CN109049716A - Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model - Google Patents
Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model Download PDFInfo
- Publication number
- CN109049716A CN109049716A CN201811267277.5A CN201811267277A CN109049716A CN 109049716 A CN109049716 A CN 109049716A CN 201811267277 A CN201811267277 A CN 201811267277A CN 109049716 A CN109049716 A CN 109049716A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- model
- image
- printing
- illustraton
- 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.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C64/00—Additive manufacturing, i.e. manufacturing of three-dimensional [3D] objects by additive deposition, additive agglomeration or additive layering, e.g. by 3D printing, stereolithography or selective laser sintering
- B29C64/30—Auxiliary operations or equipment
- B29C64/386—Data acquisition or data processing for additive manufacturing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Materials Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- Mechanical Engineering (AREA)
- Optics & Photonics (AREA)
- Image Analysis (AREA)
Abstract
This application provides generation method, device, electronic equipment and the storage mediums of a kind of 3 D-printing illustraton of model, wherein generation method includes: the two dimensional image for obtaining target to be printed；Image characteristics extraction is carried out to two dimensional image, obtains the feature vector of two dimensional image；Obtained threedimensional model diagram generator is trained based on feature vector and in advance, generates the corresponding 3 D-printing illustraton of model of two dimensional image.Contacting between two dimensional image and threedimensional model of the embodiment of the present application by establishing entity to be printed, directly can generate three-dimensional entity model by two dimensional image, greatly reduce the threshold of threedimensional model personalized designs, improve the customization degree of 3D printing service.
Description
Technical field
This application involves 3D printing technique field, more particularly, to a kind of generation method of 3 D-printing illustraton of model, device,
Electronic equipment and storage medium.
Background technique
3D printing technique is a kind of emerging technology of rapid shaping field, it is processed using layering, is superimposed molding mode,
3D entity is generated by successively increasing material.3D printing technique has not only obtained making extensively in the heavy industry such as national defence, automobile
With quickly being sent out also by online personalized designs, the private forms such as customized in fields such as personalized gift, teaching mode, toys
Exhibition, but it is higher for the threedimensional model of 3D printing design threshold, and many users do not have the specialty background of design aspect, so that he
Can not create ideal threedimensional model.
Summary of the invention
In view of this, a kind of generation method for being designed to provide 3 D-printing illustraton of model of the application, device, electronics are set
Standby and storage medium, contacting between the two dimensional image and threedimensional model by establishing entity to be printed, can be directly by two dimension
Image generates three-dimensional entity model, greatly reduces the threshold of threedimensional model personalized designs, improves determining for 3D printing service
Inhibition and generation degree.
In a first aspect, the embodiment of the present application provides a kind of generation method of 3 D-printing illustraton of model, comprising: obtain wait beat
Print the two dimensional image of target；Image characteristics extraction is carried out to two dimensional image, obtains the feature vector of two dimensional image；Based on feature to
Amount and the threedimensional model diagram generator that training obtains in advance generate the corresponding 3 D-printing illustraton of model of two dimensional image.
With reference to first aspect, the embodiment of the present application provides the first possible embodiment of first aspect, wherein root
Threedimensional model diagram generator is generated according to following steps: obtaining the two dimensional sample image and three-dimensional samples image of sample entity；By two
Dimension sample image and three-dimensional samples image are separately input into initial threedimensional model diagram generator, to initial threedimensional model diagram generator
It is trained, obtains threedimensional model diagram generator.
The possible embodiment of with reference to first aspect the first, the embodiment of the present application provide second of first aspect
Possible embodiment, wherein initial threedimensional model diagram generator is trained, threedimensional model diagram generator is obtained, comprising:
Two dimensional sample image is input to initial threedimensional model diagram generator, obtains the corresponding three-dimensional generation image of two dimensional sample image；
Three-dimensional is generated image three-dimensional samples image corresponding with two dimensional sample image to be compared, generates comparison result；According to comparison
As a result the parameter for adjusting initial threedimensional model diagram generator, obtains threedimensional model diagram generator.
