IP Library Granted Patent US 12,626,427
Granted Patent B2
US 12,626,427 · App. 18/459,159 · Granted May 12, 2026

Digital design recoloring and enhancement methods utilizing a text-to-image diffusion model

Inventors: Ankit Phogat (Noida, IN); Souymodip Chakraborty (Bangalore, IN); Sumit Chaturvedi (Noida, IN); Sumit Dhingra (New Delhi, IN); Vineet Batra (Pitam Pura, IN); Vishwas Jain (Bangalore, IN)
Assignee: Adobe Inc.
G06T11/001
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 12,626,427
App. No.
18/459,159
Granted
May 12, 2026
Kind
B2
Abstract

The systems, methods, and non-transitory computer-readable media include recoloring a digital design according to colors of a digital image and further generating an enhanced recolored digital design. In particular, in some embodiments, the disclosed systems identify a digital image for recoloring a digital design and recolors the digital design utilizing a color affine transformation algorithm to generate a recolored digital design. Further, in some embodiments, the disclosed systems generate the enhanced recolored digital design by transforming one or more colors of the recolored digital design to be within a range of the colors of the digital image utilizing a convex hull projection method. Moreover, in some embodiments, the disclosed systems further enhance the recolored digital design utilizing a contrast enhancement algorithm to modify luminescence values.

Claims (76)

1 . A system comprising:

one or more memory components; and

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

identifying a digital image for recoloring a digital design;

recoloring, utilizing a color affine transformation algorithm, colors of the digital design according to colors of the digital image to generate a recolored digital design comprising mapped colors; and

generating an enhanced recolored digital design by:

utilizing a convex hull projection method to construct a convex hull from the colors of the digital image;

projecting the mapped colors of the recolored digital design toward the convex hull to generate transformed colors; and

modifying, utilizing a contrast enhancement algorithm, luminescence values of the transformed colors to increase color separation.

2 . The system of claim 1 , wherein the operations further comprise:

determining a statistical distribution of a first range of colors of the digital design; and

from the statistical distribution, reducing the colors of the digital design to a second range of colors smaller than the first range of colors.

3 . The system of claim 1 , wherein the operations further comprise converting a first range of colors of the digital design within an RGB color space to an HSL color space.

4 . The system of claim 3 , wherein the operations further comprise:

initializing, utilizing a clustering algorithm, a set of color clusters with a range of colors smaller than the first range of colors; and

clustering, utilizing the clustering algorithm, the first range of colors of the digital design to the set of color clusters.

5 . The system of claim 4 , wherein utilizing the clustering algorithm comprises:

determining for a first color of the first range of colors, a hue value is within a predefined hue threshold of a first cluster of the set of color clusters, a saturation value matches a saturation value of the first cluster of the set of color clusters, and lightness value is within a predefined lightness threshold of the first cluster of the set of color clusters; and

assigning the first color to the first cluster of the set of color clusters.

6 . The system of claim 1 , wherein utilizing the color affine transformation algorithm comprises:

generating a three-dimensional array representation of the colors of the digital image;

generating a three-dimensional array representation of colors of the digital design;

generating, a first set of arrays from the three-dimensional array representation of the digital image and a second set of arrays from the three-dimensional array representation of the digital design; and

transforming the second set of arrays of the digital design according to the first set of arrays of the digital image.

7 . The system of claim 1 , wherein utilizing the convex hull projection method further comprises:

projecting the mapped colors towards a surface of the convex hull by transforming the mapped colors of the recolored digital design to align with the convex hull, wherein the mapped colors are treated as a set of points in a three-dimensional space;

determining a geometric structure that contains the set of points in the three-dimensional space as the geometric structure of the convex hull; and

generating a transformed recolored digital design based on the geometric structure of the convex hull.

8 . The system of claim 1 , wherein utilizing the contrast enhancement algorithm comprises modifying brightness or darkness values of the digital design.

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

identifying a digital image for recoloring a digital design;

recoloring, utilizing a color affine transformation algorithm, colors of the digital design according to colors of the digital image to generate a recolored digital design comprising mapped colors; and

generating an enhanced recolored digital design by:

utilizing a convex hull projection method to construct a convex hull from the colors of the digital image;

projecting the mapped colors of the recolored digital design toward the convex hull to generate transformed colors; and

modifying, utilizing a contrast enhancement algorithm, luminescence values of the transformed colors to increase color separation.

10 . The non-transitory computer-readable medium of claim 9 , wherein the operations further comprise:

determining a statistical distribution of a first range of colors of the digital design; and

from the statistical distribution, reducing the first range of colors of the digital design to a second range of colors smaller than the first range of colors.

11 . The non-transitory computer-readable medium of claim 9 , wherein recoloring, utilizing the color affine transformation algorithm comprises:

generating a three-dimensional array representation of the colors of the digital image;

generating a three-dimensional array representation of colors of the digital design;

generating, a first set of arrays from the three-dimensional array representation of the digital image and a second set of arrays from the three-dimensional array representation of the digital design; and

transforming the second set of arrays of the digital design according to the first set of arrays of the digital image.

