CN107845135B - Three-dimensional simulation model and model library construction method and device - Google Patents
Three-dimensional simulation model and model library construction method and device Download PDFInfo
- Publication number
- CN107845135B CN107845135B CN201711129059.0A CN201711129059A CN107845135B CN 107845135 B CN107845135 B CN 107845135B CN 201711129059 A CN201711129059 A CN 201711129059A CN 107845135 B CN107845135 B CN 107845135B
- Authority
- CN
- China
- Prior art keywords
- model
- style
- content
- library
- models
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for constructing a three-dimensional simulation model and a model library, wherein the method comprises the following steps: obtaining a model library, and classifying the models in the model library to form a sub-model library; searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library; receiving different models under the import path, and respectively using the models as a content model and a style model; synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model; and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library. The method effectively realizes the diversity of the three-dimensional simulation model, enriches the model library, effectively reduces the calculated amount when constructing the three-dimensional model library with huge number and rich content style, and improves the construction efficiency of the three-dimensional simulation model and the model library.
Description
Technical Field
The invention belongs to the technical field of computer three-dimensional simulation modeling, relates to a method and a device for constructing a three-dimensional simulation model and a model library, and particularly relates to a method and a device for constructing a three-dimensional simulation model and a model library based on multi-granularity style content transfer.
Background
In the modern times, the traditional life, study and work modes of people are rapidly changed by the increasingly diverse computer technologies, and with the continuous development of computer hardware, software, digital media and other technologies, the technical requirements of diversification of computer simulation models are greatly promoted and developed. In the age of rapid development of computer technology, computer simulation models play a great role in a plurality of fields such as simulated movies, games, virtual reality and the like, and realizing the diversity of the simulation models and enriching the diversity of the simulation model library construction models are important subjects in the current research field. With the rapid development of model construction related processing software, how to utilize style and content related semantic information of a model to better process and use a three-dimensional model, and how to synthesize a new three-dimensional model by utilizing the semantic information gradually become the latest focus of attention in the field of computer simulation three-dimensional modeling.
The cartoon seen by people for many years is two-dimensional, the advertisement and trademark on the street are three-dimensional at present, and the computer enters a three-dimensional era along with the development of a simulation model for decades, so that the demand of the three-dimensional model is doubled at present, and the three-dimensional graph is ubiquitous around people. The production of computer simulation models, computer animation and model diversification have become popular topics of computer graphics in recent years, and research levels on the diversification of computer simulation models are gradually deepened.
Nowadays, the development of the computer graphics field makes the requirements for computer simulation models play a significant role in numerous social industries and fields, for example, a crowd evacuation simulation system, computer simulation models required by various game production, and fields of real film shooting and production with magnificent fields all show the importance of the diversity of the computer simulation models. With the rapid development of computers, the application of three-dimensional models in various industries is rapidly popularized and deepened. With the continuous development of computer graphics, people have higher requirements on the diversity of models. In a series of fields needing a large number of models, such as crowd evacuation, games and the like, people have different shapes, different dresses and large action difference, and each person has unique physical actions and dresses, so that the authenticity can be improved. Therefore, the needed computer simulation model has huge scale, needs a large number of roles, has rich diversity, causes the problems of large calculation amount, difficult realization and the like.
In conclusion, an effective solution is not yet available for the problems of large calculation amount, long time consumption and difficult realization of the existing computer simulation three-dimensional modeling technology in constructing a three-dimensional model library with huge number and rich content styles.
Disclosure of Invention
Aiming at the defects in the prior art and solving the problems of large calculation amount, long time consumption and difficult realization when the three-dimensional model library with huge number and rich content style is constructed in the prior art, the invention provides the three-dimensional simulation model and the construction method and the device of the model library, which effectively realize the diversity of the three-dimensional simulation model, enrich the model library, effectively reduce the calculation amount when the three-dimensional model library with huge number and rich content style is constructed and improve the construction efficiency of the three-dimensional simulation model and the model library.