With reference to first aspect, the embodiment of the present application provides the third possible embodiment of first aspect, wherein base
Obtained threedimensional model diagram generator is trained in feature vector and in advance, generates the corresponding 3 D-printing model of two dimensional image
Figure, comprising: feature vector is converted into volume data using threedimensional model diagram generator, the voxelization for generating target to be printed is three-dimensional
Physical model figure；Voxelization three-dimensional entity model figure is converted to gridding 3 D-printing illustraton of model, for three-dimensional printer base
The 3 D-printing model of target to be printed is printed in gridding 3 D-printing illustraton of model.
The third possible embodiment with reference to first aspect, the embodiment of the present application provide the 4th kind of first aspect
Possible embodiment, wherein before voxelization three-dimensional entity model figure is converted to gridding 3 D-printing illustraton of model, also wrap
It includes: denoising being carried out to voxelization three-dimensional entity model figure, obtains the voxelization three-dimensional entity model figure after denoising.
The 4th kind of possible embodiment with reference to first aspect, the embodiment of the present application provide the 5th kind of first aspect
Possible embodiment, wherein voxelization three-dimensional entity model figure is converted to gridding 3 D-printing illustraton of model, comprising: will
Voxelization three-dimensional entity model figure after denoising is converted to the 3 D-printing illustraton of model of gridding.
Second aspect, the embodiment of the present application also provide a kind of generating means of 3 D-printing illustraton of model, comprising: obtain mould
Block, for obtaining the two dimensional image of target to be printed；Extraction module is obtained for carrying out image characteristics extraction to two dimensional image
The feature vector of two dimensional image；Generation module, the three-dimensional model diagram for being obtained based on feature vector and preparatory training are generated
Device generates the corresponding 3 D-printing illustraton of model of two dimensional image.
In conjunction with second aspect, the embodiment of the present application provides the first possible embodiment of second aspect, wherein obtains
Modulus block is also used to obtain the two dimensional sample image and three-dimensional samples image of sample entity；Generation module is also used to two-dimentional sample
This image and three-dimensional samples image are separately input into initial threedimensional model diagram generator, carry out to initial threedimensional model diagram generator
Training, obtains threedimensional model diagram generator.
The third aspect, the embodiment of the present application also provide a kind of electronic equipment, comprising: processor, memory and bus, storage
Device is stored with the executable machine readable instructions of processor, when electronic equipment operation, by total between processor and memory
Line communication, executed when machine readable instructions are executed by processor it is above-mentioned in a first aspect, or first aspect the first to the 5th kind
In step in any possible embodiment.
Fourth aspect, the embodiment of the present application also provide a kind of computer readable storage medium, the computer-readable storage medium
Computer program is stored in matter, which executes above-mentioned in a first aspect, or first aspect when being run by processor
The first step into any possible embodiment in the 5th kind.
Generation method, device, electronic equipment and the storage of a kind of 3 D-printing illustraton of model provided by the embodiments of the present application are situated between
Matter, contacting between the two dimensional image and threedimensional model by establishing entity to be printed directly can generate three by two dimensional image
Dimension physical model greatly reduces the door of threedimensional model personalized designs compared with engineer's threedimensional model in the prior art
Sill improve the customization degree of 3D printing service.The embodiment of the present application based on two dimensional image three-dimensional modeling the characteristics of be
Entire modeling process is to be automatically performed by computer, thus efficiency greatly improves, as the threedimensional model ratio for rebuilding achievement
The model established by hand has better fineness.
