Method and apparatus for editing three-dimensional model

Abstract

The embodiments of the present application relate to the technical field of computers. Provided are a method and apparatus for editing a three-dimensional model. The method comprises: acquiring a three-dimensional model and a model editing instruction; dividing the three-dimensional model into at least two model components; editing the at least two model components on the basis of the model editing instruction, so as to acquire target model components corresponding to the at least two model components; and combining the target model components respectively corresponding to the at least two model components, so as to acquire a target three-dimensional model of the three-dimensional model.

Description

A three-dimensional model editing method and device

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 27, 2023, with application number 202310935332.8 and invention name “A method and device for editing a three-dimensional model”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of computers, and in particular to a method and device for editing a three-dimensional model. Background Art

[0003] 3D model technology has advantages such as low migration cost, no site restrictions, and can greatly reduce the operating costs of digital media-related industries. It is widely used in industrial manufacturing, live video broadcasting, online shopping, film and television entertainment and other fields.

[0004] Currently, three-dimensional models are mainly generated by modeling and rendering using computer graphics (CG). That is, a 3D model designer first creates an initial 3D model, and then renders the 3D model using hardware such as a graphics card, thereby rendering the 3D model. When editing the clothing, posture, style, expression, etc. of a 3D model, in order to avoid the 3D model designer from rebuilding the model, existing technologies often deform the already constructed 3D model to obtain the edited 3D model. However, since the amount of information in a 3D model is often very large, this method of deforming the entire constructed 3D model often makes it difficult to achieve the ideal 3D model editing effect.

[0005] Summary of the Invention

[0006] In view of this, embodiments of the present application provide a method and apparatus for processing a three-dimensional model, so as to improve the editing effect of the three-dimensional model.

[0007] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0008] In a first aspect, an embodiment of the present application provides a method for editing a three-dimensional model, comprising:

[0009] Obtain 3D models and model editing instructions;

[0010] Splitting the three-dimensional model into at least two model components;

[0011] Edit the at least two model components respectively based on the model editing instruction to obtain target model components corresponding to the at least two model components;

[0012] The target model components respectively corresponding to the at least two model components are combined to obtain a target three-dimensional model of the three-dimensional model.

[0013] As an optional implementation of the embodiment of the present invention, dividing the three-dimensional model into at least two model components includes:

[0014] Obtaining component annotation information of the three-dimensional model;

[0015] The three-dimensional model is divided into at least two model components based on the component annotation information of the three-dimensional model.

[0016] As an optional implementation of the embodiment of the present invention, dividing the three-dimensional model into at least two model components includes:

[0017] The three-dimensional model is segmented into at least two model components based on a three-dimensional semantic segmentation algorithm.

[0018] As an optional implementation of the embodiment of the present invention, dividing the three-dimensional model into at least two model components includes:

[0019] Segmenting the three-dimensional model into at least two model components based on a segmentation network model;

[0020] Among them, the segmentation network model is a model obtained by training a machine learning model based on a first sample data set; the first sample data set includes multiple sample three-dimensional models and component annotation information corresponding to the multiple sample three-dimensional models.

[0021] As an optional implementation of the embodiment of the present invention, editing the at least two model components respectively according to the model editing instruction to obtain target model components corresponding to the at least two model components includes:

[0022] Determining, according to the model editing instruction, edited network models corresponding to the at least two model components, respectively; the edited network model is a model obtained by training a machine learning model based on a second sample data set; the second sample data set includes a plurality of sample model components and a model component obtained by editing the plurality of sample model components based on the model editing instruction;

[0023] The target model components corresponding to the at least two model components are obtained according to the edit network models corresponding to the at least two model components.

[0024] As an optional implementation of the embodiment of the present invention, the step of obtaining target model components corresponding to the at least two model components according to the edit network models corresponding to the at least two model components includes:

[0025] According to the editing network model and the component material library corresponding to the at least two model components, target model components corresponding to the at least two model components are obtained.

[0026] As an optional implementation of the embodiment of the present invention, after dividing the three-dimensional model into at least two model components, the method further includes:

[0027] The at least two model components are added to the component library.

[0028] As an optional implementation of the embodiment of the present invention, after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model, the method further includes:

[0029] The target three-dimensional model is post-processed based on a preset geometric graphics processing algorithm.