The invention aims to provide a method for constructing a three-dimensional simulation model.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for constructing a three-dimensional simulation model, the method comprising:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
In the invention, in the construction of a new three-dimensional simulation model, firstly, a model library is searched according to semantic information to determine an import path, so that a user can select the type of the constructed model according to requirements conveniently; secondly, style content transfer is adopted, a bounding box of a style model is selected, a new model with style model style and content model content is generated according to the style model bounding box on the basis of the content model, the diversity of the three-dimensional simulation model is realized, the calculation amount in constructing a new three-dimensional model library is effectively reduced, and the construction efficiency of the three-dimensional simulation model is improved.
As a further preferable scheme, in the method, after the import path is determined, a model under the import path is selected, the selected model is rendered to generate a model preview, and a user selects whether to import the selected model according to the model preview.
As a further preferable aspect, in the method, the import path includes a content path and a genre path, and the model in the content path is received as the content model and the model in the genre path is received as the genre model.
As a further preferred scheme, in the method, after receiving different models in the import path, the models are respectively preprocessed, and the preprocessing is to modify the model size to a preset uniform model size and adjust the model size to a suitable model position.
As a further preferable scheme, in the method, the specific step of synthesizing the content model and the style model into the new model by using the style content transfer method includes:
correspondingly partitioning the content model and the style model;
and respectively extracting bounding boxes of each part after the style model is divided, and taking the bounding boxes as the bounding boxes of the corresponding part after the content model is divided.
As a further preferable scheme, in the method, the content model in the synthesized new model is further divided into multiple granularities, and deformation adjustment is performed on each divided block.
In the invention, the content model in the synthesized new model is further divided into multiple granularities, and each divided block is subjected to deformation adjustment, so that the part of the content model, which needs to be further stylized, of the model tends to be stylized.
It is a second object of the present invention to provide a computer-readable storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme:
a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the process of:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
The third purpose of the invention is to provide a three-dimensional simulation model building device.
In order to achieve the purpose, the invention adopts the following technical scheme:
a device for constructing a three-dimensional simulation model adopts a computing terminal device and comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the process of:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
The fourth purpose of the invention is to provide a method for constructing a three-dimensional simulation model library.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for constructing a three-dimensional simulation model library comprises the following steps:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
As a further preferable scheme, in the method, the model library includes a background model and models, the models include an animal model, a character model, an architectural model and a small static-object model, and the animal model, the character model, the architectural model and the small static-object model are further classified to finally form each sub-model library.
As a further preferable scheme, in the method, after the import path is determined, a model under the import path is selected, the selected model is rendered to generate a model preview, and a user selects whether to import the selected model according to the model preview.
As a further preferable aspect, in the method, the import path includes a content path and a genre path, and the model in the content path is received as the content model and the model in the genre path is received as the genre model.
As a further preferred scheme, in the method, after receiving different models in the import path, the models are respectively preprocessed, and the preprocessing is to modify the model size to a preset uniform model size and adjust the model size to a suitable model position.
As a further preferable scheme, in the method, the specific step of synthesizing the content model and the style model into the new model by using the style content transfer method includes:
correspondingly partitioning the content model and the style model;
and respectively extracting bounding boxes of each part after the style model is divided, and taking the bounding boxes as the bounding boxes of the corresponding part after the content model is divided.
As a further preferable scheme, in the method, the content model in the synthesized new model is further divided into multiple granularities, and deformation adjustment is performed on each divided block.
It is a fifth object of the present invention to provide a computer-readable storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme:
a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the process of:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
The sixth purpose of the invention is to provide a device for constructing a three-dimensional simulation model library.
In order to achieve the purpose, the invention adopts the following technical scheme:
a device for constructing a three-dimensional simulation model library adopts a computing terminal device and comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the process of:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
The invention has the beneficial effects that:
(1) according to the method and the device for constructing the three-dimensional simulation model and the model base, in the construction of a new three-dimensional simulation model, firstly, the model base is searched according to semantic information to determine the import path, so that a user can conveniently select the type of the constructed model according to the requirement; secondly, style content transfer is adopted, a bounding box of a style model is selected, a new model with style model style and content model content is generated according to the style model bounding box on the basis of the content model, the diversity of the three-dimensional simulation model is realized, the calculation amount in constructing a new three-dimensional model library is effectively reduced, and the construction efficiency of the three-dimensional simulation model is improved.