Further, the generation method of 3 D-printing illustraton of model provided by the embodiments of the present application, passes through three-dimensional modeling data
Collection is trained initial threedimensional model diagram generator, has trained and has generated suitable for the three-dimensional model diagram towards 3 D-printing
Device facilitates the design of threedimensional model.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of flow chart of the generation method of 3 D-printing illustraton of model provided by the embodiment of the present application；
Fig. 2 shows a kind of flow charts of the generation method of threedimensional model diagram generator provided by the embodiment of the present application；
Fig. 3 shows the process of the generation method of another kind threedimensional model diagram generator provided by the embodiment of the present application
Figure；
Fig. 4 shows the flow chart of the generation method of another kind 3 D-printing illustraton of model provided by the embodiment of the present application；
Fig. 5 shows a kind of functional module of the generating means of 3 D-printing illustraton of model provided by the embodiment of the present application
Figure；
Fig. 6 shows the structural schematic diagram of a kind of electronic equipment provided by the embodiment of the present application.
Icon: 10- obtains module；20- extraction module；30- generation module；100- processor；200- memory；300- is total
Line.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
In view of the threedimensional model design threshold for 3D printing is higher, many users do not have the profession back of design aspect
Scape, so that they can not create ideal threedimensional model.Based on this, the embodiment of the present application provides a kind of 3 D-printing illustraton of model
Generation method and device, be described below by embodiment.For convenient for understanding the present embodiment, first to the application
A kind of generation method of 3 D-printing illustraton of model disclosed in embodiment describes in detail.
The embodiment of the application first aspect provides a kind of generation method of 3 D-printing illustraton of model, as shown in Figure 1,
Include the following steps:
S101 obtains the two dimensional image of target to be printed；
S102 carries out image characteristics extraction to two dimensional image, obtains the feature vector of two dimensional image；
S103 trains based on feature vector and in advance obtained threedimensional model diagram generator, it is corresponding to generate two dimensional image
3 D-printing illustraton of model.
The generation method of 3 D-printing illustraton of model provided by the embodiments of the present application in step s101 can be by carry-on
Electronic equipment (such as digital camera, mobile phone, tablet computer) obtain the two dimensional image of target to be printed；In step s 102,
The two dimensional image that will acquire is input to image characteristics extraction device, to extract the feature of the two dimensional image of target to be printed, i.e.,
Feature vector；In step s 103, the feature vector of the two dimensional image extracted is input to preparatory trained threedimensional model
Diagram generator can directly generate the corresponding 3 D-printing illustraton of model of two dimensional image of target to be printed.The embodiment of the present application can
By the two dimensional image direct construction 3 D-printing illustraton of model of target to be printed, i.e., to be constructed by two dimensional image and restore three-dimensional in fact
Body provides the threshold of the modelling link substantially reduced in 3D printing cloud platform to convenient and fast 3D printing cloud for more users
Service.
It should be noted that the reconstructing three-dimensional model based on two dimensional image, refers to the two dimension shootings such as digital cameras
Image carry out image, vision calculate etc. reason, and it is unconventional practical three-dimension object is measured, it is automatic with computer program
It calculates and obtains three-dimensional information, and generate corresponding threedimensional model, compared to traditional manual modeling process, the process of automation shows
Unrivaled superiority is gone out.
In general, the feature of two dimensional image is extracted using the method for deep layer convolutional network, with the development of image recognition technology,
There are many mature image characteristics extraction devices to be put forward one after another, for example, LeNet, AlexNet, VggNet, GoogleNet,
ResNet and MobileNet etc..The embodiment of the present application preferred depth residual error network (Residual Networks, ResNet)-
50 are used as image characteristics extraction device, because the input of multilayer convolution is added by the structure in depth residual error network with output, in this way
Operation will not increase additional parameter and design flow to network, can also greatly increase model training speed, improve training effect
Fruit, and when the number of plies of model increases, the problem of this structure can prevent model degradation, specifically removes the last layer
Except the classification layer of network, remainder layer can regard feature extraction layer as, therefore we choose the output that layer 2048 second from the bottom is tieed up
Feature vector as two dimensional image, it is preferable that the spy of 2048 dimensions can be extracted from the two dimensional image of 224*224*3 size
Levy vector.
