# US 2022/0044476 A1 · Three-dimensional model processing method, 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 2022/0044476 A1
- Document ID: US20220044476A1
- Status: Published application
- Kind: A1
- Application number: 17/451,599
- Filed: 2021-10-20
- Published: 2022-02-10
- Earliest claimed: 2020-11-23
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science Technology Co., LTD
- Inventors: Qian YING; Chen ZHAO; Li XU
- Web page: https://patentgrep.com/patent/US20220044476A1

## CPC

- B33Y 50/00: Data acquisition or data processing for additive manufacturing
- G06T 17/10: Constructive solid geometry [CSG] using solid primitives, e.g. cylinders, cubes
- G06N 3/02: Neural networks
- G06N 3/045: Combinations of networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06T 15/08: Volume rendering
- G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
- G06T 2219/2012: Colour editing, changing, or manipulating; Use of colour codes
- Y02D 10/00: Energy efficient computing, e.g. low power processors, power management or thermal management
- B33Y: ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

A three-dimensional model processing method, an electronic device, and a storage medium are provided, which are related to fields of deep learning, augmented reality, and the like. The specific implementation includes: generating a target virtual three-dimensional model based on a target model template; generating a target picture based on graphic and textual information and a preset network; and determining a superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture.

## Claims

### Claim 1

A three-dimensional model processing method, comprising:
generating a target virtual three-dimensional model based on a target model template;
generating a target picture based on graphic and textual information and a preset network; and
determining a superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture.

### Claim 2 (depends on 1)

The three-dimensional model processing method according to claim 1, further comprising:
determining a candidate three-dimensional model template corresponding to a target shape category, in response to selecting the target shape category; selecting the target model template from the candidate three-dimensional model template corresponding to the target shape category;
wherein generating the target virtual three-dimensional model based on the target model template comprises: performing a weight adjustment on the target model template, to obtain an adjusted target model template, and generating the target virtual three-dimensional model according to the adjusted target model template.

### Claim 3 (depends on 1)

The three-dimensional model processing method according to claim 1, wherein generating the target picture based on the graphic and textual information and the preset network comprises:
formatting textual information in the graphic and textual information, to obtain formatted textual information; inputting identification graphic information in the graphic and textual information and the formatted textual information into the preset network, to obtain N pictures output by the preset network; and determining the target picture based on the N pictures, wherein N is an integer greater than or equal to 1.

### Claim 4 (depends on 3)

The three-dimensional model processing method according to claim 3, wherein determining the target picture based on the N pictures comprises:
inputting the N pictures into a discriminator, to obtain discrimination results respectively corresponding to the N pictures output by the discriminator;
taking M pictures, among the N pictures, corresponding to a first result in the discrimination results as M candidate pictures, wherein M is an integer greater than or equal to 1 and less than or equal to N; and
selecting the target picture from the M candidate pictures.

### Claim 5 (depends on 1)

The three-dimensional model processing method according to claim 1, wherein generating the target virtual three-dimensional model based on the target model template comprises:
selecting the target model template from a candidate three-dimensional model template; and adjusting the target model template based on a model-related parameter, to obtain the target virtual three-dimensional model.

### Claim 6 (depends on 1)

The three-dimensional model processing method according to claim 1, wherein determining the superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
determining an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
performing a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 7

The three-dimensional model processing method according to 2, wherein determining the superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
determining an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
performing a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 8

The three-dimensional model processing method according to 3, wherein determining the superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
determining an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
performing a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 9

The three-dimensional model processing method according to 4, wherein determining the superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
determining an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
performing a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 10

The three-dimensional model processing method according to 5, wherein determining the superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
determining an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
performing a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 11 (depends on 6)

The three-dimensional model processing method according to claim 6, wherein determining the initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture comprises:
performing a three-dimensional rendering on the target virtual three-dimensional model and the target picture by using a local three-dimensional rendering engine, to obtain an initial rendering picture of the target virtual three-dimensional model;
or
uploading the target virtual three-dimensional model and the target picture to a server provided with a three-dimensional rendering engine, and acquiring an initial rendering picture of the target virtual three-dimensional model fed back by the server provided with the three-dimensional rendering engine.

### Claim 12

An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor, wherein
the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:
generate a target virtual three-dimensional model based on a target model template;
generate a target picture based on graphic and textual information and a preset network; and
determine a superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture.

### Claim 13 (depends on 12)

The electronic device according to claim 12, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
determine a candidate three-dimensional model template corresponding to a target shape category, in response to selecting the target shape category; select the target model template from the candidate three-dimensional model template corresponding to the target shape category;
wherein generating the target virtual three-dimensional model based on the target model template comprises: performing a weight adjustment on the target model template, to obtain an adjusted target model template, and generating the target virtual three-dimensional model according to the adjusted target model template.

### Claim 14 (depends on 12)

The electronic device according to claim 12, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
format textual information in the graphic and textual information, to obtain formatted textual information; input identification graphic information in the graphic and textual information and the formatted textual information into the preset network, to obtain N pictures output by the preset network; and determining the target picture based on the N pictures, wherein N is an integer greater than or equal to 1.

### Claim 15 (depends on 14)

The electronic device according to claim 14, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
input the N pictures into a discriminator, to obtain discrimination results respectively corresponding to the N pictures output by the discriminator;
take M pictures, among the N pictures, corresponding to a first result in the discrimination results as M candidate pictures, wherein M is an integer greater than or equal to 1 and less than or equal to N; and
select the target picture from the M candidate pictures.

### Claim 16 (depends on 12)

The electronic device according to claim 12, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
select the target model template from a candidate three-dimensional model template; and adjust the target model template based on a model-related parameter, to obtain the target virtual three-dimensional model.

### Claim 17 (depends on 12)

The electronic device according to claim 12, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
determine an initial rendering picture of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture; and
perform a material rendering on the initial rendering picture of the target virtual three-dimensional model based on a target material-related parameter, to obtain a rendering picture of the target virtual three-dimensional model.

### Claim 18 (depends on 17)

The electronic device according to claim 17, wherein the instructions are executed by the at least one processor to further enable the at least one processor to:
perform a three-dimensional rendering on the target virtual three-dimensional model and the target picture by using a local three-dimensional rendering engine, to obtain an initial rendering picture of the target virtual three-dimensional model;
or
upload the target virtual three-dimensional model and the target picture to a server provided with a three-dimensional rendering engine, and acquire an initial rendering picture of the target virtual three-dimensional model fed back by the server provided with the three-dimensional rendering engine.

### Claim 19

A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions, when executed by a computer, cause the computer to:
generate a target virtual three-dimensional model based on a target model template;
generate a target picture based on graphic and textual information and a preset network; and
determine a superposition processing result of the target virtual three-dimensional model based on the target virtual three-dimensional model and the target picture.

### Claim 20 (depends on 19)

The non-transitory computer-readable storage medium according to claim 19, wherein the computer instructions, when executed by a computer, further cause the computer to:
determine a candidate three-dimensional model template corresponding to a target shape category, in response to selecting the target shape category; select the target model template from the candidate three-dimensional model template corresponding to the target shape category;
wherein generating the target virtual three-dimensional model based on the target model template comprises: performing a weight adjustment on the target model template, to obtain an adjusted target model template, and generating the target virtual three-dimensional model according to the adjusted target model template.
