# US 11,308,692 B2 · Method and device for processing image, 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 11,308,692 B2
- Document ID: US11308692B2
- Status: Granted
- Kind: B2
- Application number: 16/901,379
- Filed: 2020-06-15
- Published: 2020-10-01
- Granted: 2022-04-19
- Earliest claimed: 2019-06-14
- Assignees: Beijing Dajia Internet Information Technology Co., Ltd.
- Applicants: Beijing Dajia Internet Information Technology Co., Ltd.
- Inventors: Liqian Ma
- Web page: https://patentgrep.com/patent/US11308692B2

## CPC

- G06T 17/205: {Re-meshing}
- G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)}
- G06T 7/344: {involving models}
- G06T 15/205: {Image-based rendering}
- G06T 2200/04: involving 3D image data
- G06T 2210/16: Cloth
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- Y02D: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE

## Abstract

Embodiments of the present disclosure relates to a method and device for processing an image, and a nonvolatile storage medium. The method includes: acquiring a first image and a first virtual object having a corresponding relationship with a preset standard model, the first image includes a target object; determining control information based on the target object and the standard model; obtaining a second virtual object matched with the target object by processing the first virtual object based on the control information; and generating a second image; the second image includes the target object fitted with the second virtual object.

## Claims

### Claim 1

A method for processing image, comprising:
acquiring a first image and a first virtual object, wherein the first image comprises a target object, the first virtual object has a corresponding relationship with a preset standard model, and the preset standard model is obtained by a three-dimensional reconstruction algorithm and a sample image;
determining a target model by reconstructing the target object in three-dimension based on the three-dimensional reconstruction algorithm, wherein the target model corresponds to the target object;
obtaining first preset vertexes on a first mesh model corresponding to the target model by transforming third preset vertexes on a third mesh model corresponding to the standard model through a first mapping between the target model and the standard model;
obtaining control information based on a transformation matrix of the first preset vertexes in local coordinate systems relative to a world coordinate system;
obtaining a second virtual object, by processing the first virtual object based on the control information, wherein the second virtual object is matched with the target object, and
generating a second image based on the second virtual object, wherein the second image comprise the target object fitted with the second virtual object.

### Claim 2 (depends on 1)

The method for processing image according to claim 1, wherein said obtaining the second virtual object comprises:
acquiring second preset vertexes on a second mesh model, wherein the second mesh model corresponds to the first virtual object; and
obtaining the second virtual object based on the second preset vertexes and the control information.

### Claim 3 (depends on 1)

The method for processing image according to claim 1, wherein before obtaining a second virtual object based on the first virtual object and the control information, the method further comprises:
aligning the first virtual object with the standard model;
selecting third preset vertexes on the third mesh model;
acquiring a conversion relationship of the third preset vertexes in local coordinate systems relative to a world coordinate system;
determining second preset vertexes on a second mesh model and weights corresponding to respective second preset vertexes; wherein the second mesh model corresponds to the first virtual object, the weights are inversely proportional to distances between the respective second preset vertexes and respective third preset vertexes; and
establishing a second-mapping between a third mesh model and the second mesh model by calculating coordinates of the respective second preset vertexes in the local coordinate systems of the third preset vertexes based on the conversion relationship.

### Claim 4

A device for processing image, comprising:
a processor; and
a memory for storing computer executable instructions; wherein the processor is configured to execute the computer executable instructions in the memory to perform following:
acquiring a first image and a first virtual object, wherein the first virtual object has the first image comprises a target object, the first virtual object has a corresponding relationship with a preset standard model, and the preset standard model is obtained by a three-dimensional reconstruction algorithm and a sample image;
determining a target model by reconstructing the target object in three-dimension based on the three-dimensional reconstruction algorithm, wherein the target model corresponds to the target object;
obtaining first preset vertexes on a first mesh model corresponding to the target model by transforming third preset vertexes on a third mesh model corresponding to the standard model through a first mapping between the target model and the standard model;
obtaining control information based on a transformation matrix of the first preset vertexes in local coordinate systems relative to a world coordinate system;
obtaining a second virtual object, by processing the first virtual object based on the control information; wherein the second virtual object is matched with the target object, and
generating a second image based on the second virtual object, wherein the second image comprise the target object fitted with the second virtual object.

### Claim 5 (depends on 4)

The method for processing image according to claim 4, wherein the processor is configured to execute the computer executable instructions in the memory to obtain the second virtual object by:
acquiring second preset vertexes on a second mesh model, wherein the second mesh model corresponds to the first virtual object; and
obtaining the second virtual object based on the second preset vertexes and the control information.

### Claim 6 (depends on 4)

The device for processing image according to claim 4, wherein the processor is further configured to execute the computer executable instructions in the memory to perform following:
before obtaining a second virtual object based on the first virtual object and the control information,
aligning the first virtual object with the standard model;
selecting third preset vertexes on the third mesh model;
acquiring a conversion relationship of the third preset vertexes in local coordinate systems relative to a world coordinate system;
determining second preset vertexes on a second mesh model and weights corresponding to respective second preset vertexes; wherein the second mesh model corresponds to the first virtual object, the weights are inversely proportional to distances between the respective second preset vertexes and respective third preset vertexes; and
establishing a second-mapping between a third mesh model and the second mesh model by calculating coordinates of the respective second preset vertexes in the local coordinate systems of the third preset vertexes based on the conversion relationship.

### Claim 7

A nonvolatile storage medium, configured to store computer executable instructions, when the computer executable instructions are executed by a processor of an electronic apparatus, following is implemented:
acquiring a first image and a first virtual object, wherein the first image comprises a target object, the first virtual object has a corresponding relationship with a preset standard model, and the preset standard model is obtained by a three-dimensional reconstruction algorithm and a sample image;
determining a target model by reconstructing the target object in three-dimension based on the three-dimensional reconstruction algorithm, wherein the target model corresponds to the target object;
obtaining first preset vertexes on a first mesh model corresponding to the target model by transforming third preset vertexes on a third mesh model corresponding to the standard model through a first mapping between the target model and the standard model;
obtaining control information based on a transformation matrix of the first preset vertexes in local coordinate systems relative to a world coordinate system;
obtaining a second virtual object, by processing the first virtual object based on the control information, wherein the second virtual object is matched with the target object, and
generating a second image based on the second virtual object, wherein the second image comprise the target object fitted with the second virtual object.

### Claim 8 (depends on 7)

The nonvolatile storage medium according to claim 7, wherein when the computer executable instructions are executed by the processor, said obtaining the second virtual object comprises:
acquiring second preset vertexes on a second mesh model, wherein the second mesh model corresponds to the first virtual object; and
obtaining the second virtual object based on the second preset vertexes and the control information.

### Claim 9 (depends on 7)

The nonvolatile storage medium according to claim 7, wherein when the computer executable instructions are executed by the processor, following is implemented:
before obtaining a second virtual object based on the first virtual object and the control information,
aligning the first virtual object with the standard model;
selecting third preset vertexes on the third mesh model;
acquiring a conversion relationship of the third preset vertexes in local coordinate systems relative to a world coordinate system;
determining second preset vertexes on a second mesh model and weights corresponding to respective second preset vertexes; wherein the second mesh model corresponds to the first virtual object, the weights are inversely proportional to distances between the respective second preset vertexes and respective third preset vertexes; and
establishing a second-mapping between a third mesh model and the second mesh model by calculating coordinates of the respective second preset vertexes in the local coordinate systems of the third preset vertexes based on the conversion relationship.