Seamless compositing using a soft selection

Patent metadata

Field	Value
Publication number	US-9892537-B2
Application number	US-201715646509-A
Country	US
Kind code	B2
Filing date	Jul 11, 2017
Priority date	Nov 9, 2015
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

A healing component that heals foreground pixels with background pixels is provided. In some embodiments, the healing component is programmed or otherwise configured to respond to a single healing request by identifying a plurality of regions within a selected area and healing each region of the plurality of regions independently of other regions.

First claim

What is claimed is:

1. A content editing device comprising:
memory; and
at least one processor coupled to the memory and configured to:
receive a request to reduce transitions in a set of pixels within a background, each pixel in the set of pixels being at least partially selected and at least one pixel in the set of pixels being partially selected;
in response to receipt of the request:
identify a first portion of the set;
identify a second portion of the set distinct from the first portion and comprising the at least one pixel;
reduce transitions in the first portion, separately from the second portion, using one or more foreground pixels at least in part by:
computing differences between the one or more foreground pixels and pixels in a boundary between the first portion and the second portion; and
modifying the first portion based on the differences at least in part by executing an interpolation process on the first portion using the differences;

reduce transitions in the second portion, separately from the first portion, using the one or more foreground pixels at least in part by:
modifying the second portion based on the differences at least in part by executing an extrapolation process on the second portion using the differences; and

blend the set of pixels with the background.

2. The device of claim 1 , wherein the first portion comprises pixels that have a degree of selection greater than or equal to 50%.

3. The device of claim 1 , wherein the at least one processor is configured to blend the set of pixels with the background at least in part by executing an alpha blending process.

4. The device of claim 1 , further comprising a user interface executable by the at least one processor, wherein the at least one processor is further configured to provide, via the user interface, a visual cue of the set of pixels.

5. The device of claim 4 , wherein the visual cue comprises pixels in the boundary.

6. The device of claim 4 , wherein the visual cue comprises pixels distinct from pixels in the boundary.

7. The device of claim 1 , wherein the at least one processor is further configured to automatically sample the one or more foreground pixels after identifying the set of pixels.

8. A method of editing content using a content editing device comprising memory and at least one processor, the method comprising:
receiving a request to reduce transitions in a set of pixels within a background, each pixel in the set of pixels being at least partially selected and at least one pixel in the set of pixels being partially selected;
in response to receiving the request:
identifying a first portion of the set;
identifying a second portion of the set distinct from the first portion and comprising the at least one pixel;
reducing transitions in the first portion, separately from the second portion, using one or more foreground pixels at least in part by:
computing differences between the one or more foreground pixels and pixels in a boundary between the first portion and the second portion; and
modifying the first portion based on the differences at least in part by executing an interpolation process on the first portion using the differences;

reducing transitions in the second portion, separately from the first portion, using the one or more foreground pixels at least in part by:
modifying the second portion based on the differences at least in part by executing an extrapolation process on the second portion using the differences; and

blending the set of pixels with the background.

9. The method of claim 8 , wherein identifying the first portion comprises identifying pixels having a degree of selection greater than or equal to 50%.

10. The method of claim 8 , wherein blending the set of pixels with the background comprises executing an alpha blending process.

11. The method of claim 8 , wherein the content editing device further comprises a user interface coupled to the at least one processor and the method further comprises providing, via the user interface, a visual cue of the set of pixels.

12. The method of claim 11 , wherein the visual cue comprises pixels in the boundary.

13. The method of claim 11 , wherein the visual cue comprises pixels distinct from pixels in the boundary.

14. The method of claim 8 , further comprising automatically sampling the one or more foreground pixels after identifying the set of pixels.

15. A non-transitory data storage medium storing instructions executable by a programmable device, the instructions being configured to execute a method of editing content, the method comprising:
receiving a request to reduce transitions in a set of pixels within a background, each pixel in the set of pixels being at least partially selected and at least one pixel in the set of pixels being partially selected;
in response to receiving the request:
identifying a first portion of the set;
identifying a second portion of the set distinct from the first portion and comprising the at least one pixel;
reducing transitions in the first portion, separately from the second portion, using one or more foreground pixels at least in part by:
computing differences between the one or more foreground pixels and pixels in a boundary between the first portion and the second portion; and
modifying the first portion based on the differences at least in part by executing an interpolation process on the first portion using the differences;

reducing transitions in the second portion, separately from the first portion, using the one or more foreground pixels at least in part by:
modifying the second portion based on the differences at least in part by executing an extrapolation process on the second portion using the differences; and

blending the set of pixels with the background.

16. The data storage medium of claim 15 , wherein identifying the first portion comprises identifying pixels having a degree of selection greater than or equal to 50%.

17. The data storage medium of claim 15 , wherein the method further comprises providing, via a user interface, a visual cue of the set of pixels.

18. The data storage medium of claim 17 , wherein the visual cue comprises pixels in the boundary.

19. The data storage medium of claim 17 , wherein the visual cue comprises pixels distinct from pixels in the boundary.

20. The data storage medium of claim 15 , wherein the method further comprises automatically sampling the one or more foreground pixels after identifying the set of pixels.

Assignees

• Adobe Systems Inc

Inventors

• Paris Sylvain
• Amirghodsi Sohrab
• Shechtman Elya

Classifications

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06K9/4604

  Physics · mapped topic

• G06T7/12

  Edge-based segmentation · CPC title

• G06K9/6215

  Physics · mapped topic

• G06T11/60 Primary

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