[0030] As an optional implementation of the embodiment of the present invention, after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model, the method further includes:

[0031] Obtaining a texture map of the target three-dimensional model;

[0032] The target three-dimensional model is rendered based on the texture map to obtain a two-dimensional image corresponding to the target three-dimensional model.

[0033] In a second aspect, an embodiment of the present application provides a device for editing a three-dimensional model, comprising:

[0034] An acquisition unit, used for acquiring a three-dimensional model and model editing instructions;

[0035] a segmentation unit, configured to segment the three-dimensional model into at least two model components;

[0036] an editing unit, configured to edit the at least two model components respectively based on the model editing instruction to obtain target model components corresponding to the at least two model components;

[0037] A combining unit is used to combine the target model components respectively corresponding to the at least two model components to obtain a target three-dimensional model of the three-dimensional model.

[0038] As an optional implementation of the embodiment of the present application, the segmentation unit is specifically used to obtain component annotation information of the three-dimensional model; and segment the three-dimensional model into at least two model components based on the component annotation information of the three-dimensional model.

[0039] As an optional implementation of the embodiment of the present application, the segmentation unit is specifically used to segment the three-dimensional model into at least two model components based on a three-dimensional semantic segmentation algorithm.

[0040] As an optional implementation of the embodiment of the present application, the segmentation unit is specifically configured to segment the three-dimensional model into at least two model components based on a segmentation network model;

[0041] Among them, the segmentation network model is a model obtained by training a machine learning model based on a first sample data set; the first sample data set includes multiple sample three-dimensional models and component annotation information corresponding to the multiple sample three-dimensional models.

[0042] As an optional implementation of an embodiment of the present application, the editing unit is specifically used to determine the editing network models corresponding to the at least two model components respectively according to the model editing instruction; the editing network model is a model obtained by training the machine learning model based on a second sample data set; the second sample data set includes multiple sample model components and model components obtained after editing the multiple sample model components based on the model editing instruction; the target model components corresponding to the at least two model components are obtained according to the editing network models corresponding to the at least two model components.

[0043] As an optional implementation of the embodiment of the present application, the editing unit is specifically used to obtain the target model components corresponding to the at least two model components according to the corresponding editing network model and component material library input by the at least two model components.

[0044] As an optional implementation of the embodiment of the present application, the segmentation unit is further configured to add the at least two model components to the component material library after segmenting the three-dimensional model into at least two model components.

[0045] As an optional implementation of an embodiment of the present application, the combination unit is also used to post-process the target three-dimensional model based on a preset geometric graphics processing algorithm after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model.

[0046] As an optional implementation of an embodiment of the present application, the combination unit is further used to obtain a texture map of the target three-dimensional model after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model; and render the target three-dimensional model based on the texture map to obtain a two-dimensional image corresponding to the target three-dimensional model.

[0047] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory is used to store a computer program and the processor is used to enable the electronic device to implement the three-dimensional model editing method described in any of the above embodiments when executing the computer program.

[0048] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which, when the computer program is executed by a computing device, enables the computing device to implement the three-dimensional model editing method described in any of the above embodiments.

[0049] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a computer, enables the computer to implement the three-dimensional model editing method described in any one of the above-mentioned embodiments.

[0050] The three-dimensional model editing method provided in the embodiment of the present application first divides the three-dimensional model into at least two model components after obtaining the three-dimensional model and the model editing instruction, and then edits the at least two model components respectively based on the model editing instruction to obtain the target model components corresponding to the at least two model components, and then combines the target model components respectively corresponding to the at least two model components to obtain the target three-dimensional model of the three-dimensional model. Compared with the prior art of editing the three-dimensional model as a whole, since the three-dimensional model editing method provided in the embodiment of the present application divides the three-dimensional model into at least two model components when editing the three-dimensional model, and then edits the at least two model components obtained by dividing the three-dimensional model respectively, and combines the editing results of the at least two model components to obtain the edited three-dimensional model, the embodiment of the present application can reduce the amount of information of the editing object, improve the editing effect of each component, and thus improve the editing effect of the three-dimensional model. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] FIG1 is a flowchart of a method for editing a three-dimensional model according to an embodiment of the present application;

[0054] FIG2 is a schematic diagram of three-dimensional model segmentation provided in an embodiment of the present application;

[0055] FIG3 is a second flowchart of the method for editing a three-dimensional model provided in an embodiment of the present application;

[0056] FIG4 is a structural diagram of a three-dimensional model editing device provided in an embodiment of the present application;

[0057] FIG5 is a schematic diagram of a three-dimensional model editing device provided in an embodiment of the present application;

[0058] FIG6 is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned objectives, features and advantages of the present application, the scheme of the present application will be further described below. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present application, but the present application may also be implemented in other ways different from those described herein. Obviously, the embodiments in the specification are only part of the embodiments of the present application, not all of the embodiments.