In one embodiment of the application, it is preferable that provide a kind of generation method of threedimensional model diagram generator, such as
Shown in Fig. 2, include the following steps:
S201 obtains the two dimensional sample image and three-dimensional samples image of sample entity；
Two dimensional sample image and three-dimensional samples image are separately input into initial threedimensional model diagram generator, to first by S202
Beginning threedimensional model diagram generator is trained, and obtains threedimensional model diagram generator.
In this embodiment, initial threedimensional model diagram generator is trained by transferring 3D model data collection, wherein
3D model data collection is preferably increased income data set (ShapeNet), which has included at least abundant different real in multiple types
The three-dimensional samples image and two dimensional sample image of body, and then these one-to-one three-dimensional samples images and two-dimentional sample can be passed through
This image is trained initial threedimensional model diagram generator, and the training effect to initial threedimensional model diagram generator is reached with this
Fruit with the threedimensional model diagram generator after being trained, and then can be realized the two dimensional image of target to be printed being input to this
Threedimensional model diagram generator after training directly generates the corresponding 3 D-printing illustraton of model of two dimensional image of target to be printed.
It should be noted that the embodiment of the present application is to realize from two dimensional image to generate printer model figure, condition is preferably chosen
Confrontation network (Conditional Generative Adversarial Networks, CGAN) is generated as initial three-dimensional mould
Type diagram generator, wherein generate confrontation network (Generative Adversarial Networks) relative to autocoder
There is the abundant fitting data of energy with unsupervised learnings methods such as autoregression models, fast speed generates the sharper keen advantage of sample,
The basic thought of GAN is derived from the zero-sum two-person game of game theory, including generates model and discrimination model composition, generates model and catches
The potential distribution of truthful data sample is caught, and generates new data sample, discrimination model can regard two classifiers as, differentiate defeated
What is entered is the sample of truthful data or generation.And CGAN is a kind of generation confrontation model of conditional constraint, it is generating mould
Conditional-variable is introduced in the modeling of type and discrimination model, conditional-variable can be label here, be also possible to from difference
The data of mode, the conditional-variable of the application are two dimensional image, using this additional conditional-variable, for generating model logarithm
According to generation have directive function, therefore, CGAN, which can also be regarded as, becomes to have one kind of monitor model to change unsupervised GAN
Into.
In one embodiment of the application, it is preferable that the generation method of another threedimensional model diagram generator is provided,
As shown in figure 3, including the following steps:
S301 obtains the two dimensional sample image and three-dimensional samples image of sample entity；
Two dimensional sample image is input to initial threedimensional model diagram generator, it is corresponding to obtain two dimensional sample image by S302
Three-dimensional generates image；
Three-dimensional is generated image three-dimensional samples image corresponding with two dimensional sample image and is compared, generated and compare by S303
As a result；
S304 adjusts the parameter of initial threedimensional model diagram generator according to comparison result, obtains threedimensional model diagram generator.
In this embodiment, 3D model data collection includes the three-dimensional samples image and two dimensional sample image of different entities, excellent
Select GAN network as initial threedimensional model diagram generator, wherein GAN network includes generating model and discrimination model, in general, raw
The distribution of sample data is captured at model, two dimensional sample image is input to generation model by the embodiment of the present application, to obtain two dimension
Three-dimensional is further generated image and three-dimensional samples image inputs discrimination model by the corresponding three-dimensional generation image of sample image
The middle judgement for carrying out true and false sample, wherein discrimination model is two classifiers, estimates a sample from training data
Otherwise the probability of (rather than generating data), exports small probability if sample exports maximum probability from true training data,
Herein, three-dimensional samples image is true training data, and it is the training data generated that three-dimensional, which generates image, further, is led to
The comparison result optimization for crossing discrimination model output generates model, makes the three-dimensional image that generates for generating model generation close to true sample
This, even if three-dimensional generates image close to three-dimensional samples image, further, according to comparison result, re-optimization discrimination model, to mention
The discriminating power of high discrimination model generates sample that model generates close to true sample in this way after successive ignition training,
Achieve the purpose that the initial threedimensional model diagram generator of training.
