dimensional model according to the modification;

determining implicit function gradients and implicit function values based on comparing the implicit function and the modified implicit function;

generating a modified three-dimensional model by transferring the modification from the implicit function to the three-dimensional model by

preserving the implicit function gradients and implicit function values;

and

providing the modified three-dimensional model for display on a client device.

8. The system of claim 7 , wherein preserving the implicit function values associated with the implicit function comprises:

determining an implicit function value at a point in space before the modification and after the modification; and

determining a transformation for the three-dimensional model that will preserve a distance at the point to a vertex of the three-dimensional model.

9. The system of claim 7 , wherein preserving the implicit function gradients associated with the implicit function comprises:

determining a gradient at a point before the modification and after the modification; and

determining a transformation for the three-dimensional model that will preserve the gradient at the point to a vertex of the three-dimensional model.

10. The system of claim 7 , wherein generating the modified three-dimensional model comprises transferring the modification to the three-dimensional mesh associated with the three-dimensional model.

11. The system of claim 7 , wherein transferring the modification to the three-dimensional model comprises applying the modification to a subset of vertices of the three-dimensional mesh associated with the three-dimensional model.

12. The system of claim 7 , wherein transferring the modification from the implicit function to the three-dimensional model comprises:

subdividing the modification into a sequence of deformation steps that preserve the implicit function values and the implicit function gradients at mesh vertices of the three-dimensional model; and

applying the sequence of deformation steps to vertices of the three-dimensional model.

13. The system of claim 7 , wherein generating the modified three-dimensional model comprises transferring the modification from the implicit function to the three-dimensional model by using only a parameter space associated with the implicit function.

14. The system of claim 7 , wherein the one or more processing devices are further to configured to perform operations comprising smoothing deformations of the modified three-dimensional model that result from transferring the modification.

15. A non-transitory computer readable medium storing executable instructions which, when executed by a processing device, cause the processing device to perform operations comprising:

fitting an implicit function to a three-dimensional mesh associated with a three-dimensional model;

receiving an indication of a user interaction defining a modification to the three-dimensional model;

in response to the user interaction, generating a modified implicit function by modifying the implicit function corresponding to the three-dimensional model according to the modification;

determining implicit function gradients and implicit function values based on comparing the implicit function and the modified implicit function;

based on preserving the implicit function gradients and implicit function values, generating a modified three-dimensional model by transferring the modification from the implicit function to the three-dimensional model; and

providing the modified three-dimensional model for display on a client device.

16. The non-transitory computer readable medium of claim 15 , wherein generating the modified three-dimensional model comprises preserving implicit function values at mesh vertices as part of transferring the modification.

17. The non-transitory computer readable medium of claim 15 , wherein generating the modified three-dimensional model comprises preserving the implicit function gradients at mesh vertices as part of transferring the modification.

18. The non-transitory computer readable medium of claim 15 , wherein generating the modified three-dimensional model comprises transferring the modification from the implicit function to the three-dimensional mesh associated with the three-dimensional model.

19. The non-transitory computer readable medium of claim 15 , wherein:

the implicit function is modifiable in a first parameter space; and

the three-dimensional mesh associated with the three-dimensional model is modifiable by moving its set of vertices while preserving their connectivity.

20. The non-transitory computer readable medium of claim 15 , wherein receiving the indication of the user interaction defining the modification comprises receiving, from a client device, an indication of an adjustment to a handle or adjusting a semantic parameter associated with the implicit function within a model manipulation interface.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 9, 2023
From: KUSUPATI, UDAY; THIERY, JEAN; KAISER, ADRIEN
To: ADOBE INC.
Reel/Frame 062936/0011 →
Continuity (1)
Related Publication 20240303930A1 · Sep 12, 2024
References Cited (17)
US 7737969B2 · Shen · 2010 [cited by examiner]
US 12165258B2 · Zhu · 2024 [cited by examiner]
US 20130124149A1 · Carr · 2013 [cited by examiner]
Greg Turk et al., Shape Transformation Using Variational Implicit Functions, SIGGRAPH '05:ACM Siggraph 2005 Courses, Jul. 31, 2005, pp. 335-342 (also labeled pp. 13-20). [cited by examiner]
Yifan, Wang, Lukas Rahmann, and Olga Sorkine-Hornung. “Geometry-consistent neural shape representation with implicit displacement fields.” ICLR. 2022. [cited by applicant]
Yifan, Wang, et al. “Neural cages for detail-preserving 3d deformations.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. [cited by applicant]
Morreale, Luca, et al. “Neural Convolutional Surfaces.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022. [cited by applicant]
Yin, Kangxue, et al. “3dstylenet: Creating 3d shapes with geometric and texture style variations.” Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021. [cited by applicant]
Olga Sorkine and Marc Alexa. “As-rigid-as-possible surface modeling.” Symposium on Geometry processing. vol. 4. 2007. [cited by applicant]
Zohar Levi and Craig Gotsman. “Smooth rotation enhanced as-rigid-as-possible mesh animation.” IEEE transactions on visualization and computer graphics 21.2 (2014): 264-277. [cited by applicant]
Combined Search and Examination Report received in application No. 2318850.1 dated Nov. 21, 2024. [cited by applicant]
Jean-Marc Thiery et al. “Jacobians and Hessians of mean value coordinates for closed triangular meshes”, Visual Computer 30, 981-995 (2013). https://doi.org/10.1007/s00371-013-0889-y. [cited by applicant]
Kyle Genova et al. “Learning Templates with Structured Implicit Functions”, 12 pages, arXiv preprint arXiv: 1904.06447v1, Apr. 12, 2019. [cited by applicant]
Matheus Gadelha et al. “Learning Generative Models of Shape Handles,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 399-408, doi: 10.1109/CVPR42600.2020.00048. [cited by applicant]
Mehmet Ersin Yumer et al. “Semantic Shape Editing Using Deformation Handles”, ACM Transactions on Graphics (TOG), vol. 34, Issue 4, Article No. 86, pp. 1-12, Jul. 27, 2015, https://doi.org/10.1145/276690. [cited by applicant]
Rodolphe Vaillant et al. “Implicit skinning: Real-Time Skin Deformation with Contact Modeling”, ACM Transactions on Graphics (TOG), vol. 32, Issue 4, Article No. 125, pp. 1-12, Jul. 21, 2013, https://doi.org/10.1145/246… [cited by applicant]
Tao Ju et al. “Mean Value Coordinates for Closed Triangular Meshes”, ACM Transactions on Graphics (TOG), vol. 24, Issue 3, pp. 561-566, Jul. 1, 2005, https://doi.org/10.1145/1073204.1073229. [cited by applicant]