# US 2025/0095260 A1 · Image processing method and apparatus, electronic device 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 2025/0095260 A1
- Document ID: US20250095260A1
- Status: Published application
- Kind: A1
- Application number: 18/882,642
- Filed: 2024-09-11
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Beijing Zitiao Network Technology Co., Ltd.
- Applicants: Beijing ZItiao Network Technology Co., Ltd.
- Inventors: Wang LIU; Jiawei CHEN
- Web page: https://patentgrep.com/patent/US20250095260A1

## CPC

- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G06T 13/205: {driven by audio data}
- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The embodiment of the disclosure provides an image processing method and apparatus, an electronic device and a storage medium, and the method includes: obtaining audio data and target part data corresponding to a target object; determining first to-be-fused data corresponding to the audio data; and determining second to-be-fused data corresponding to the target part data; and determining target fusion data based on the first to-be-fused data and the second to-be-fused data to drive a display of a target virtual object based on the target fusion data. According to the technical solution provided by the embodiment of the disclosure, the following technical effect is achieved: the audio information and the part data of the target object are processed online, target fusion data is determined, and a display of a three-dimensional virtual object is driven based on the target fusion data.

## Claims

### Claim 1

An image processing method, comprising:
obtaining audio data and target part data corresponding to a target object, wherein the target part data corresponds to position information and state information of a predetermined capture part;
determining first to-be-fused data corresponding to the audio data;
determining second to-be-fused data corresponding to the target part data; and
determining target fusion data based on the first to-be-fused data and the second to-be-fused data to drive a display of a target virtual object based on the target fusion data.

### Claim 2 (depends on 1)

The method of claim 1, wherein obtaining the audio data and the target part data corresponding to the target object comprises:
in response to a virtual object driving operation, capturing audio information corresponding to the target object based on an audio capture device; and
capturing the target part data corresponding to the target object based on a face image capture device,
wherein a part corresponding to the target part data comprises at least one part of the five sense organs.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the first to-be-fused data corresponding to the audio data comprises:
determining a plurality of pieces of text information corresponding to the audio data, and determining pronunciation information corresponding to the plurality of pieces of text information; and
determining first to-be-fused data of a mouth part based on the pronunciation information.

### Claim 4 (depends on 1)

The method of claim 1, wherein determining the second to-be-fused data corresponding to the target part comprises:
determining mesh point data of a plurality of meshes corresponding to the target part based on the target part data; and
determining the mesh point data as the second to-be-fused data.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining the target fusion data based on the first to-be-fused data and the second to-be-fused data comprises:
determining a maximum value among the first to-be-fused data and the second to-be-fused data corresponding to a same mesh point, and determining the maximum value as a target mesh point data of the corresponding mesh point; and
determining the target fusion data according to the target mesh point data of at least part of mesh points.

### Claim 6 (depends on 5)

The method of claim 5, wherein determining the target fusion data according to the target mesh point data of at least part of the mesh points comprises:
determining to-be-superimposed fusion data of the target mesh point by adjusting the target mesh point data according to a predetermined fusion curve; and
updating the target fusion data based on the to-be-superimposed fusion data.

### Claim 7 (depends on 6)

The method of claim 6, wherein the fusion curve corresponds to a predetermined facial expression.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
updating a facial expression and a mouth shape of the target virtual object based on the target fusion data, so that the facial expression and the mouth shape of the target virtual object correspond to those of the target object.

### Claim 9

An electronic device, comprising:
one or more processors; and
a storage device configured to store one or more programs;
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement acts comprising:
obtaining audio data and target part data corresponding to a target object, wherein the target part data corresponds to position information and state information of a predetermined capture part;
determining first to-be-fused data corresponding to the audio data;
determining second to-be-fused data corresponding to the target part data; and
determining target fusion data based on the first to-be-fused data and the second to-be-fused data to drive a display of a target virtual object based on the target fusion data.

### Claim 10 (depends on 9)

The device of claim 9, wherein obtaining the audio data and the target part data corresponding to the target object comprises:
in response to a virtual object driving operation, capturing audio information corresponding to the target object based on an audio capture device; and
capturing the target part data corresponding to the target object based on a face image capture device,
wherein a part corresponding to the target part data comprises at least one part of the five sense organs.

### Claim 11 (depends on 9)

The device of claim 9, wherein determining the first to-be-fused data corresponding to the audio data comprises:
determining a plurality of pieces of text information corresponding to the audio data, and determining pronunciation information corresponding to the plurality of pieces of text information; and
determining first to-be-fused data of a mouth part based on the pronunciation information.

### Claim 12 (depends on 9)

The device of claim 9, wherein determining the second to-be-fused data corresponding to the target part comprises:
determining mesh point data of a plurality of meshes corresponding to the target part based on the target part data; and
determining the mesh point data as the second to-be-fused data.

### Claim 13 (depends on 9)

The device of claim 9, wherein determining the target fusion data based on the first to-be-fused data and the second to-be-fused data comprises:
determining a maximum value among the first to-be-fused data and the second to-be-fused data corresponding to a same mesh point, and determining the maximum value as a target mesh point data of the corresponding mesh point; and
determining the target fusion data according to the target mesh point data of at least part of mesh points.

### Claim 14 (depends on 13)

The device of claim 13, wherein determining the target fusion data according to the target mesh point data of at least part of the mesh points comprises:
determining to-be-superimposed fusion data of the target mesh point by adjusting the target mesh point data according to a predetermined fusion curve; and
updating the target fusion data based on the to-be-superimposed fusion data.

### Claim 15 (depends on 14)

The device of claim 14, wherein the fusion curve corresponds to a predetermined facial expression.

### Claim 16 (depends on 9)

The device of claim 9, wherein the acts further comprise:
updating a facial expression and a mouth shape of the target virtual object based on the target fusion data, so that the facial expression and the mouth shape of the target virtual object correspond to those of the target object.

### Claim 17

A non-transitory storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, implements acts comprising:
obtaining audio data and target part data corresponding to a target object, wherein the target part data corresponds to position information and state information of a predetermined capture part;
determining first to-be-fused data corresponding to the audio data;
determining second to-be-fused data corresponding to the target part data; and
determining target fusion data based on the first to-be-fused data and the second to-be-fused data to drive a display of a target virtual object based on the target fusion data.

### Claim 18 (depends on 17)

The medium of claim 17, wherein obtaining the audio data and the target part data corresponding to the target object comprises:
in response to a virtual object driving operation, capturing audio information corresponding to the target object based on an audio capture device; and
capturing the target part data corresponding to the target object based on a face image capture device,
wherein a part corresponding to the target part data comprises at least one part of the five sense organs.

### Claim 19 (depends on 17)

The medium of claim 17, wherein determining the first to-be-fused data corresponding to the audio data comprises:
determining a plurality of pieces of text information corresponding to the audio data, and determining pronunciation information corresponding to the plurality of pieces of text information; and
determining first to-be-fused data of a mouth part based on the pronunciation information.

### Claim 20 (depends on 17)

The medium of claim 17, wherein determining the second to-be-fused data corresponding to the target part comprises:
determining mesh point data of a plurality of meshes corresponding to the target part based on the target part data; and
determining the mesh point data as the second to-be-fused data.