In one embodiment of the application, it is preferable that provide the generation method of another 3 D-printing illustraton of model, such as
Shown in Fig. 4, include the following steps:
S401 obtains the two dimensional image of target to be printed；
S402 carries out image characteristics extraction to two dimensional image, obtains the feature vector of two dimensional image；
Feature vector is converted to volume data using threedimensional model diagram generator, generates the voxel of target to be printed by S403
Change three-dimensional entity model figure；
Voxelization three-dimensional entity model figure is converted to gridding 3 D-printing illustraton of model, for three-dimensional printer by S404
The 3 D-printing model of target to be printed is printed based on gridding 3 D-printing illustraton of model.
In this embodiment, two dimensional image is input to threedimensional model diagram generator, output is voxelization 3D solid
Illustraton of model prints the 3 D-printing model of target to be printed for the ease of 3D printer, it is necessary to by voxelization 3D solid mould
Type figure is converted to gridding 3 D-printing illustraton of model.
It should be noted that voxel is the abbreviation of volume element (Volume Pixel), the solid comprising voxel can lead to
The polygon contour surface for crossing three-dimensional rendering or extraction given threshold value profile shows.It is that numerical data is divided in three-dimensional space
On minimum unit, minimum unit-pixel of conceptive similar two-dimensional space；Grid (Polygon mesh) is three-dimensional computations
The set on polyhedron-shaped vertex and polygon is indicated in machine graphics, it is also called unstrctured grid, these grids are usual
It is made of triangle, quadrangle or other simple convex polygons, can simplify render process in this way.
In one embodiment of the application, it is preferable that voxelization three-dimensional entity model figure is converted to gridding three-dimensional
Before printer model figure, further includes: carry out denoising to voxelization three-dimensional entity model figure, obtain the body after denoising
Elementization three-dimensional entity model figure.
In this embodiment, the model of generation is that the expression of voxelization needs to be converted in the limited situation of precision
For the model of gridding, for the model that needs are smoothed, may in model surface, there are some noises, this is just needed
Carry out denoising to voxelization three-dimensional entity model figure can be by going for model surface noise that may be present accordingly
Make an uproar algorithm or by online editing tool to model carry out denoising.
In one embodiment of the application, it is preferable that voxelization three-dimensional entity model figure is converted to gridding three-dimensional
Printer model figure, comprising: the voxelization three-dimensional entity model figure after denoising is converted to the 3 D-printing mould of gridding
Type figure.
In this embodiment, since the surface of the voxelization three-dimensional entity model of generation can have noise, i.e., some discrete
Point, therefore, in order to print the 3 D-printing model of smooth target to be printed, it is necessary to voxelization three-dimensional entity model figure
After being denoised, then convert it into the 3 D-printing illustraton of model of the gridding of suitable 3D printer printing.
Based on the same inventive concept, the life with 3 D-printing illustraton of model is additionally provided in the embodiment of the application second aspect
At the corresponding generating means of method, the principle and the embodiment of the present application solved the problems, such as due to the generating means in the embodiment of the present application
Above-mentioned generation method is similar, therefore the implementation of device may refer to the implementation of method, and overlaps will not be repeated.
The embodiment of the application second aspect provides a kind of generating means of 3 D-printing illustraton of model, as shown in figure 5,
The device includes:
Module 10 is obtained, for obtaining the two dimensional image of target to be printed；
Extraction module 20 obtains the feature vector of two dimensional image for carrying out image characteristics extraction to two dimensional image；
Generation module 30, the threedimensional model diagram generator for being obtained based on feature vector and preparatory training, generates two
Tie up the corresponding 3 D-printing illustraton of model of image.
In one embodiment of the application, it is preferable that obtain module 10, be also used to obtain the two dimensional sample of sample entity
Image and three-dimensional samples image；Generation module 30 is also used to for two dimensional sample image and three-dimensional samples image being separately input into just
Beginning threedimensional model diagram generator is trained initial threedimensional model diagram generator, obtains threedimensional model diagram generator.