12 . The non-transitory computer-readable medium of claim 9 , wherein generating an enhanced recolored digital design further comprises:

projecting the mapped colors toward a surface of the convex hull by transforming the mapped colors of the recolored digital design to align with the convex hull, wherein the mapped colors are treated as a set of points in a three-dimensional space;

determining a geometric structure that contains the set of points in the three-dimensional space as the geometric structure of the convex hull;

generating a transformed recolored digital design based on the geometric structure of the convex hull; and

modifying the transformed recolored digital design by utilizing the contrast enhancement algorithm to modify brightness or darkness values to generate the enhanced recolored digital design.

13 . A method comprising:

identifying a digital image for recoloring a digital design;

recoloring, utilizing a color affine transformation algorithm, colors of the digital design according to colors of the digital image to generate a recolored digital design comprising mapped colors; and

generating an enhanced recolored digital design by:

utilizing a convex hull projection method to construct a convex hull from the colors of the digital image;

projecting the mapped colors of the recolored digital design toward the convex hull to generate transformed colors; and

modifying, utilizing a contrast enhancement algorithm, luminescence values of the transformed colors to increase color separation.

14 . The method of claim 13 , further comprising:

determining a statistical distribution of a first range of colors of the digital design; and

from the statistical distribution, reducing the colors of the digital design to a second range of colors smaller than the first range of colors.

15 . The method of claim 13 , further comprising converting a first range of colors of the digital design within an RGB color space to an HSL color space.

16 . The method of claim 15 , further comprising:

initializing, utilizing a clustering algorithm, a set of color clusters with a range of colors smaller than the first range of colors; and

clustering, utilizing the clustering algorithm, the first range of colors of the digital design to the set of color clusters.

17 . The method of claim 16 , wherein utilizing the clustering algorithm comprises:

determining for a first color of the first range of colors, a hue value is within a predefined hue threshold of a first cluster of the set of color clusters, a saturation value matches a saturation value of the first cluster of the set of color clusters, and lightness value is within a predefined lightness threshold of the first cluster of the set of color clusters; and

assigning the first color to the first cluster of the set of color clusters.

18 . The method of claim 13 , wherein utilizing the color affine transformation algorithm comprises:

generating a three-dimensional array representation of the colors of the digital image;

generating a three-dimensional array representation of colors of the digital design;

generating, a first set of arrays from the three-dimensional array representation of the digital image and a second set of arrays from the three-dimensional array representation of the digital design; and

transforming the second set of arrays of the digital design according to the first set of arrays of the digital image.

19 . The method of claim 13 , wherein utilizing the convex hull projection method further comprises:

projecting the mapped colors towards a surface of the convex hull by transforming the mapped colors of the recolored digital design to align with the convex hull, wherein the mapped colors are treated as a set of points in a three-dimensional space;

determining a geometric structure that contains the set of points in the three-dimensional space as the geometric structure of the convex hull; and

generating a transformed recolored digital design based on the geometric structure of the convex hull.

20 . The method of claim 13 , wherein utilizing the contrast enhancement algorithm comprises modifying brightness or darkness values of the digital design.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 31, 2023
From: PHOGAT, ANKIT; CHAKRABORTY, SOUYMODIP; CHATURVEDI, SUMIT; DHINGRA, SUMIT; BATRA, VINEET; JAIN, VISHWAS
To: ADOBE INC.
Reel/Frame 064768/0020 →
Continuity (1)
Related Publication 20250078341A1 · Mar 6, 2025
References Cited (12)
US 6384836B1 · Naylor, Jr. · 2002 [cited by examiner]
US 11043012B2 · Phogat et al. · 2021 [cited by applicant]
US 11455753B1 · Alemi · 2022 [cited by examiner]
US 20090148040A1 · Tin · 2009 [cited by examiner]
US 20120075331A1 · Mallick · 2012 [cited by examiner]
Arici Tarik, Dikbas Salih, and Altunbasak Yucel. A histogram modification framework and its application for image contrast enhancement. Image Processing, IEEE Transactions on, 18:1921-1935, Oct. 2009. [cited by applicant]
Erik Reinhard, Michael Ashikhmin, Bruce Gooch, and Peter Shirley. Color transfer between images. IEEE Comput. Graph. Appl., 21(5):34-41, Sep. 2001. [cited by applicant]
Huiwen Chang, Ohad Fried, Yiming Liu, Stephen DiVerdi, and Adam Finkelstein. Palette-based photo recoloring. ACM Transactions on Graphics (Proc. SIGGRAPH), 34(4), Jul. 2015. [cited by applicant]
Richard Zhang, Phillip Isola, and Alexei A Efros. Colorful image colorization. In ECCV, 2016. [cited by applicant]
Roger A. Horn and Charles R. Johnson. Topics in Matrix Analysis. Cambridge University Press, 1991. [cited by applicant]
Sharon Lin, Daniel Ritchie, Matthew Fisher, and Pat Hanrahan. Probabilistic color-by-numbers: Suggesting pattern colorizations using factor graphs. ACM Transactions on Graphics (TOG), 32(4):1-12, 2013. [cited by applicant]
Xuezhong Xiao and Lizhuang Ma. Color transfer in correlated color space. pp. 305-309, Jun. 2006. [cited by applicant]