Digital content editing using a procedural model

US11900514B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-11900514-B2
Application numberUS-202217867082-A
CountryUS
Kind codeB2
Filing dateJul 18, 2022
Priority dateOct 26, 2020
Publication dateFeb 13, 2024
Grant dateFeb 13, 2024

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

Procedural model digital content editing techniques are described that overcome the limitations of conventional techniques to make procedural models available for interaction by a wide range of users without requiring specialized knowledge and do so without “breaking” the underlying model. In the techniques described herein, an inverse procedural model system receives a user input that specifies an edit to digital content generated by a procedural model. Input parameters from these candidate input parameters are selected by the system which cause the digital content generated by the procedural model to incorporate the edit.

First claim

Opening claim text (preview).

What is claimed is: 1. A method comprising: generating, by a processing system, edited digital content that tracks a user input specifying an edit to a dimension of an object depicted by digital content, the digital content including a two-dimensional model or a three-dimensional model generated using a procedural model; generating, by the processing system, candidate input parameters over a plurality of iterations using an optimization function that is configured to minimize a distance between digital content generated using the procedural model using the candidate input parameters over the plurality of iterations with the edited digital content and that incorporate the edit to the digital content and remove data that is not salient to determining the candidate input parameters; comparing, by the processing system, digital content generated using the procedural model using the candidate input parameters over the plurality of iterations with the edited digital content; selecting, by the processing system, input parameters from the candidate input parameters from a respective said iteration that cause the procedural model to generate the digital content as having the edit; generating, by the processing system, the digital content as having the edit by executing the procedural model using the input parameters to edit the object; and displaying, by the processing system, the digital content as having the edit. 2. The method as described in claim 1 , wherein the input parameters cause the digital content generated by the procedural model to include the edit without making a change to the procedural model, itself. 3. The method as described in claim 1 , further comprising: generating a simplified model from the procedural model, the simplified model having a plurality of bounding objects; generating an edited simplified model by applying the edit to at least one of the bounding objects of the simplified model; and generating a plurality of candidate bounding objects over a plurality of iterations using respective said candidate input parameters, and wherein the selecting of the input parameters is based on a comparison of the plurality of candidate bounding objects and the bounding objects of the edited simplified model. 4. The method as described in claim 3 , wherein the edit is tracked by applying the edit to the at least one of the bounding objects. 5. The method as described in claim 3 , wherein the comparison is based on a distance between the plurality of candidate bounding objects and bounding objects of the edited simplified model and the selecting is performed to minimize the distance. 6. The method of claim 3 , wherein the simplified model approximates an outer boundary of the object. 7. The method as described in claim 1 , wherein the generating the plurality of candidate input parameters over the plurality of iterations is performed using an auto differentiation function. 8. A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising: receiving a user input specifying an edit to a dimension of an object depicted by digital content generated using a procedural model; generating a plurality of candidate input parameters over a plurality of iterations using an optimization function that is configured to minimize a distance between digital content generated using the procedural model using the candidate input parameters over the plurality of iterations with the edited digital content and that incorporate the edit to the digital content and remove data that is not salient to determining the candidate input parameters; selecting input parameters from the plurality of candidate input parameters that cause the procedural model to generate the digital content as having the edit; generating the digital content as having the edit by executing the procedural model using the input parameters to edit the object; and displaying the digital content as having the edit. 9. The non-transitory computer-readable storage medium of claim 8 , wherein the input parameters cause the digital content generated by the procedural model to include the edit without making a change to the procedural model, itself. 10. The non-transitory computer-readable storage medium of claim 8 , further comprising: generating a simplified model from the procedural model, the simplified model having a plurality of bounding objects; generating an edited simplified model by applying the edit to at least one of the bounding objects of the simplified model; and generating a plurality of candidate bounding objects over a plurality of iterations using respective said candidate input parameters, and wherein the selecting of the input parameters is based on a comparison of the plurality of candidate bounding objects and the bounding objects of the edited simplified model. 11. The non-transitory computer-readable storage medium of claim 10 , wherein the edit is tracked by applying the edit to the at least one of the bounding objects. 12. The non-transitory computer-readable storage medium of claim 10 , wherein the comparison is based on a distance between the plurality of candidate bounding objects and bounding objects of the edited simplified model and the selecting is performed to minimize the distance. 13. The non-transitory computer-readable storage medium of claim 8 , wherein the generating the plurality of candidate input parameters over the plurality of iterations is performed using an auto differentiation function. 14. The non-transitory computer-readable storage medium of claim 8 , wherein the edit to the digital content includes an affine transformation. 15. A system comprising: a user input module implemented at least partially in hardware of a processing device to receive a user input specifying an edit to a dimension of an object depicted by digital content, the digital content generated using a procedural model; a candidate parameter generation module implemented at least partially in hardware of the processing device to generate a plurality of candidate input parameters over a plurality of iterations using an optimization function that is configured to minimize a distance between digital content generated using the procedural model using the candidate input parameters over the plurality of iterations with the edited digital content and that incorporate the edit to the digital content and remove data that is not salient to determining the candidate input parameters; a distance determination module implemented at least partially in hardware of the processing device to: compare digital content generated using the procedural model using the candidate input parameters over the plurality of iterations with the edited digital content; and select input parameters from the candidate input parameters from a respective said iteration that cause the procedural model to generate the digital content as having the edit; and a procedural model output module implemented at least partially in hardware of the processing device to generate the digital content as having the edit by executing the procedural model using the input parameters to edit the object. 16. The system as described in claim 15 , wherein the input parameters cause the digital content generated by the procedural model to include the edit without making a change to the procedural model, itself. 17. The system as described in claim 15 , further comprising: a simplified model generation module to generate a simplified

Assignees

Inventors

Classifications

  • G06T11/60Primary

    Creating or editing images; Combining images with text · CPC title

  • Physics · mapped topic

  • involving graphical user interfaces [GUIs] · CPC title

  • G06T19/20Primary

    Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts · CPC title

  • Shape modification · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US11900514B2 cover?
Procedural model digital content editing techniques are described that overcome the limitations of conventional techniques to make procedural models available for interaction by a wide range of users without requiring specialized knowledge and do so without “breaking” the underlying model. In the techniques described herein, an inverse procedural model system receives a user input that specifie…
Who is the assignee on this patent?
Adobe Inc
What technology area does this patent fall under?
Primary CPC classification G06T11/60. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Feb 13 2024 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 7 related publications on this page (citations in our corpus or others sharing the same primary CPC).