In one embodiment of the application, it is preferable that generation module 30 is also used to:
Two dimensional sample image is input to initial threedimensional model diagram generator, it is corresponding three-dimensional raw to obtain two dimensional sample image
At image；
Three-dimensional is generated image three-dimensional samples image corresponding with two dimensional sample image to be compared, generates comparison result；
The parameter that initial threedimensional model diagram generator is adjusted according to comparison result, obtains threedimensional model diagram generator.
In one embodiment of the application, it is preferable that generation module 30 includes:
Generation module 30 is also used to: feature vector being converted to volume data using threedimensional model diagram generator, is generated wait beat
Print the voxelization three-dimensional entity model figure of target；
Conversion module, for voxelization three-dimensional entity model figure to be converted to gridding 3 D-printing illustraton of model, for three
Dimension printer prints the 3 D-printing model of target to be printed based on gridding 3 D-printing illustraton of model.
In one embodiment of the application, it is preferable that the generating means of 3 D-printing illustraton of model, further includes:
Processing module obtains the body after denoising for carrying out denoising to voxelization three-dimensional entity model figure
Elementization three-dimensional entity model figure.
In one embodiment of the application, it is preferable that conversion module is also used to the voxelization three after denoising
Dimension physical model figure is converted to the 3 D-printing illustraton of model of gridding.
The embodiment of the application third aspect, as shown in fig. 6, for a kind of electronic equipment provided by the embodiment of the present application
Structural schematic diagram, the electronic equipment include: processor 100, memory 200 and bus 300, and memory 200 is stored with processor
100 executable machine readable instructions pass through bus 300 when electronic equipment operation between processor 100 and memory 200
Communication executes the generation method of the 3 D-printing illustraton of model of any of the above-described when machine readable instructions are executed by processor 100
Step.
The embodiment of the application fourth aspect additionally provides a kind of computer readable storage medium, computer-readable storage
It is stored with computer program on medium, the 3 D-printing illustraton of model of any of the above-described is executed when computer program is run by processor
Generation method the step of.
Specifically, computer readable storage medium can be general storage medium, such as mobile disk, hard disk, this is deposited
When computer program on storage media is run, it is able to carry out the generation method of above-mentioned 3 D-printing illustraton of model.
The computer program product of 3 D-printing model map generalization, including storage are carried out provided by the embodiment of the present application
The computer readable storage medium of the executable non-volatile program code of processor, the instruction that said program code includes can
For executing previous methods method as described in the examples, specific implementation can be found in embodiment of the method, and details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can
To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for
The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of generation method of 3 D-printing illustraton of model characterized by comprising
Obtain the two dimensional image of target to be printed；
Image characteristics extraction is carried out to the two dimensional image, obtains the feature vector of the two dimensional image；
Obtained threedimensional model diagram generator is trained based on described eigenvector and in advance, it is corresponding to generate the two dimensional image
3 D-printing illustraton of model.
2. being generated the method according to claim 1, wherein generating the three-dimensional model diagram according to following steps
Device:
Obtain the two dimensional sample image and three-dimensional samples image of sample entity；
The two dimensional sample image and the three-dimensional samples image are separately input into initial threedimensional model diagram generator, to described
Initial threedimensional model diagram generator is trained, and obtains the threedimensional model diagram generator.
3. according to the method described in claim 2, it is characterized in that, described instruct the initial threedimensional model diagram generator
Practice, obtain the threedimensional model diagram generator, comprising:
The two dimensional sample image is input to the initial threedimensional model diagram generator, it is corresponding to obtain the two dimensional sample image
Three-dimensional generate image；
The three-dimensional image three-dimensional samples image corresponding with the two dimensional sample image that generates is compared, generates and compares knot
Fruit；
The parameter that the initial threedimensional model diagram generator is adjusted according to the comparison result obtains the three-dimensional model diagram and generates
Device.
