IP Library Granted Patent US 11,651,532
Granted Patent B1
US 11,651,532 · App. 17/376,360 · Granted May 16, 2023

Assisted creation of artistic digital images

Inventor: Christopher Tremblay (Cantley, CA)
Assignee: Corel Corporation
G06T11/203G06N3/08G06T11/001G06V10/44G06T2200/24
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 11,651,532
App. No.
17/376,360
Granted
May 16, 2023
Kind
B1
Abstract

An example method of automated creation of artistic digital images comprises: producing a styled digital image by performing stylization of a source digital image based on a specified visual style; identifying a plurality of visual elements of the styled digital image; generating a sequence of digital paint coat layers for the styled digital image, wherein each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image, and wherein each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives; and producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers, wherein the output digital image exhibits one or more visual features of the visual style.

Claims (113)

1. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on the specified visual style;

identifying a plurality of visual elements of the styled digital image;

generating a sequence of digital paint coat layers for the styled digital image; and

producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers; wherein

the output digital image exhibits one or more visual features of the visual style;

each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image,

each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives;

the stylization comprises applying a given shape to a fragment of the source digital image by applying a homomorphic transformation to the fragment; and

the given shape is associated with the specified visual style.

2. The method according to claim 1 , wherein

receiving the indication from the user of the specified visual style comprises the user selecting one or more other images from an image library; and

each other image of the selected one or more other images employs the specified visual style.

3. The method according to claim 1 , further comprising

pre-processing the source digital image prior to performing the stylization; wherein

the pre-processing removes visible defects within the source digital image.

4. The method according to claim 1 , wherein

the stylization of the source digital image is performed using one or more machine learning based models.

5. The method according to claim 1 , wherein

the stylization of the source digital image is performed by one or more rule-based stylization processes.

6. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on a specified visual style;

exporting the styled digital image into a digital canvas;

receiving, via a graphical user interface (GUI), one or more GUI commands specifying a set of graphic primitives to be rendered on the digital canvas;

generating the specified set of graphic primitives;

visually rendering an output digital image comprising the set of graphic primitives; wherein

the output digital image exhibits one or more visual features of the visual style;

the stylization comprises applying a given shape to a fragment of the source digital image by applying a homomorphic transformation to the fragment; and

the given shape is associated with the specified visual style.

7. The method according to claim 6 , wherein

visually rendering the output digital image further comprises rendering the styled digital image as an underpainting to the set of graphic primitives.

8. The method of claim 6 , wherein

producing the styled digital image by performing stylization of the source digital image based on the specified visual style comprises:

identifying a plurality of visual elements of the styled digital image;

generating a sequence of digital paint coat layers for the styled digital image; and

producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers,

the output digital image exhibits one or more visual features of the visual style;

each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image, and

each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives.

9. The method according to claim 6 , wherein

receiving the indication from the user of the specified visual style comprises the user selecting one or more other images from an image library; and

each other image of the selected one or more other images employs the specified visual style.

10. The method according to claim 6 , further comprising

pre-processing the source digital image prior to performing the stylization; wherein

the pre-processing removes visible defects within the source digital image.

11. The method according to claim 6 , wherein

the stylization of the source digital image is performed using at least one of one or more machine learning based models and one or more rule-based stylization processes.

12. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on the specified visual style;

identifying a plurality of visual elements of the styled digital image;

generating a sequence of digital paint coat layers for the styled digital image; and

producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers; wherein

the output digital image exhibits one or more visual features of the visual style;

each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image,

each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives;

receiving the indication from the user of the specified visual style comprises the user selecting one or more other images from an image library;

each other image of the selected one or more other images employs the specified visual style;

the stylization comprises applying a given shape to a fragment of the source digital image by applying a homomorphic transformation to the fragment; and

the given shape is established in dependence upon the selected one or more other images employing the specified visual style.

13. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on the specified visual style;

identifying a plurality of visual elements of the styled digital image;

generating a sequence of digital paint coat layers for the styled digital image; and

producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers; wherein

the output digital image exhibits one or more visual features of the visual style;

each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image,

each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives;

the sequence of digital paint coat layers for the styled digital image define an underpainting;

the underpainting is exported to a digital canvas rendered within a graphical user interface (GUI) of a software application; and

the user or another user can digitally paint onto the underpainting using a sequence of GUI commands within the software application.

14. The method according to claim 13 , wherein

the digital painting generates a graphic primitive where the graphic primitive is established in dependence upon the sequence of GUI commands and at least one of an element and a parameter of the underpainting associated with a region of the underpainting associated with the digital painting.

15. The method according to claim 13 , wherein

the digital painting generates a set of graphic primitives where each graphic primitive of the set of graphic primitives is established in dependence upon the sequence of GUI commands and at least one of an element and a parameter of the underpainting associated with a region of the underpainting associated with the digital painting; and

two or more graphic primitives of the set of graphic primitives may at least partially overlap wherein the partially overlapped portions of the two or more graphic primitives of the set of graphic primitives simulate multiple paint layers applied to a physical canvas.

16. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on a specified visual style;

exporting the styled digital image into a digital canvas;

receiving, via a graphical user interface (GUI), one or more GUI commands specifying a set of graphic primitives to be rendered on the digital canvas;

generating the specified set of graphic primitives; and

visually rendering an output digital image comprising the set of graphic primitives; wherein

the output digital image exhibits one or more visual features of the visual style;

receiving the indication from the user of the specified visual style comprises the user selecting one or more other images from an image library;

each other image of the selected one or more other images employs the specified visual style;

the stylization comprises applying a given shape to a fragment of the source digital image by applying a homomorphic transformation to the fragment; and

the given shape is established in dependence upon the selected one or more other images employing the specified visual style.

17. A method, comprising:

receiving, by a computer system, a source digital image;

receiving, by the computer system, an indication from a user relating to a specified visual style;

producing a styled digital image by performing stylization of the source digital image based on a specified visual style;

exporting the styled digital image into a digital canvas;

receiving, via a graphical user interface (GUI), one or more GUI commands specifying a set of graphic primitives to be rendered on the digital canvas;

generating the specified set of graphic primitives; and

visually rendering an output digital image comprising the set of graphic primitives; wherein

the output digital image exhibits one or more visual features of the visual style;

the styled digital image exported into the digital canvas comprises a sequence of digital paint coat layers which define an underpainting;

the underpainting is rendered within a graphical user interface (GUI) of a software application; and

the user or another user can digitally paint onto the underpainting using a sequence of GUI commands within the software application.

18. The method according to claim 17 , wherein

the digital painting generates a graphic primitive where the graphic primitive is established in dependence upon the sequence of GUI commands and at least one of an element and a parameter of the underpainting associated with a region of the underpainting associated with the digital painting.

19. The method according to claim 17 , wherein

the digital painting generates a set of graphic primitives where each graphic primitive of the set of graphic primitives is established in dependence upon the sequence of GUI commands and at least one of an element and a parameter of the underpainting associated with a region of the underpainting associated with the digital painting; and

two or more graphic primitives of the set of graphic primitives may at least partially overlap wherein the partially overlapped portions of the two or more graphic primitives of the set of graphic primitives simulate multiple paint layers applied to a physical canvas.

Assignments (2)
SECURITY INTEREST Recorded May 1, 2026
From: COREL CORPORATION
To: FIRST-CITIZENS BANK & TRUST COMPANY
Reel/Frame 075315/0928 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2021
From: TREMBLAY, CHRISTOPHER
To: COREL CORPORATION
Reel/Frame 056864/0828 →
Continuity (1)
Division 16935566 · Jul 22, 2020