(2) According to the method and the device for constructing the three-dimensional simulation model and the model library, the content model in the synthesized new model is further divided into multiple granularities, and each divided block is subjected to deformation adjustment, so that the part of the content model, which needs to be further stylized, of the model tends to be stylized, and the model library is enriched.
(3) The method and the device for constructing the three-dimensional simulation model and the model library realize the functions of a small model library, the import of the model and the import according to the corresponding proportion, and have convenient and flexible operation; the model library is definite in classification, the model is convenient and quick to search, the intention of a user is met, the user can find a needed model in a complicated model sea, and the model can be determined according to the preview picture when the model is not determined to be needed.
(4) The method and the device for constructing the three-dimensional simulation model and the model library are not only limited to the technology of model library style content transfer, but also are suitable for making scene models, and have unprecedented effects in scenes with various styles, such as animation making scenes, crowd simulation, animation effect and the like.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flowchart of a method of example 1 of the present invention;
FIG. 2 is a flowchart of a method of example 4 of the present invention;
FIG. 3 is a flowchart of a method of example 6 of the present invention;
FIG. 4 is a schematic view of a chair according to embodiment 6 of the present invention;
FIG. 5 is a schematic diagram showing the hierarchy of the classification classes of the model library according to embodiment 6 of the present invention;
FIG. 6 is a diagram showing a genre path and a content path when a model is imported in embodiment 6 of the present invention;
FIG. 7 is a schematic diagram of a chair preview not generated in embodiment 6 of the present invention;
FIG. 8 is a schematic diagram of generation of a chair preview in embodiment 6 of the present invention;
FIG. 9 is a schematic diagram showing the operation of the style transformation according to embodiment 6 of the present invention;
FIG. 10 is a schematic diagram of multi-granularity partitioning of a content model after style transformation in embodiment 6 of the present invention;
FIG. 11 is a schematic diagram of a stylized manual variation of a stylized transform of embodiment 6 of the present invention;
FIG. 12 is a schematic diagram of a chair model after multi-granularity style transformation in embodiment 6 of the present invention;
fig. 13 is a schematic diagram of another model style transformation according to embodiment 6 of the present invention.
The specific implementation mode is as follows:
the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Aiming at the defects in the prior art and solving the problems of large calculation amount, long time consumption and difficult realization when the three-dimensional model library with huge number and rich content style is constructed in the prior art, the invention provides the three-dimensional simulation model and the construction method and the device of the model library, which effectively realize the diversity of the three-dimensional simulation model, enrich the model library, effectively reduce the calculation amount when the three-dimensional model library with huge number and rich content style is constructed and improve the construction efficiency of the three-dimensional simulation model and the model library.
The embodiments and features of the embodiments in the present application may be combined with each other without conflict. The invention is further described with reference to the following figures and examples.
Example 1:
the purpose of this embodiment 1 is to provide a method for constructing a three-dimensional simulation model.
In order to achieve the purpose, the invention adopts the following technical scheme:
as shown in figure 1 of the drawings, in which,
a method for constructing a three-dimensional simulation model, the method comprising:
step (1): obtaining a model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method;
the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
In the invention, in the construction of a new three-dimensional simulation model, firstly, a model library is searched according to semantic information to determine an import path, so that a user can select the type of the constructed model according to requirements conveniently; secondly, style content transfer is adopted, a bounding box of a style model is selected, a new model with style model style and content model content is generated according to the style model bounding box on the basis of the content model, the diversity of the three-dimensional simulation model is realized, the calculation amount in constructing a new three-dimensional model library is effectively reduced, and the construction efficiency of the three-dimensional simulation model is improved.
In the step (2), after the import path is determined, the model under the import path is selected, the selected model is rendered to generate a model preview, and a user selects whether to import the selected model according to the model preview.
It should be noted that in this embodiment, a preview image in advance is required, and when the model is imported, the module may select an angle to render according to its own needs to generate the preview image, where the generated preview image may generate a corresponding picture in the folder where the model is located. In the process of importing the model, a process of generating a preview image is provided, because the model cannot be seen before the model is imported under the model path, the model is rendered at the position to generate the model preview image, whether the model is the model required by the user is conveniently judged in advance, the model is imported into Maya to select an angle, the rendering is clicked in the Maya, and the preview image with the selected angle appears at the moment, so that the method is convenient and fast.