4. the method according to claim 1, wherein described obtained based on described eigenvector and preparatory training
Threedimensional model diagram generator, generate the corresponding 3 D-printing illustraton of model of the two dimensional image, comprising:
Described eigenvector is converted into volume data using the threedimensional model diagram generator, generates the body of the target to be printed
Elementization three-dimensional entity model figure；
The voxelization three-dimensional entity model figure is converted to gridding 3 D-printing illustraton of model, so that three-dimensional printer is based on institute
State the 3 D-printing model that gridding 3 D-printing illustraton of model prints the target to be printed.
5. according to the method described in claim 4, it is characterized in that, described be converted to the voxelization three-dimensional entity model figure
Before gridding 3 D-printing illustraton of model, further includes:
Denoising is carried out to the voxelization three-dimensional entity model figure, obtains the voxelization 3D solid mould after denoising
Type figure.
6. according to the method described in claim 5, it is characterized in that, described be converted to the voxelization three-dimensional entity model figure
Gridding 3 D-printing illustraton of model, comprising:
Voxelization three-dimensional entity model figure after denoising is converted to the 3 D-printing illustraton of model of gridding.
7. a kind of generating means of 3 D-printing illustraton of model characterized by comprising
Module is obtained, for obtaining the two dimensional image of target to be printed；
Extraction module obtains the feature vector of the two dimensional image for carrying out image characteristics extraction to the two dimensional image；
Generation module, for based on the described eigenvector and in advance obtained threedimensional model diagram generator of training, described in generation
The corresponding 3 D-printing illustraton of model of two dimensional image.
8. device according to claim 7, which is characterized in that
The acquisition module is also used to obtain the two dimensional sample image and three-dimensional samples image of sample entity；
The generation module is also used to the two dimensional sample image and the three-dimensional samples image being separately input into initial three-dimensional
Model diagram generator is trained the initial threedimensional model diagram generator, obtains the threedimensional model diagram generator.
9. a kind of electronic equipment characterized by comprising processor, memory and bus, the memory are stored with the place
The executable machine readable instructions of device are managed, when electronic equipment operation, pass through bus between the processor and the memory
Communication executes the 3 D-printing as described in any in claim 1 to 6 when the machine readable instructions are executed by the processor
The step of generation method of illustraton of model.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer journey on the computer readable storage medium
Sequence executes when the computer program is run by processor such as 3 D-printing illustraton of model described in any one of claims 1 to 6
The step of generation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811267277.5A CN109049716A (en) | 2018-10-29 | 2018-10-29 | Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811267277.5A CN109049716A (en) | 2018-10-29 | 2018-10-29 | Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109049716A true CN109049716A (en) | 2018-12-21 |
Family
ID=64767603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811267277.5A Pending CN109049716A (en) | 2018-10-29 | 2018-10-29 | Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109049716A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297272A (en) * | 2019-07-05 | 2019-10-01 | 中南大学 | Three-dimensional velocity structure generation method, device, equipment and storage medium |
| CN110992476A (en) * | 2019-12-18 | 2020-04-10 | 深圳度影医疗科技有限公司 | 3D printing method of fetus three-dimensional ultrasonic image, storage medium and ultrasonic equipment |
| CN111243085A (en) * | 2020-01-20 | 2020-06-05 | 北京字节跳动网络技术有限公司 | Training method and device for image reconstruction network model and electronic equipment |