[0061] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete way. In addition, in the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more.

[0062] The embodiment of the present application provides a method for editing a three-dimensional model. As shown in FIG1 , the method for editing a three-dimensional model includes the following steps S11 to S14:

[0063] S11. Obtain a three-dimensional model and model editing instructions.

[0064] In some embodiments, the method of obtaining the three-dimensional model may include: reading the three-dimensional model from a remote server or a local storage space according to a specified Uniform Resource Identifier (URI).

[0065] The three-dimensional model in the embodiment of the present application can be a three-dimensional mesh model, a point cloud model (Point Cloud), etc. The three-dimensional mesh model can include: geometric information and attribute information of the model such as vertex position coordinates, topological structure, vertex normal vector, color, etc.

[0066] The model editing instructions in the embodiment of the present application are used to indicate the editing operations that need to be performed on the three-dimensional model. The model editing instructions can be natural language instructions such as text and voice, or they can be computer language instructions such as code and script. The embodiment of the present application does not limit this, and the model editing instructions shall be able to indicate the editing operations that need to be performed on the three-dimensional model.

[0067] S12. Divide the three-dimensional model into at least two model components.

[0068] In some embodiments, segmenting the three-dimensional model into at least two model components includes determining a component to be edited based on a model editing instruction, and segmenting the three-dimensional model into at least two model components based on the component to be edited. For example, if the three-dimensional model is a three-dimensional model of a person, and the model editing instruction instructs editing the person's clothing, the three-dimensional model of the person may be segmented into two model components: a clothing component and a body component.

[0069] In some embodiments, segmenting the three-dimensional model into at least two model components includes segmenting the to-be-edited component into at least two model components according to a preset segmentation strategy. For example, if the three-dimensional model is a three-dimensional model of a person, and the preset segmentation strategy is to segment the three-dimensional model into a head component, a torso component, a left upper limb component, a right upper limb component, a left lower limb component, and a right lower limb component, then the preset segmentation strategy can be used to segment the three-dimensional model of the person into six model components: a head component, a torso component, a left upper limb component, a right upper limb component, a left lower limb component, and a right lower limb component.

[0070] For example, as shown in FIG2 , when the three-dimensional model is a three-dimensional model of a person 200 , the three-dimensional model of the person 200 can be divided into four model components, namely: a head component 201 , a left upper limb component 202 , a right upper limb component 203 and a torso component 204 .

[0071] S13. Edit the at least two model components respectively based on the model editing instruction to obtain target model components corresponding to the at least two model components.

[0072] In the embodiment of the present application, the target model component corresponding to any model component is the model component obtained by editing the model component based on the model editing instruction.

[0073] S14. Combine the target model components corresponding to the at least two model components to obtain a target three-dimensional model of the three-dimensional model.

[0074] The three-dimensional model editing method provided in the embodiment of the present application first divides the three-dimensional model into at least two model components after obtaining the three-dimensional model and the model editing instruction, and then edits the at least two model components respectively based on the model editing instruction to obtain the target model components corresponding to the at least two model components, and then combines the target model components respectively corresponding to the at least two model components to obtain the target three-dimensional model of the three-dimensional model. Compared with the prior art of editing the three-dimensional model as a whole, since the three-dimensional model editing method provided in the embodiment of the present application divides the three-dimensional model into at least two model components when editing the three-dimensional model, and then edits the at least two model components obtained by dividing the three-dimensional model respectively, and combines the editing results of the at least two model components to obtain the edited three-dimensional model, the embodiment of the present application can reduce the amount of information of the editing object, improve the editing effect of each component, and thus improve the editing effect of the three-dimensional model.

[0075] As an extension and refinement of the above embodiment, the present application provides another method for editing a three-dimensional model. As shown in FIG3 , the method for editing a three-dimensional model includes the following steps:

[0076] S301: Acquire a 3D model and model editing instructions.

[0077] In some embodiments, obtaining the three-dimensional model and the model editing instructions is achieved by displaying a model editing interface to the user through a model editing application, and determining the three-dimensional model and the model editing instructions based on user operations in the model editing interface.