In step (2), the import path includes a content path and a genre path, and the model in the content path is received as a content model and the model in the genre path is received as a genre model.
It should be noted that after the path of the model is defined, the model needed by the user can be found in the corresponding directory after the program is imported, and the model is imported. The model import here has two windows, one is the model import of the style path, and the other is the model import of the content path, and the import principle is the same, so that the style model can be conveniently extracted under the style path, and the content model can be conveniently extracted under the content path.
In the step (3), after receiving different models in the import path, preprocessing the models respectively, wherein the preprocessing is to modify the model size into a preset unified model size and adjust the model size to a proper model position.
It should be noted that, to want style conversion, a model needs to be imported first, but the specification of the model is large or small, and in order to avoid the problem that the difference is too large when the model is imported, the length, width and height of the model can be input when the model is imported, so that the model is more convenient and faster to convert with each other when the model is imported, and the model can be dragged left and right in the importing process to reach a proper position, so that the conversion is convenient.
In the step (4), the specific step of synthesizing the content model and the style model into the new model by using the style content transfer method includes:
step (4-1): correspondingly partitioning the content model and the style model;
step (4-2): and respectively extracting bounding boxes of each part after the style model is divided, and taking the bounding boxes as the bounding boxes of the corresponding part after the content model is divided.
In step (4), the content model in the synthesized new model is further divided into multiple granularities, and deformation adjustment is performed on each divided block.
In the invention, the content model in the synthesized new model is further divided into multiple granularities, and each divided block is subjected to deformation adjustment, so that the part of the content model, which needs to be further stylized, of the model tends to be stylized.
It should be noted that the core of this embodiment is mainly to extract bounding boxes of each part of the model under the style path, and the bounding boxes serve as bounding boxes of each part of the content path model, so that a new model is synthesized. Different from the style model, the content model is subjected to multi-granularity blocking after blocking, and each block is deformed, so that the model tends to be stylized. The style content transformation of the model combines the style model under the style path and the content model under the content path to generate a new model with content model content and style model style.
Example 2:
the object of this embodiment 2 is to provide a computer-readable storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme:
a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the process of:
step (1): obtaining a model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method;
the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
In the present embodiment, examples of the computer-readable recording medium include magnetic storage media (e.g., ROM, RAM, USB, floppy disks, hard disks, etc.), optical recording media (e.g., CD-ROMs or DVDs), PC interfaces (e.g., PCI-Expres, WiFi, etc.), and the like. However, the various aspects of the present disclosure are not limited thereto.
Example 3:
the purpose of this embodiment 3 is to provide a three-dimensional simulation model building apparatus.
In order to achieve the purpose, the invention adopts the following technical scheme:
a device for constructing a three-dimensional simulation model adopts a computing terminal device, which comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the process of:
step (1): obtaining a model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method;
the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model.
Example 4:
embodiment 4 is to provide a method for constructing a three-dimensional simulation model library, and this embodiment is based on embodiment 1.
In order to achieve the purpose, the invention adopts the following technical scheme:
as shown in figure 2 of the drawings, in which,
a method for constructing a three-dimensional simulation model library comprises the following steps:
step (1): obtaining a model library, and classifying the models in the model library to form a sub-model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and (5): and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
In the step (1), the model library comprises a background model and a model, the model comprises an animal model, a character model, a building model and a small static-object model, and the animal model, the character model, the building model and the small static-object model are further classified to finally form each sub-model library.
It should be noted that, the transfer of style content requires a large number of models of the same type, and since the models are transformed in the same type, the models need to be classified appropriately. Firstly, three-dimensional modeling software Maya and MEL language carried by the Maya are adopted for programming design, models are collected in advance and classified, and the current models are mainly divided into a background part and a model part. The models are further divided into a series of models such as animal models, building models, character models and the like. The model is convenient to select, and the model can be selected more easily according to requirements.
It should be noted that the specific implementation process of step (2) to step (4) in this embodiment is the same as that of step (2) to step (4) in embodiment 1.
It should be noted that, this embodiment not only can implement single model import, but also can implement batch import of models according to corresponding proportions, implement small model library function, import of models, and import according to corresponding proportions, and is convenient and flexible to operate.