| WO2023061307A1 (en) * | 2021-10-11 | 2023-04-20 | 广州黑格智造信息科技有限公司 | Method and apparatus for preprocessing three-dimensional printing data, and digital operation platform |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930382A (en) * | 2016-04-14 | 2016-09-07 | 严进龙 | Method for searching for 3D model with 2D pictures |
| CN106096619A (en) * | 2016-06-21 | 2016-11-09 | 青岛译锁堂安全技术有限公司 | Based on artificial intelligence technology join spoon method and system |
-
2018
- 2018-10-29 CN CN201811267277.5A patent/CN109049716A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930382A (en) * | 2016-04-14 | 2016-09-07 | 严进龙 | Method for searching for 3D model with 2D pictures |
| CN106096619A (en) * | 2016-06-21 | 2016-11-09 | 青岛译锁堂安全技术有限公司 | Based on artificial intelligence technology join spoon method and system |
Non-Patent Citations (2)
| Title |
|---|
| 中国航天科工集团第三研究院三一〇所: "《自主系统与人工智能领域科技发展报告》", 30 April 2017, 国防工业出版社 * |
| 王天一: "《人工智能革命 历史、当下与未来》", 30 June 2017, 北京时代华文书局 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297272A (en) * | 2019-07-05 | 2019-10-01 | 中南大学 | Three-dimensional velocity structure generation method, device, equipment and storage medium |
| CN110992476A (en) * | 2019-12-18 | 2020-04-10 | 深圳度影医疗科技有限公司 | 3D printing method of fetus three-dimensional ultrasonic image, storage medium and ultrasonic equipment |
| CN110992476B (en) * | 2019-12-18 | 2021-07-13 | 深圳度影医疗科技有限公司 | 3D printing method of fetus three-dimensional ultrasonic image, storage medium and ultrasonic equipment |
| CN111243085A (en) * | 2020-01-20 | 2020-06-05 | 北京字节跳动网络技术有限公司 | Training method and device for image reconstruction network model and electronic equipment |
| CN111243085B (en) * | 2020-01-20 | 2021-06-22 | 北京字节跳动网络技术有限公司 | Training method and device for image reconstruction network model and electronic equipment |
| WO2023061307A1 (en) * | 2021-10-11 | 2023-04-20 | 广州黑格智造信息科技有限公司 | Method and apparatus for preprocessing three-dimensional printing data, and digital operation platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xu et al. | Point-nerf: Point-based neural radiance fields | |
| Richter et al. | Matryoshka networks: Predicting 3d geometry via nested shape layers | |
| Gadelha et al. | 3d shape induction from 2d views of multiple objects | |
| US10259164B2 (en) | Methods and apparatus for 3D printing of point cloud data | |
| CN109791697B (en) | Predicting depth from image data using statistical models | |
| Wang et al. | Hf-neus: Improved surface reconstruction using high-frequency details | |
| CN110674829B (en) | Three-dimensional target detection method based on graph convolution attention network | |
| Sun et al. | Swformer: Sparse window transformer for 3d object detection in point clouds | |
| CN109049716A (en) | Generation method, device, electronic equipment and the storage medium of 3 D-printing illustraton of model | |
| CN113538664B (en) | Vehicle de-illumination three-dimensional reconstruction method and device, electronic equipment and storage medium | |
| CN112396645B (en) | Monocular image depth estimation method and system based on convolution residual learning | |
| CN110288697A (en) | 3D face representation and method for reconstructing based on multiple dimensioned figure convolutional neural networks | |
| Sridhar et al. | Multiview aggregation for learning category-specific shape reconstruction | |
| CN113096234A (en) | Method and device for generating three-dimensional grid model by using multiple color pictures | |
| CN111739167B (en) | 3D human head reconstruction method, device, equipment and medium | |
| JP7129529B2 (en) | UV mapping to 3D objects using artificial intelligence | |
| CN113610172B (en) | Neural network model training method and device and sensing data fusion method and device | |
| CN108124489B (en) | Information processing method, apparatus, cloud processing device and computer program product | |
| Rios et al. | Scalability of learning tasks on 3D CAE models using point cloud autoencoders | |
| CN108986210B (en) | Method and device for reconstructing three-dimensional scene | |
| Huang et al. | ES-Net: An efficient stereo matching network | |
| Kania et al. | Hypernerfgan: Hypernetwork approach to 3d nerf gan | |
| Lin et al. | A-SATMVSNet: An attention-aware multi-view stereo matching network based on satellite imagery | |
| Bhardwaj et al. | SingleSketch2Mesh: generating 3D mesh model from sketch | |
| KR102012828B1 (en) | Apparatus and method for volume rendering |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181221 |