Granted Patent B2

US 12,517,637 · App. 18/205,216 · Granted Jan 6, 2026

Inventors: Kun Duan (Los Angeles, CA); Yunchao Gong (Playa Vista, CA); Nan Hu (San Jose, CA)

Assignee: Snap Inc.

G06F3/04845G06F3/0488G06F3/04883G06T7/11G06T7/12G06T7/13G06T7/162G06T11/001G06T11/203G06T2200/24G06T2207/10024G06T2207/20028G06T2207/20092

Abstract

Claims (63)

1 . A method comprising:

on a computing device, causing presentation of a user interface comprising an image;

detecting an input as a stroke drawn on the image;

determining a region of interest in the image based on the stroke;

performing a method to recolorize the region of interest by:

performing a comparison of luminance values of neighboring pixels; and

determining a recolorization color based on the comparison; and

filling the region of interest with the recolorization color to produce a recolorized image.

2 . The method of claim 1 , wherein the user interface further comprises multiple selectable colors and the method further comprises detecting a selected color from the multiple selectable colors.

3 . The method of claim 1 , further comprising causing presentation of the recolorized image on the computing device.

4 . The method of claim 1 , comprising expanding the stroke to generate a mask.

5 . The method of claim 4 , comprising refining the mask to determine a precise boundary of the region of interest.

6 . The method of claim 5 , wherein refining of the mask comprises:

computing a convex hull of the mask;

dilating the convex hull by a predetermined amount to generate an enlarged convex hull mask; and

segmenting the image based on the enlarged convex hull mask.

7 . The method of claim 5 , wherein refining of the mask further comprises simulating one or more additional strokes on the image.

8 . The method of claim 7 , wherein simulating of the one or more additional strokes on the image comprises:

performing bilateral filtering on the image to remove high-frequency edges;

performing edge detection on the image to generate an edge map; and

dilating the edge map such that edges of the edge map are thickened.

9 . The method of claim 1 , further comprising generating a mask by performing operations comprising:

identifying one or more contour points on the stroke; and

applying a flood fill algorithm to the image using the one or more contour points as seeds, resulting in the mask.

10 . The method of claim 2 , comprising generating a mask by performing operations comprising:

identifying one or more contour points on the stroke;

identifying contour pixels, each pixel of the contour pixels having a color within a threshold color difference to a neighboring pixel; and

replacing the color of connected pixels with the selected color resulting in the mask.

11 . A system comprising:

one or more processors; and

a non-transitory computer readable storage medium comprising instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising:

on a computing device, causing presentation of a user interface comprising an image;

detecting an input as a stroke drawn on the image;

determining a region of interest in the image based on the stroke;

performing a method to recolorize the region of interest by:

performing a comparison of luminance values of neighboring pixels; and

determining a recolorization color based on the comparison; and

filling the region of interest with the recolorization color to produce a recolorized image.

12 . The system of claim 11 , wherein the user interface further comprises multiple selectable colors and the method further comprises detecting a selected color from the multiple selectable colors.

13 . The system of claim 11 , further comprising causing presentation of the recolorized image on the computing device.

14 . The system of claim 11 , comprising expanding the stroke to generate a mask.

15 . The system of claim 14 , wherein the operations caused by instructions executed by the one or more processors further include:

refining the mask to determine a precise boundary of the region of interest.

16 . The system of claim 15 , wherein refining of the mask comprises:

computing a convex hull of the mask;

dilating the convex hull by a predetermined amount to generate an enlarged convex hull mask; and

segmenting the image based on the enlarged convex hull mask.

17 . The system of claim 15 , wherein refining of the mask further comprises simulating one or more additional strokes on the image.

18 . The system of claim 17 , wherein simulating of the one or more additional strokes on the image comprises:

performing bilateral filtering on the image to remove high-frequency edges;

performing edge detection on the image to generate an edge map; and

dilating the edge map such that edges of the edge map are thickened.

19 . The system of claim 11 , wherein the operations further include generating a mask by performing operations comprising:

identifying one or more contour points on the stroke; and

applying a flood fill algorithm to the image using the one or more contour points as seeds resulting in the mask.

20 . A machine-readable non-transitory storage medium having instruction data executable by a machine to cause the machine to perform operations comprising:

on a computing device, causing presentation of a user interface comprising an image;

detecting an input as a stroke drawn on the image;

determining a region of interest in the image based on the stroke;

performing a method to recolorize the region of interest by:

performing a comparison of luminance values of neighboring pixels; and

determining a recolorization color based on the comparison; and

filling the region of interest with the recolorization color to produce a recolorized image.

Assignments (1)

Continuity (5)

References Cited (42)