The embodiment consists of two parts, namely model library manufacturing and multi-granularity style content transfer. The model library comprises a model library construction module, a model import module and a model rendering module, the model is imported into a Maya interface by the model library module, semantic search enables the model to be more convenient to find, and a user can easily find the model according to the model required by the user; the model is imported through the model library, and after the model is imported, the style model can be transformed according to the expected idea to become a new model with style and content model contents.
Example 5:
the object of this embodiment 5 is to provide a computer-readable storage medium.
In order to achieve the purpose, the invention adopts the following technical scheme:
a computer readable storage medium having stored therein a plurality of instructions adapted to be loaded by a processor of a terminal device and to perform the process of:
step (1): obtaining a model library, and classifying the models in the model library to form a sub-model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and (5): and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
In the present embodiment, examples of the computer-readable recording medium include magnetic storage media (e.g., ROM, RAM, USB, floppy disks, hard disks, etc.), optical recording media (e.g., CD-ROMs or DVDs), PC interfaces (e.g., PCI-Expres, WiFi, etc.), and the like. However, the various aspects of the present disclosure are not limited thereto.
Example 6:
the purpose of this embodiment 6 is to provide a device for constructing a three-dimensional simulation model library.
In order to achieve the purpose, the invention adopts the following technical scheme:
a device for constructing a three-dimensional simulation model library adopts a computing terminal device, which comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the process of:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
step (1): obtaining a model library, and classifying the models in the model library to form a sub-model library;
step (2): searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
and (3): receiving different models under the import path, and respectively using the models as a content model and a style model;
and (4): synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
and (5): and merging the new model library into the sub model library until all models in the sub model library are executed, so as to enrich the model library.
Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using general purpose computer means, or alternatively, they can be implemented using program code that is executable by computing means, such that they are stored in memory means and executed by computing means, or they are separately fabricated into individual integrated circuit modules, or multiple modules or steps of them are fabricated into a single integrated circuit module. The present invention is not limited to any specific combination of hardware and software.
In this embodiment, taking a variant of a chair as an example, as shown in fig. 3-4, the step of using the three-dimensional simulation model and the model library of the device component by the user includes:
step (1): in the construction module of the model library, the collected models are classified according to the characteristics of the models, so that a user can see the models at a glance, and the models wanted by the user are obtained according to the thought of the user, so that the model library is convenient to use and has clear layers.
It should be noted that the model can be smoothly imported only after the model is imported, the following operation is carried out after the Maya is imported, all model libraries are laid by the whole system, a code popup window of mel language is operated, and the model required by the user is selected under the path;
in the step (1), the specific types include:
the model library comprises background models and models, wherein the models comprise character models, building models and small still life models, each module is divided into a plurality of modules, and the more clear the division is, the easier the user searches, as shown in fig. 5.
Step (2): the model rendering process is a process of importing one more preview model, the chair model needed by the user is found under the path of the step (1), the preview image of the model can be displayed in the right window, and the model can be selected more conveniently and quickly.
It should be noted that no rendering of the preview image is not generated, the model is imported by clicking, and then the model is imported into the Maya interface, and when the appropriate angle and size are selected, and the rendering is clicked, the appropriate preview image appears. The user may select a model from the preview.
In the step (2), the specific steps include:
step (2-1): the code is run into the Maya editor and a corresponding dialog box pops up when the path selection, genre path and content path appear, as shown in fig. 6.
Step (2-2): and (3) clicking a path from the left side of the content path window to select the style path and the content path generated in the step (2-1), selecting the position of the chair model library, and selecting the model.
Step (2-3): and a mesh file window on the right side of the window is provided with a preview of a selection model, a right click is performed, an import is selected, and a chair is imported.
Step (2-4): the same procedure as in (2-3) is performed on the style model to import the style model, and the style model is also imported into the Maya interface.
In the step (2-3), the generation of the preview map includes the following detailed steps:
step (2-3-1): the mesh file on the right side of the window appears a gray frame, and the preview is not generated at this time, as shown in fig. 7;
step (2-3-2): clicking import by right clicking, and importing the model;
step (2-3-3): and selecting a proper angle, and finally summarizing the whole situation to the maximum. The angle is suitable.
Step (2-3-4): right clicking on the gray box selects render icon model to be rendered out, clicking on right refresh. The preview is generated as shown in fig. 8.