[0078] S302: Divide the three-dimensional model into at least two model components.

[0079] In some embodiments, the implementation of step S302 (segmenting the three-dimensional model into at least two model components) includes the following steps a and b:

[0080] Step a: Obtain component annotation information of the three-dimensional model.

[0081] Step b: dividing the three-dimensional model into at least two model components based on the component annotation information of the three-dimensional model.

[0082] That is, when generating a three-dimensional model, the three-dimensional model is semantically segmented and annotated, and the three-dimensional model is divided into model components according to the annotation information.

[0083] In some embodiments, the implementation of the above step S302 (segmenting the three-dimensional model into at least two model components) includes: segmenting the three-dimensional model into at least two model components based on a three-dimensional semantic segmentation algorithm.

[0084] For example, the 3D semantic segmentation algorithm may be a projection-based 3D semantic segmentation algorithm, that is, the 3D model is first projected into multiple 2D images from multiple angles, semantic segmentation is then performed on the multiple projected 2D images, and the 3D model is segmented based on the semantic segmentation results of the multiple 2D images.

[0085] In some embodiments, the implementation of the above step S302 (segmenting the three-dimensional model into at least two model components) includes: segmenting the three-dimensional model into at least two model components based on a segmentation network model.

[0086] Among them, the segmentation network model is a model obtained by training a machine learning model based on a first sample data set; the first sample data set includes multiple sample three-dimensional models and component annotation information corresponding to the multiple sample three-dimensional models.

[0087] Exemplarily, the machine learning model may be a deep neural network model (DNN), a convolutional neural network model (CNN), or the like.

[0088] In some embodiments, the training process of the segmentation network model may include: inputting a sample three-dimensional model into the segmentation network model to be trained, and obtaining the semantic segmentation result of the sample three-dimensional model output by the segmentation network model to be trained, calculating the loss value based on the semantic segmentation result of the sample three-dimensional model, the component annotation information corresponding to the sample three-dimensional model, and a preset loss function, and adjusting the model parameters of the segmentation network model to be trained based on the loss value.

[0089] S303: Determine the editing network models corresponding to the at least two model components respectively according to the model editing instruction.

[0090] Among them, the edited network model is a model obtained by training a machine learning model based on a second sample data set; the second sample data set includes multiple sample model components and model components obtained after editing the multiple sample model components based on the model editing instructions.

[0091] For example, there are two style conversion network models pre-trained for facial components. The first style conversion network model is used to convert facial components into a cartoon style, and the second style conversion network model is used to convert facial components into an oil painting style. When the model editing instruction indicates that the three-dimensional model is converted into a cartoon style, the first style conversion network model is determined as the editing network model corresponding to the facial component.

[0092] S304: Obtain target model components corresponding to the at least two model components according to the edit network models corresponding to the at least two model components.

[0093] That is, the model component is input into the corresponding editing network model, and the output of the editing network model is used as the target model component corresponding to the model component.

[0094] In some embodiments, obtaining target model components corresponding to the at least two model components according to the edit network models corresponding to the at least two model components respectively includes:

[0095] According to the editing network model and the component material library corresponding to the at least two model components, target model components corresponding to the at least two model components are obtained.

[0096] For example: when editing a facial model component, you need to add a glasses model component to the facial component. You can first obtain the matching glasses model component from the component material library, and then obtain the facial component wearing glasses based on the glasses model component, the facial model component, and the editing network model corresponding to the facial model component.

[0097] S305: Combine the target model components corresponding to the at least two model components to obtain a target three-dimensional model of the three-dimensional model.

[0098] That is, the edited model components (the target model components corresponding to the at least two model components) are reassembled to obtain the edited three-dimensional model (the target three-dimensional model).

[0099] S306: Post-process the target three-dimensional model based on a preset geometric graphics processing algorithm.

[0100] Since the target three-dimensional model obtained by combining the target model components corresponding to the at least two model components is likely to have problems such as mold penetration, holes, abnormal deformation, missing mesh at component connections, burrs, etc., the embodiment of the present application will introduce a post-processing graphic geometry processing algorithm to ensure the rationality and driving capability of the generation of the target three-dimensional model after combining the target model components corresponding to the at least two model components.

