# US 11,308,674 B2 · Dynamic image compositing method and apparatus, terminal and storage medium

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

- Number: US 11,308,674 B2
- Document ID: US11308674B2
- Status: Granted
- Kind: B2
- Application number: 16/799,640
- Filed: 2020-02-24
- Published: 2020-06-18
- Granted: 2022-04-19
- Earliest claimed: 2017-09-30
- Assignees: Tencent Technology (Shenzhen) Company Limited
- Applicants: Tencent Technology (Shenzhen) Company Limited
- Inventors: Yi Xu; Qifa Guo; Shengwei Lin
- Web page: https://patentgrep.com/patent/US11308674B2

## CPC

- G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 11/60: Creating or editing images; Combining images with text
- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G06T 13/80: Two-dimensional [2D] animation, e.g. using sprites
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/20221: Image fusion; Image merging
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Embodiments of this application disclose a dynamic image compositing method performed at a terminal. A skeleton animation of an animation model is displayed on a real-world image captured by the terminal; a currently displayed target real-world image is captured in a case that a photographing instruction is received, and the skeleton animation of the animation model is recorded, to obtain the recorded skeleton animation; image compositing is performed on the target real-world image and each frame of image of the recorded skeleton animation, to obtain a plurality of composited images; and the plurality of composited images are combined into a corresponding dynamic image. Based on the solutions, the real-world image and the skeleton animation of the animation model may be automatically composited into the corresponding dynamic image, and a user does not need to perform a large quantity of repetitive image addition and selection operations.

## Claims

### Claim 1

A dynamic image compositing method performed at a terminal having one or more processors and memory storing a plurality of programs to be executed by the one or more processors, the method comprising:
displaying a skeleton animation of an animation model on a real-world image captured by the terminal;
receiving a photographing instruction;
in response to the photographing instruction:
capturing a currently displayed target real-world image and recording the skeleton animation of the animation model, the recorded skeleton animation including a plurality of image frames;
associating the target real-world image with a parent image display control and each of the plurality of image frames of the animation model with a child image display control, respectively;
performing image composition on the target real-world image and each of the plurality of image frames of the animation model according to a current offset location of the child image display control relative to the parent image display control, to obtain a plurality of composited images, each composited image having the target real-world image as its background and a corresponding image frame of the animation model; and
combining the plurality of composited images into a dynamic image animation.

### Claim 2 (depends on 1)

The dynamic image compositing method according to claim 1, wherein the displaying a skeleton animation of an animation model on a real-world image captured by the terminal comprises:
displaying the captured real-world image through a first image display component of the terminal; and
displaying the skeleton animation of the animation model through a second image display component of the terminal, wherein the second image display component is superimposed on the first image display component; and
the capturing a currently displayed target real-world image and recording the skeleton animation of the animation model comprises:
capturing the currently displayed target real-world image through the first image display component, and simultaneously recording the skeleton animation of the animation model through the second image display component.

### Claim 3 (depends on 2)

The dynamic image compositing method according to claim 2, wherein the recording the skeleton animation of the animation model through the second image display component comprises:
capturing a currently displayed skeleton animation image of the animation model at intervals of a preset time length through the second image display component to serve as a frame of image of the recorded skeleton animation.

### Claim 4 (depends on 1)

The dynamic image compositing method according to claim 1, further comprising:
displaying the target real-world image and each of the plurality of image frames of the animation model on an interface through the parent image display control and the child image display control.

### Claim 5 (depends on 4)

The dynamic image compositing method according to claim 4, further comprising:
in response to the photographing instruction, recording an animation offset location of the current skeleton animation of the animation model relative to the real-world image; and
the displaying the target real-world image and each of the plurality of image frames of the animation model on a corresponding interface through the parent image display control and the child image display control comprises:
setting the current offset location of the child image display control relative to the parent image display control according to the animation offset location; and
displaying the target real-world image and each of the plurality of image frames of the animation model on the corresponding interface according to the parent image display control and the child image display control after the setting.

### Claim 6 (depends on 1)

The dynamic image compositing method according to claim 1, further comprising:
determining a location in an interface according to a location of the animation model and a size of the skeleton animation, and adding an information display box to the location;
displaying, in the information display box, information inputted by a user;
performing image capture on the information display box, to obtain an information display box image; and
adding the information display box image to the dynamic image.

### Claim 7 (depends on 6)

The dynamic image compositing method according to claim 6, wherein the adding the information display box image to the dynamic image comprises:
performing image composition on the information display box image and each of the plurality of composited images, and combining obtained images into the dynamic image.

### Claim 8

A terminal comprising one or more processors, memory coupled to the one or more processors and a plurality of programs stored in the memory that, when executed by the one or more processors, cause the terminal to perform a plurality of operations comprising:
displaying a skeleton animation of an animation model on a real-world image captured by the terminal;
receiving a photographing instruction;
in response to the photographing instruction:
capturing a currently displayed target real-world image and recording the skeleton animation of the animation model, the recorded skeleton animation including a plurality of image frames;
associating the target real-world image with a parent image display control and each of the plurality of image frames of the animation model with a child image display control, respectively;
performing image composition on the target real-world image and each of the plurality of image frames of the animation model according to a current offset location of the child image display control relative to the parent image display control, to obtain a plurality of composited images, each composited image having the target real-world image as its background and a corresponding image frame of the animation model; and
combining the plurality of composited images into a dynamic image animation.