And (3): and (3) rendering in the step (2), carrying out model style transformation, importing a style model from a style path, importing a content model from a content path, operating a program to carry out model transformation, wherein the style transformation is the transformation between models of the same type, and if the style transformation is not the transformation of the same type, the model style transformation has no meaning. Such as between chairs, between people. And selecting a content model module, clicking the acquisition bounding box, clicking the corresponding part of the style model, clicking for operation, and converting the model. The content model programs a model having a style model style. After transformation, clicking a model part which needs to be further stylized, manually deforming, and changing the content model into a model with a style model style.
In the step (3), the specific steps include:
step (3-1): the style model is imported, the morphing program is run, the content to be morphed of the content model is clicked and selected, the load behind the transformation form is clicked, and the morphing module of the content model is selected, as shown in fig. 9.
Step (3-2): and (3-1) repeating the step, clicking the load after the transformation after, and selecting the deformation module of the style model.
Step (3-3): after the global style transformation, clicking on the content model requires further stylized content.
Step (3-4): clicking on the command content model bounding box programs the model of the style model style, at which point the content model has been stylized.
Step (3-5): and after the overall style is transformed, clicking a small module of which the content model needs to be further stylized, comparing the style model, and manually deforming to enable the content model to be more similar to the style of the style model, and properly adjusting to finish the deformation of the model.
The deformed model has been subjected to multi-granularity blocking in advance, as shown in fig. 10. A further stylization is performed against the style model multiple chair backs as shown in fig. 11. The model now already has the style of the stylistic model. As shown in fig. 12.
FIG. 13 is a schematic diagram of another model style transformation according to the present invention.
The invention has the beneficial effects that:
(1) according to the method and the device for constructing the three-dimensional simulation model and the model base, in the construction of a new three-dimensional simulation model, firstly, the model base is searched according to semantic information to determine the import path, so that a user can conveniently select the type of the constructed model according to the requirement; secondly, style content transfer is adopted, a bounding box of a style model is selected, a new model with style model style and content model content is generated according to the style model bounding box on the basis of the content model, the diversity of the three-dimensional simulation model is realized, the calculation amount in constructing a new three-dimensional model library is effectively reduced, and the construction efficiency of the three-dimensional simulation model is improved.
(2) According to the method and the device for constructing the three-dimensional simulation model and the model library, the content model in the synthesized new model is further divided into multiple granularities, and each divided block is subjected to deformation adjustment, so that the part of the content model, which needs to be further stylized, of the model tends to be stylized, and the model library is enriched.
(3) The method and the device for constructing the three-dimensional simulation model and the model library realize the functions of a small model library, the import of the model and the import according to the corresponding proportion, and have convenient and flexible operation; the model library is definite in classification, the model is convenient and quick to search, the intention of a user is met, the user can find a needed model in a complicated model sea, and the model can be determined according to the preview picture when the model is not determined to be needed.
(4) The method and the device for constructing the three-dimensional simulation model and the model library are not only limited to the technology of model library style content transfer, but also are suitable for making scene models, and have unprecedented effects in scenes with various styles, such as animation making scenes, crowd simulation, animation effect and the like.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A method for constructing a three-dimensional simulation model is characterized by comprising the following steps:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
2. The method of claim 1, wherein after determining the import path, selecting a model under the import path, rendering the selected model to generate a model preview, and a user selecting whether to import the selected model according to the model preview;
and/or
The import path comprises a content path and a style path, a model under the content path is received as a content model, and a model under the style path is received as a style model;
and/or
And after receiving different models in the import path, respectively preprocessing the models, wherein the preprocessing comprises the steps of modifying the model size into a preset unified model size and adjusting the model size to a proper model position.
3. A computer readable storage medium having stored therein a plurality of instructions, wherein the instructions are adapted to be loaded by a processor of a terminal device and to perform the following:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
4. A device for constructing a three-dimensional simulation model adopts a computing terminal device and comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the following:
obtaining a model library;
searching a model library according to semantic information to determine an import path, wherein the types of models under the import path are the same;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
5. A method for constructing a three-dimensional simulation model library is characterized by comprising the following steps:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
merging the new module library into the sub-model library until all the models in the complete sub-model library are executed, and enriching the model library;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
6. The method of claim 5, wherein the library of models includes background models and models, the models include animal models, character models, architectural models, and static small models, and the animal models, character models, architectural models, and static small models are further classified to form libraries of sub-models.