[0101] 4, in some embodiments, the 3D model editing device for executing the 3D model editing method of the embodiment shown in FIG3 includes: an input module 41, a segmentation module 42, a plurality of editing network models 43, a combination module 44, and a post-processing module 45. The input module 41 is used to obtain the 3D model E mesh and model editing instructions, the segmentation module 42 is used to segment the three-dimensional model into multiple model components (E head、E la 、E ra ……), multiple editing network models 43 are respectively used to edit a model component to obtain the edited model component (D head 、D la 、D ra ……), the combining module 44 is used to combine the edited model components into the edited three-dimensional model D mesh The post-processing module 45 is used to post-process the target three-dimensional model based on the geometric graphics processing algorithm to obtain a processed three-dimensional model D mesh ′.

[0102] In some embodiments, after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model, the three-dimensional model editing method provided in the embodiment of the present application also includes: obtaining the texture map of the target three-dimensional model; rendering the target three-dimensional model based on the texture map to obtain a two-dimensional image corresponding to the target three-dimensional model.

[0103] In some embodiments, the method of obtaining the texture map of the target three-dimensional model may include: obtaining an image specified by a user as the texture map of the target three-dimensional model.

[0104] In other embodiments, the method of obtaining the texture map of the target three-dimensional model may include: deforming and aligning the texture map of the three-dimensional model based on the difference between the three-dimensional model and the target three-dimensional model to obtain the texture map of the target three-dimensional model.

[0105] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present application also provides a three-dimensional model editing device, which corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will no longer repeat the details of the aforementioned method embodiment one by one, but it should be clear that the three-dimensional model editing device in this embodiment can correspond to all the contents of the aforementioned method embodiment.

[0106] An embodiment of the present application provides a device for editing a three-dimensional model. FIG5 is a schematic structural diagram of the device for editing a three-dimensional model. As shown in FIG5 , the device 500 for editing a three-dimensional model includes:

[0107] An acquisition unit 51 is used to acquire a three-dimensional model and a model editing instruction;

[0108] a segmentation unit 52, configured to segment the three-dimensional model into at least two model components;

[0109] An editing unit 53, configured to edit the at least two model components respectively based on the model editing instruction to obtain target model components corresponding to the at least two model components;

[0110] The combining unit 54 is configured to combine the target model components corresponding to the at least two model components to obtain a target three-dimensional model of the three-dimensional model.

[0111] As an optional implementation of the embodiment of the present application, the segmentation unit 52 is specifically used to obtain component annotation information of the three-dimensional model; and segment the three-dimensional model into at least two model components based on the component annotation information of the three-dimensional model.

[0112] As an optional implementation of the embodiment of the present application, the segmentation unit 52 is specifically configured to segment the three-dimensional model into at least two model components based on a three-dimensional semantic segmentation algorithm.

[0113] As an optional implementation of the embodiment of the present application, the segmentation unit 52 is specifically configured to segment the three-dimensional model into at least two model components based on a segmentation network model;

[0114] Among them, the segmentation network model is a model obtained by training a machine learning model based on a first sample data set; the first sample data set includes multiple sample three-dimensional models and component annotation information corresponding to the multiple sample three-dimensional models.

[0115] As an optional implementation of an embodiment of the present application, the editing unit 53 is specifically used to determine the editing network models corresponding to the at least two model components respectively according to the model editing instruction; the editing network model is a model obtained by training the machine learning model based on the second sample data set; the second sample data set includes multiple sample model components and model components obtained after editing the multiple sample model components based on the model editing instruction; the target model components corresponding to the at least two model components are obtained according to the editing network models corresponding to the at least two model components.

[0116] As an optional implementation of the embodiment of the present application, the editing unit 53 is specifically used to obtain the target model components corresponding to the at least two model components according to the corresponding editing network model and component material library input by the at least two model components.

[0117] As an optional implementation of the embodiment of the present application, the segmentation unit 52 is further configured to add the at least two model components to the component material library after segmenting the three-dimensional model into at least two model components.

[0118] As an optional implementation of an embodiment of the present application, the combination unit 54 is also used to post-process the target three-dimensional model based on a preset geometric graphics processing algorithm after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model.

[0119] As an optional implementation of an embodiment of the present application, the combination unit 54 is also used to obtain a texture map of the target three-dimensional model after combining the target model components corresponding to the at least two model components to obtain the editing result of the three-dimensional model; and render the target three-dimensional model based on the texture map to obtain a two-dimensional image corresponding to the target three-dimensional model.