### Claim 9 (depends on 8)

The terminal according to claim 8, wherein the displaying a skeleton animation of an animation model on a real-world image captured by the terminal comprises:
displaying the captured real-world image through a first image display component of the terminal; and
displaying the skeleton animation of the animation model through a second image display component of the terminal, wherein the second image display component is superimposed on the first image display component; and
the capturing a currently displayed target real-world image and recording the skeleton animation of the animation model comprises:
capturing the currently displayed target real-world image through the first image display component, and simultaneously recording the skeleton animation of the animation model through the second image display component.

### Claim 10 (depends on 9)

The terminal according to claim 9, wherein the recording the skeleton animation of the animation model through the second image display component comprises:
capturing a currently displayed skeleton animation image of the animation model at intervals of a preset time length through the second image display component to serve as a frame of image of the recorded skeleton animation.

### Claim 11 (depends on 8)

The terminal according to claim 8, wherein the plurality of operations further comprise:
displaying the target real-world image and each of the plurality of image frames of the animation model on an interface through the parent image display control and the child image display control.

### Claim 12 (depends on 11)

The terminal according to claim 11, wherein the plurality of operations further comprise:
in response to the photographing instruction, recording an animation offset location of the current skeleton animation of the animation model relative to the real-world image; and
the displaying the target real-world image and each of the plurality of image frames of the animation model on a corresponding interface through the parent image display control and the child image display control comprises:
setting the current offset location of the child image display control relative to the parent image display control according to the animation offset location; and
displaying the target real-world image and each of the plurality of image frames of the animation model on the corresponding interface according to the parent image display control and the child image display control after the setting.

### Claim 13 (depends on 8)

The terminal according to claim 8, wherein the plurality of operations further comprise:
determining a location in an interface according to a location of the animation model and a size of the skeleton animation, and adding an information display box to the location;
displaying, in the information display box, information inputted by a user;
performing image capture on the information display box, to obtain an information display box image; and
adding the information display box image to the dynamic image.

### Claim 14 (depends on 13)

The terminal according to claim 13, wherein the adding the information display box image to the dynamic image comprises:
performing image composition on the information display box image and each of the plurality of composited images, and combining obtained images into the dynamic image.

### Claim 15

A non-transitory computer readable storage medium storing a plurality of machine readable instructions in connection with a terminal having one or more processors, wherein the plurality of machine readable instructions, when executed by the one or more processors, cause the terminal to perform a plurality of operations including:
displaying a skeleton animation of an animation model on a real-world image captured by the terminal;
receiving a photographing instruction;
in response to the photographing instruction:
capturing a currently displayed target real-world image and recording the skeleton animation of the animation model, the recorded skeleton animation including a plurality of image frames;
associating the target real-world image with a parent image display control and each of the plurality of image frames of the animation model with a child image display control, respectively;
performing image composition on the target real-world image and each of the plurality of image frames of the animation model according to a current offset location of the child image display control relative to the parent image display control, to obtain a plurality of composited images, each composited image having the target real-world image as its background and a corresponding image frame of the animation model; and
combining the plurality of composited images into a dynamic image animation.

### Claim 16 (depends on 15)

The non-transitory computer readable storage medium according to claim 15, wherein the displaying a skeleton animation of an animation model on a real-world image captured by the terminal comprises:
displaying the captured real-world image through a first image display component of the terminal; and
displaying the skeleton animation of the animation model through a second image display component of the terminal, wherein the second image display component is superimposed on the first image display component; and
the capturing a currently displayed target real-world image and recording the skeleton animation of the animation model comprises:
capturing the currently displayed target real-world image through the first image display component, and simultaneously recording the skeleton animation of the animation model through the second image display component.

### Claim 17 (depends on 15)

The non-transitory computer readable storage medium according to claim 15, wherein the plurality of operations further comprise:
displaying the target real-world image and each of the plurality of image frames of the animation model on an interface through the parent image display control and the child image display control.

### Claim 18 (depends on 15)

The non-transitory computer readable storage medium according to claim 15, wherein the plurality of operations further comprise:
determining a location in an interface according to a location of the animation model and a size of the skeleton animation, and adding an information display box to the location;
displaying, in the information display box, information inputted by a user;
performing image capture on the information display box, to obtain an information display box image; and
adding the information display box image to the dynamic image.

### Claim 19 (depends on 18)

The non-transitory computer readable storage medium according to claim 18, wherein the adding the information display box image to the dynamic image comprises:
performing image composition on the information display box image and each of the plurality of composited images, and combining obtained images into the dynamic image.

### Claim 20 (depends on 17)

The non-transitory computer readable storage medium according to claim 17, wherein the plurality of operations further comprise:
in response to the photographing instruction, recording an animation offset location of the current skeleton animation of the animation model relative to the real-world image; and
the displaying the target real-world image and each of the plurality of image frames of the animation model on a corresponding interface through the parent image display control and the child image display control comprises:
setting the current offset location of the child image display control relative to the parent image display control according to the animation offset location; and
displaying the target real-world image and each of the plurality of image frames of the animation model on the corresponding interface according to the parent image display control and the child image display control after the setting.