7. The method of claim 5, wherein after determining the import path, selecting a model under the import path, rendering the selected model to generate a model preview, and a user selecting whether to import the selected model according to the model preview;
and/or
The import path comprises a content path and a style path, a model under the content path is received as a content model, and a model under the style path is received as a style model;
and/or
After receiving different models in the import path, respectively preprocessing the models, wherein the preprocessing comprises the steps of modifying the model size into a preset unified model size and adjusting the model size to a proper model position;
and/or
The specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
8. A computer readable storage medium having stored therein a plurality of instructions, wherein the instructions are adapted to be loaded by a processor of a terminal device and to perform the following:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
merging the new module library into the sub-model library until all the models in the complete sub-model library are executed, and enriching the model library;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
9. A device for constructing a three-dimensional simulation model library adopts a computing terminal device and comprises a processor and a computer readable storage medium, wherein the processor is used for realizing instructions; a computer readable storage medium for storing a plurality of instructions adapted to be loaded by a processor and to perform the following:
obtaining a model library, and classifying the models in the model library to form a sub-model library;
searching a model library according to semantic information to determine an import path, wherein the import path corresponds to a sub-model library;
receiving different models under the import path, and respectively using the models as a content model and a style model;
synthesizing the content model and the style model into a new model by adopting a style content transfer method, and storing the new model in a new model library; the style content transfer method is to extract the bounding box of the style model as the bounding box of the content model;
merging the new module library into the sub-model library until all the models in the complete sub-model library are executed, and enriching the model library;
the specific steps of synthesizing the content model and the style model into a new model by adopting a style content transfer method comprise:
correspondingly partitioning the content model and the style model;
extracting bounding boxes of each part after the style model is divided respectively to be used as bounding boxes of corresponding parts after the content model is divided into blocks;
and/or
And further carrying out multi-granularity division on the content model in the synthesized new model, and carrying out deformation adjustment on each divided block.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711129059.0A CN107845135B (en) | 2017-11-15 | 2017-11-15 | Three-dimensional simulation model and model library construction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711129059.0A CN107845135B (en) | 2017-11-15 | 2017-11-15 | Three-dimensional simulation model and model library construction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107845135A CN107845135A (en) | 2018-03-27 |
| CN107845135B true CN107845135B (en) | 2020-11-20 |
Family
ID=61679436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711129059.0A Expired - Fee Related CN107845135B (en) | 2017-11-15 | 2017-11-15 | Three-dimensional simulation model and model library construction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107845135B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109783885B (en) * | 2018-12-25 | 2023-08-11 | 山东师范大学 | Multi-physical field coupling simulation analysis method and system for intelligent power module |
| CN111179422B (en) * | 2019-12-31 | 2023-08-04 | 深圳市优必选科技股份有限公司 | Model construction method and device and terminal equipment |
| CN113487727B (en) * | 2021-07-14 | 2022-09-02 | 广西民族大学 | Three-dimensional modeling system, device and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009067351A1 (en) * | 2007-11-19 | 2009-05-28 | Caustic Graphics, Inc. | Systems and methods for rendering with ray tracing |
| CN101923462A (en) * | 2009-06-10 | 2010-12-22 | 成都如临其境创意科技有限公司 | FlashVR-based three-dimensional mini-scene network publishing engine |
| CN102088472A (en) * | 2010-11-12 | 2011-06-08 | 中国传媒大学 | Wide area network-oriented decomposition support method for animation rendering task and implementation method |
