# US 2018/0293714 A1 · Controlling smoothness of a transition between images

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0293714 A1
- Document ID: US20180293714A1
- Status: Published application
- Kind: A1
- Application number: 16/009,714
- Filed: 2018-06-15
- Published: 2018-10-11
- Earliest claimed: 2015-06-14
- Assignees: Adobe Systems Incorporated
- Applicants: Adobe Systems Incorporated
- Inventors: SYLVAIN PARIS; SOHRAB AMIRGHODSI; ALIAKBAR DARABI; ELYA SHECHTMAN
- Web page: https://patentgrep.com/patent/US20180293714A1

## CPC

- G06T 11/60: Creating or editing images; Combining images with text
- G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images
- G06T 5/70: Denoising; Smoothing
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 2207/10024: Color image
- G06T 2207/20192: Edge enhancement; Edge preservation
- G06T 2207/20221: Image fusion; Image merging
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Embodiments described herein are directed to methods and systems for facilitating control of smoothness of transitions between images. In embodiments, a difference of color values of pixels between a foreground image and the background image are identified along a boundary associated with a location at which to paste the foreground image relative to the background image. Thereafter, recursive down sampling of a region of pixels within the boundary by a sampling factor is performed to produce a plurality of down sampled images having color difference indicators associated with each pixel of the down sampled images. Such color difference indicators indicate whether a difference of color value exists for the corresponding pixel. To effectuate a seamless transition, the color difference indicators are normalized in association with each recursively down sampled image.

## Claims

### Claim 1

A computer-implemented method for compositing images with a seamless transition, the method comprising:
identifying a composition boundary between a first image and a second image;
recursively down sampling one or more boundary pixels along the composition boundary between the first image and the second image to determine a color difference value for the one or more boundary pixels;
generating a set of final color difference values for the one or more boundary pixels along the composition boundary by recursively up sampling an image generated during a last down sampling operation; and
compositing the first image with the second image using the set of final color difference values for the one or more boundary pixels between the first image and the second image.

### Claim 2 (depends on 1)

The method of claim 1, wherein the color difference values represent a difference in a red color, a difference in a green color, and a difference in a blue color.

### Claim 3 (depends on 1)

The method of claim 1, wherein each recursive down sampling instance comprises:
identifying a largest color difference indicator,
dividing each color difference component and color difference indicator associated with a corresponding down sampled image by the largest color difference indicator, and
multiplying each color difference component and color difference indicator associated with the corresponding down sampled image by a predetermined factor.

### Claim 4 (depends on 1)

The method of claim 1, wherein the boundary pixels include undefined pixels in the first image and defined pixels in the second image, the undefined pixels to be replaced with the corresponding defined pixels.

### Claim 5 (depends on 1)

The method of claim 1, wherein the recursive down sampling proceeds until no more undefined pixels remain in a down sampled image.

### Claim 6 (depends on 1)

The method of claim 1, further comprising;
recursively up sampling the boundary pixels along the composition boundary between the first image and the second image, wherein undefined pixels of the boundary pixels are filling in based on defined pixels.

### Claim 7 (depends on 1)

The method of claim 1, wherein generating the set of final color difference values further comprises dividing the color difference values of the image generated during a last down sampling operation by a color difference indicator associated with a final up sampled image.

### Claim 8 (depends on 1)

The method of claim 1, wherein the composition of the first image with the second images further comprises using the set of final color difference values by recursively averaging the color difference values of adjacent defined pixels to fill in undefined pixels.

### Claim 9

A non-transitory computer-readable storage medium including instructions which, when executed by a computer, cause the computer to perform operations to:
identify a composition boundary between a first image and a second image;
down sample one or more boundary pixels along the composition boundary between the first image and the second image to determine a color difference value for the one or more boundary pixels;
generate a set of final color difference values for the one or more boundary pixels along the composition boundary by up sampling an image generated during a last down sampling operation; and
produce a composition of the first image and the second image using the set of final color difference values for the one or more boundary pixels between the first image and the second image.

### Claim 10 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, further cause the computer to:
normalize color difference indicators in association with each recursively down sampled image, wherein the normalizing comprises:
identifying a largest color difference indicator from among the color difference indicators associated with the corresponding down sampled image, and
dividing each of the color difference indicators associated with the corresponding down sampled image by the largest color difference indicator.

### Claim 11 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, further cause the computer to:
augment the normalization by multiplying each color difference indicator by a predetermined factor.

### Claim 12 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, wherein the color difference values of pixels comprises a first difference representing a difference of a red color value, a second difference representing a difference of a green color value, and a third difference representing a difference of a blue color value.

### Claim 13 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, further cause the computer to:
recursively up sample the boundary pixels along the composition boundary between the first image and the second image, wherein undefined pixels of the boundary pixels are filling in based on defined pixels.

### Claim 14 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein to generate the set of final color difference values further comprises to divide the color difference values of the image generated during a last down sampling operation by a color difference indicator associated with a final up sampled image.

### Claim 15 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the composition of the first image with the second images further comprises using the set of final color difference values by recursively averaging the color difference values of adjacent defined pixels to fill in undefined pixels.

### Claim 16 (depends on 9)

The non-transitory computer-readable storage medium of claim 9, wherein the first image is a foreground image and the second image is a background image.

### Claim 17

A computing system comprising:
one or more processors; and
one or more non-transitory computer-readable storage media, coupled with the one or more processors, having instructions stored thereon, which, when executed by the one or more processors, cause the computing system to provide:
means for identifying a composition boundary between a first image and a second image;
means for recursively down sampling one or more boundary pixels along the composition boundary between the first image and the second image to determine a color difference value for the one or more boundary pixels;
means for producing a composition of the first image and the second image using a set of final color difference values for the one or more boundary pixels between the first image and the second image.

### Claim 18 (depends on 17)

The system of claim 17 further comprising:
means for generating the set of final color difference values for the boundary pixels along the composition boundary by recursively up sampling an image generated during a last down sampling operation.

### Claim 19 (depends on 17)

The system of claim 17 further comprising:
means for recursively up sampling the boundary pixels along the composition boundary between the first image and the second image, wherein undefined pixels of the boundary pixels are filling in based on defined pixels.

### Claim 20 (depends on 17)

The system of claim 17 further comprising:
means for a user to specify the composition boundary.