[0120] The three-dimensional model editing device provided in this embodiment can execute the three-dimensional model editing method provided in the above method embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0121] Based on the same inventive concept, an embodiment of the present application further provides an electronic device. FIG6 is a schematic diagram of the structure of the electronic device provided in an embodiment of the present application. As shown in FIG6 , the electronic device provided in this embodiment includes: a memory 61 and a processor 62. The memory 61 is used to store a computer program, and the processor 62 is used to execute the three-dimensional model editing method provided in the above embodiment when executing the computer program.

[0122] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the computing device implements the three-dimensional model editing method provided in the above embodiment.

[0123] Based on the same inventive concept, an embodiment of the present application further provides a computer program product. When the computer program product is run on a computer, the computing device implements the three-dimensional model editing method provided in the above embodiment.

[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0125] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware model components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0126] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0127] Computer-readable media includes both permanent and non-permanent, removable and non-removable storage media. Storage media can implement any method or technology for storing information, which can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein, and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for editing a three-dimensional model, wherein: include: Obtain 3D models and model editing instructions; Splitting the three-dimensional model into at least two model components; Edit the at least two model components respectively based on the model editing instruction to obtain target model components corresponding to the at least two model components; The target model components respectively corresponding to the at least two model components are combined to obtain a target three-dimensional model of the three-dimensional model.

2. The method according to claim 1, wherein: The step of dividing the three-dimensional model into at least two model components comprises: Obtaining component annotation information of the three-dimensional model; The three-dimensional model is segmented into at least two model components based on the component annotation information of the three-dimensional model.

3. The method according to claim 1, wherein: The step of dividing the three-dimensional model into at least two model components comprises: The three-dimensional model is segmented into at least two model components based on a three-dimensional semantic segmentation algorithm.

4. The method according to claim 1, wherein: The step of dividing the three-dimensional model into at least two model components comprises: Segmenting the three-dimensional model into at least two model components based on a segmentation network model; Among them, the segmentation network model is a model obtained by training a machine learning model based on a first sample data set; the first sample data set includes multiple sample three-dimensional models and component annotation information corresponding to the multiple sample three-dimensional models.

5. The method according to claim 1, wherein: The editing of the at least two model components respectively according to the model editing instruction to obtain target model components corresponding to the at least two model components includes: Determine the editing instructions corresponding to the at least two model components respectively according to the model editing instruction The editing network model is a model obtained by training a machine learning model based on a second sample data set; the second sample data set includes a plurality of sample model components and a model component obtained by editing the plurality of sample model components based on the model editing instruction; The target model components corresponding to the at least two model components are obtained according to the edited network models corresponding to the at least two model components.

6. The method according to claim 5, wherein: The step of obtaining target model components corresponding to the at least two model components according to the edit network models corresponding to the at least two model components inputs respectively includes: According to the editing network model and the component material library corresponding to the at least two model components, the target model components corresponding to the at least two model components are obtained.

7. The method according to claim 6, wherein: After segmenting the three-dimensional model into at least two model components, the method further comprises: The at least two model components are added to the component library.

8. The method according to any one of claims 1 to 7, wherein: After combining the target model components respectively corresponding to the at least two model components to obtain the editing result of the three-dimensional model, the method further includes: The target three-dimensional model is post-processed based on a preset geometric graphics processing algorithm.

9. The method according to any one of claims 1 to 7, wherein: After combining the target model components respectively corresponding to the at least two model components to obtain the editing result of the three-dimensional model, the method further includes: Obtaining a texture map of the target three-dimensional model; The target three-dimensional model is rendered based on the texture map to obtain a two-dimensional image corresponding to the target three-dimensional model.

10. A three-dimensional model editing device, wherein: include: An acquisition unit, used for acquiring a three-dimensional model and a model editing instruction; A segmentation unit, used for segmenting the three-dimensional model into at least two model components; An editing unit is used to edit the at least two models based on the model editing instruction. The components are edited to obtain target model components corresponding to the at least two model components; A combining unit is used to combine the target model components respectively corresponding to the at least two model components to obtain a target three-dimensional model of the three-dimensional model.

11. An electronic device, wherein: include: A memory and a processor, wherein the memory is used to store a computer program and the processor is used to enable the electronic device to implement the three-dimensional model editing method described in any one of claims 1-9 when executing the computer program.

12. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the three-dimensional model editing method according to any one of claims 1 to 9.

Images