| CN102663801A (en) * | 2012-04-19 | 2012-09-12 | 北京天下图数据技术有限公司 | Method for improving three-dimensional model rendering performance |
| CN105006023A (en) * | 2015-08-04 | 2015-10-28 | 北京航空航天大学 | Multi-category three-dimension model combination modeling method supporting aided design |
| CN105069827A (en) * | 2015-08-19 | 2015-11-18 | 北京中科大洋科技发展股份有限公司 | Method for processing video transitions through three-dimensional model |
| WO2016058085A1 (en) * | 2014-10-16 | 2016-04-21 | Arb Labs Inc. | Systems, methods and devices for monitoring game activities |
| CN106446351A (en) * | 2016-08-31 | 2017-02-22 | 郑州捷安高科股份有限公司 | Real-time drawing-oriented large-scale scene organization and scheduling technology and simulation system |
-
2017
- 2017-11-15 CN CN201711129059.0A patent/CN107845135B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009067351A1 (en) * | 2007-11-19 | 2009-05-28 | Caustic Graphics, Inc. | Systems and methods for rendering with ray tracing |
| CN101923462A (en) * | 2009-06-10 | 2010-12-22 | 成都如临其境创意科技有限公司 | FlashVR-based three-dimensional mini-scene network publishing engine |
| CN102088472A (en) * | 2010-11-12 | 2011-06-08 | 中国传媒大学 | Wide area network-oriented decomposition support method for animation rendering task and implementation method |
| CN102663801A (en) * | 2012-04-19 | 2012-09-12 | 北京天下图数据技术有限公司 | Method for improving three-dimensional model rendering performance |
| WO2016058085A1 (en) * | 2014-10-16 | 2016-04-21 | Arb Labs Inc. | Systems, methods and devices for monitoring game activities |
| CN105006023A (en) * | 2015-08-04 | 2015-10-28 | 北京航空航天大学 | Multi-category three-dimension model combination modeling method supporting aided design |
| CN105069827A (en) * | 2015-08-19 | 2015-11-18 | 北京中科大洋科技发展股份有限公司 | Method for processing video transitions through three-dimensional model |
| CN106446351A (en) * | 2016-08-31 | 2017-02-22 | 郑州捷安高科股份有限公司 | Real-time drawing-oriented large-scale scene organization and scheduling technology and simulation system |
Non-Patent Citations (2)
| Title |
|---|
| 3D Diff：An interactive Approach to Mesh Differencing and Conflict Resolution;Anthony Steed等;《Association for Computing Machinery》;20121231;全文 * |
| 基于高斯过程分类器的三维模型多粒度语义检索;高波涌 等;《模式识别与人工智能》;20111031;第24卷(第5期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107845135A (en) | 2018-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11328523B2 (en) | Image composites using a generative neural network | |
| WO2020125567A1 (en) | Automatic animation generation method, and automatic animation generation system | |
| CN103620545B (en) | The classification of media collection, scalable present | |
| CN105409201B (en) | Automated video cycle with progressive dynamic | |
| US8966356B1 (en) | Providing views of three-dimensional (3D) object data models | |
| CN107845135B (en) | Three-dimensional simulation model and model library construction method and device | |
| CN112074876A (en) | Authoring content in a three-dimensional environment | |
| CN106530371A (en) | Method and device for editing and playing animation | |
| JP7240505B2 (en) | Voice packet recommendation method, device, electronic device and program | |
| US20180143741A1 (en) | Intelligent graphical feature generation for user content | |
| KR20140024361A (en) | Employing mesh files to animate transitions in client applications | |
| Sorger et al. | Metamorphers: Storytelling templates for illustrative animated transitions in molecular visualization | |
| CN110705242A (en) | Method and device for manufacturing slide template and electronic equipment | |
| CN111460770B (en) | Method, device, equipment and storage medium for synchronizing element attributes in document | |
| Zhang | Three‐Dimensional Animation Space Design Based on Virtual Reality | |
| Dai et al. | Harmonious Group Choreography with Trajectory-Controllable Diffusion | |
| Zhang et al. | Research of Simulation of Creative Stage Scene Based on the 3DGans Technology. | |
| KR20150101064A (en) | System for making cartoon character | |
| Shi et al. | A new automatic visual scene segmentation algorithm for flash movie | |
| Liu et al. | Research on the computer case design of 3D human animation visual experience | |
| Gao et al. | Application of Digital Media Technology in 3D Animation Design and Production | |
| Li | Development and Application of 3D Home Design and Its Display System Based on VR Technology | |
| Lee et al. | Efficient 3D content authoring framework based on mobile AR | |
| CN118247434A (en) | Video generation method, apparatus, electronic device, storage medium, and program product | |
| CN113822957A (en) | Method and apparatus for synthesizing image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201120 Termination date: 20211115 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |