CN110415361A - It is broken object joining method and device - Google Patents
It is broken object joining method and device Download PDFInfo
- Publication number
- CN110415361A CN110415361A CN201910681901.4A CN201910681901A CN110415361A CN 110415361 A CN110415361 A CN 110415361A CN 201910681901 A CN201910681901 A CN 201910681901A CN 110415361 A CN110415361 A CN 110415361A
- Authority
- CN
- China
- Prior art keywords
- model
- moved
- point
- fragment
- optimal
- 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.)
- Granted
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2008—Assembling, disassembling
Abstract
The embodiment of the present invention provides a kind of fracture object joining method and device, wherein method includes: the two three dimensional fragment models for importing and being formed after target object fracture, and described two three dimensional fragment models are respectively fragment model and target debris model to be moved；By first obtaining the optimal R between the fragment model to be moved and target debris model, then obtain the optimal t between the fragment model to be moved and target debris model for spin matrix R and translation vector t decoupling；The optimal R and optimal t is used by the plane of disruption in the fragment model to be moved, the plane of disruption of the plane of disruption of the fragment model to be moved and the target debris model is spliced.The embodiment of the present invention can realize the automatic Mosaic of fracture object under three-dimensional virtual environment, can effectively improve splicing efficiency, and splicing accuracy is high.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of fracture object joining methods and device.
Background technique
After target object fracture, it will form two collapsed portions, the plane of disruption to two collapsed portions needed to spell
It connects, restores the style of target object.
Currently, traditional method spliced to fracture object is to complete work by manually mostly.People use
Visually observe the feature of the plane of disruption, thus it is speculated that the positional relationship of script between fragment is manually adjusted, fragment is pieced together one
It rises, sees whether they coincide.
Although traditional method comparison spliced to fracture object is intuitive, complicated splicing operation needs in this way
The personnel to be spliced have enough specialized capabilities and splicing experience abundant, and the personnel of splicing need to target object
Structure is very familiar to；Moreover, a large amount of time and efforts of splicing personnel can be expended by manually splicing to fracture object, spell
The accuracy connect is relatively low.
Summary of the invention
In view of the problems of the existing technology, the embodiment of the present invention provides a kind of fracture object joining method and device.
The embodiment of the present invention provides a kind of fracture object joining method, comprising:
Import two three dimensional fragment models being formed after target object fracture, described two three dimensional fragment models be respectively to
Mobile fragment model and target debris model；
By first obtaining the fragment model to be moved and target debris model for spin matrix R and translation vector t decoupling
Between optimal R, then obtain the optimal t between the fragment model to be moved and target debris model；
The optimal R and optimal t is used by the plane of disruption in the fragment model to be moved, it will be described to be moved
The plane of disruption of the plane of disruption of fragment model and the target debris model is spliced.
Optionally, it is described by by spin matrix R and translation vector t decoupling, first obtain the fragment model to be moved and
Optimal R between target debris model, comprising:
The plane of disruption for extracting target debris model respectively is formed by edge wheel profile EdgeAWith fragment model to be moved
The plane of disruption is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is N1, EdgeBPlace
The normal vector list for having tri patch is N2, EdgeAThe spatial position list that there is tri patch in place is P1, EdgeBPlace has three
The spatial position list of edged surface piece is P2, connects all the points forming curves C1 in P1, connects all the points forming curves in P2
C2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector column respectively
Table n1 and normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11i
With i-th of normal vector n in n22iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain between the fragment model to be moved and target debris model most
Excellent R；
Wherein, the preset relation are as follows:
Optionally, described by enabling n1 and n2 meet preset relation, obtain the fragment model to be moved and target debris
Optimal R between model, comprising:
Replace R to solve to the preset relation using quaternary number operation rule using quaternary number, obtain it is described to
Optimal R between mobile fragment model and target debris model.
Optionally, the optimal t obtained between the fragment model to be moved and target debris model again, comprising:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBPlace
The set of some points, calculates separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference
The intra-office point drawn game exterior point concept of stochastical sampling consistency algorithm, traverses and calculates V2' in all the points whether be intra-office point, packet
It includes: to V2' in s-th of point V2s', s=1 ..., m ', m ' are V2The quantity at ' midpoint calculates distance V2s' nearest V1In
Two o'clock h1And h2, calculate V2s′h1With V2s′h2Angle, if V2s′h1With V2s′h2Angle be more than or equal to preset threshold, then V2s′
For point not in the know, otherwise V2s' it is intra-office point；Calculate V2The ratio of ' middle intra-office point；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current not in the know
Point V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: most apart from each point not in the know
Close V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, described in return
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2The ratio of ' middle intra-office point
Example is less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s′
Nearest V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
The embodiment of the present invention provides a kind of fracture object splicing apparatus, comprising:
Import modul, for importing the two three dimensional fragment models formed after target object fracture, described two three-dimensionals are broken
Piece model is respectively fragment model and target debris model to be moved；
Module is obtained, for by first obtaining the fragment model to be moved for spin matrix R and translation vector t decoupling
Optimal R between target debris model, then obtain optimal between the fragment model to be moved and target debris model
T；
Splicing module, for using the optimal R and optimal by the plane of disruption in the fragment model to be moved
T splices the plane of disruption of the plane of disruption of the fragment model to be moved and the target debris model.
Optionally, it is described by by spin matrix R and translation vector t decoupling, first obtain the fragment model to be moved and
Optimal R between target debris model, comprising:
The plane of disruption for extracting target debris model respectively is formed by edge wheel profile EdgeAWith fragment model to be moved
The plane of disruption is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is N1, EdgeBPlace
The normal vector list for having tri patch is N2, EdgeAThe spatial position list that there is tri patch in place is P1, EdgeBPlace has three
The spatial position list of edged surface piece is P2, connects all the points forming curves C1 in P1, connects all the points forming curves in P2
C2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector column respectively
Table n1 and normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11i
With i-th of normal vector n in n22iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain between the fragment model to be moved and target debris model most
Excellent R；
Wherein, the preset relation are as follows:
Optionally, described by enabling n1 and n2 meet preset relation, obtain the fragment model to be moved and target debris
Optimal R between model, comprising:
Replace R to solve to the preset relation using quaternary number operation rule using quaternary number, obtain it is described to
Optimal R between mobile fragment model and target debris model.
Optionally, the optimal t obtained between the fragment model to be moved and target debris model again, comprising:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBPlace
The set of some points, calculates separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference
The intra-office point drawn game exterior point concept of stochastical sampling consistency algorithm, traverses and calculates V2Whether ' middle all the points are intra-office point, packet
It includes: to V2' in s-th of point V2s', s=1 ..., m ', m ' are V2The quantity at ' midpoint calculates distance V2s' nearest V1In
Two o'clock h1And h2, calculate V2s′h1With V2s′h2Angle, if V2s′h1With V2s′h2Angle be more than or equal to preset threshold, then V2s′
For point not in the know, otherwise V2s' it is intra-office point；Calculate V2The ratio of ' middle intra-office point；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current not in the know
Point V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: most apart from each point not in the know
Close V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, described in return
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2The ratio of ' middle intra-office point
Example is less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s′
Nearest V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
The embodiment of the present invention provides a kind of electronic equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor are realized when executing described program such as the step of the above method.
Fracture object joining method and device provided in an embodiment of the present invention pass through what is formed after importing target object fracture
Two three dimensional fragment models (fragment model and target debris model i.e. to be moved), by solving spin matrix R and translation vector t
Coupling first obtains the optimal R between fragment model and target debris model to be moved, then obtains fragment model to be moved and target
Optimal t between fragment model uses optimal R and optimal t by the plane of disruption in fragment model to be moved, will be wait move
The plane of disruption of dynamic fragment model and the plane of disruption of target debris model are spliced, and thereby, it is possible to real under three-dimensional virtual environment
It is now broken the automatic Mosaic of object, splicing efficiency can be effectively improved, splicing accuracy is high.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram for fracture object joining method that one embodiment of the invention provides；
Fig. 2 is a kind of structural schematic diagram for fracture object splicing apparatus that one embodiment of the invention provides；
Fig. 3 is the entity structure schematic diagram for the electronic equipment that one embodiment of the invention provides.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 shows a kind of flow diagram of fracture object joining method of one embodiment of the invention offer, such as Fig. 1 institute
Show, the fracture object joining method of the present embodiment, comprising:
S1, the two three dimensional fragment models formed after target object fracture, described two three dimensional fragment model difference are imported
For fragment model to be moved and target debris model.
It should be noted that the executing subject for being broken object joining method described in the present embodiment is processor.
It is understood that two fragments (fragment and target debris i.e. to be moved) can be formed after target object fracture,
In a particular application, the present embodiment can (Computed Tomography, electronics calculate by obtaining the CT of fragment to be moved
Machine tomoscan) data generate fragment model to be moved according to the CT data of fragment to be moved, and it is broken by obtaining target
The CT data of piece generate target debris model according to the CT data of target debris, and then in three-dimensional virtual environment described in importing
Fragment model to be moved and the target debris model.
S2, by by spin matrix R and translation vector t decoupling, first obtain the fragment model to be moved and target debris
Optimal R between model, then obtain the optimal t between the fragment model to be moved and target debris model.
It is understood that decoupling is that the math equation containing multiple variables is instigated to become that single variable can be used in mathematics
The equation group of expression, i.e. variable no longer while jointly directly affect an equation as a result, to Simplified analysis calculate；By suitable
When control amount selection, a multi-variable system turns to the mathematics of multiple independent single-variable systems by the means such as coordinate transform
The coupling between variable unless each of model, i.e. solution.
It is understood that the present embodiment is first to obtain institute by way of by spin matrix R and translation vector t decoupling
The optimal R between fragment model and target debris model to be moved is stated, then obtains the fragment model to be moved and target is broken
Optimal t between piece model uses the optimal R and optimal with the subsequent plane of disruption in the fragment model to be moved
T realizes the splicing of the plane of disruption to the plane of disruption and target debris model of the fragment model to be moved.
S3, the optimal R and optimal t is used by the plane of disruption in the fragment model to be moved, will it is described to
The plane of disruption of mobile fragment model and the plane of disruption of the target debris model are spliced.
It is understood that the plane of disruption in the fragment model to be moved uses the optimal spin matrix R and most
Excellent translation vector t can be realized the plane of disruption of the plane of disruption and the target debris model to the fragment model to be moved
Splicing.
It is understood that the present embodiment is (i.e. to be moved for two three dimensional fragment models under three-dimensional virtual environment
Fragment model and target debris model), by way of by spin matrix R and translation vector t decoupling, first obtain described to be moved
Optimal R between fragment model and target debris model, then obtain the fragment model to be moved and target debris model it
Between optimal t, then use the optimal R and optimal t in the plane of disruption of the fragment model to be moved, will it is described to
The plane of disruption of mobile fragment model and the plane of disruption of the target debris model are spliced, can be real under three-dimensional virtual environment
Now it is broken the automatic Mosaic of object.
Fracture object joining method provided in an embodiment of the present invention, by importing two three formed after target object fracture
It ties up fragment model (fragment model and target debris model i.e. to be moved), by decoupling spin matrix R and translation vector t, first
The optimal R between fragment model and target debris model to be moved is obtained, then obtains fragment model and target debris to be moved
Optimal t between model uses optimal R and optimal t by the plane of disruption in fragment model to be moved, will be to be moved broken
The plane of disruption of piece model and the plane of disruption of target debris model are spliced, disconnected thereby, it is possible to realize under three-dimensional virtual environment
The automatic Mosaic of object is split, splicing efficiency can be effectively improved, splicing accuracy is high.
Further, on the basis of the above embodiments, in the step S2 " by by spin matrix R and translation vector
T decoupling is measured, the optimal R " between the fragment model to be moved and target debris model is first obtained, may include:
The plane of disruption (the Surf of target debris model is extracted respectivelyA) it is formed by edge wheel profile EdgeAWith fragment to be moved
The plane of disruption (the Surf of modelB) it is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is
N1, EdgeBThe normal vector list that there is tri patch in place is N2, EdgeAThe spatial position list that there is tri patch in place is P1,
EdgeBThe spatial position list that there is tri patch in place is P2, connects all the points forming curves C1 in P1, connects the institute in P2
There is a forming curves C2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector column respectively
Table n1 and normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11i
With i-th of normal vector n in n22iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain between the fragment model to be moved and target debris model most
Excellent R；
Wherein, the preset relation are as follows:
It is understood that in EdgeACurved surface outside encirclement can be denoted asIn EdgeBCurved surface outside encirclement can be denoted asWithIt is exactly the original surface information of breaking part；If the fragment model to be moved and target are broken
After piece model splicing,WithContinuity is preferable, and SurfAAnd SurfBIt is non-intersecting, then illustrate to splice successfully.
For above-mentioned formula (1), it is to be understood that assuming that normal vector point set n2 using after optimal R, then n1 and
Corresponding normal vector angle will be minimum in n2, and since all normal vectors are all unit vectors, angle minimum is just represented pair
Answer normal vector dot product maximum.That is R be it is optimal when, to i-th of unit normal vector in n2 vector lists be multiplied by after 3 × 3 matrix R again with
I-th of unit normal vector dot product of n1 vector lists executes identical operation to all m group normal vectors, and sums, at this time and most
Greatly.Formula (1) gives the way of restraint of a global optimum, participates in calculating with the normal vector in all lists, avoids only making
With local triangle dough sheet normal information to fall into local optimum.
Although having found the constraint relationship formula that optimal R meets, it includes nine unknown numbers that R, which has altogether, it is desirable to directly
It is relatively difficult to solve R, it is therefore, further, described by enabling n1 and n2 meet preset relation, obtain the fragment mould to be moved
Optimal R between type and target debris model may include:
Replace R to solve to the preset relation using quaternary number operation rule using quaternary number, obtain it is described to
Optimal R between mobile fragment model and target debris model.
Specifically, above-mentioned formula (1) can be rewritten as to following formula (2):
Wherein,WithIndicate unit quaternion,It isConjugation.According to quaternary number operation rule, above-mentioned formula (2)
It can be written as formula (3):
Due to n1iWith n2iIt is all unit normal vector, if n1i=(x1i,y1i,z1i), n2i=(x2i,y2i,z2i), in formula (3)It is writeable are as follows:
In formula (3)It is writeable are as follows:
After formula (4) and formula (5) replacement formula (3), formula (6) can be obtained:
According to quaternary number algorithm, formula (6) can be rewritten as to formula (7):
According to linear algebra knowledge, as long asIt is maximum eigenvalue N character pair vector, then the value of formula (7) is maximum.It asks
The corresponding feature vector of maximum eigenvalue N outLater, 3 × 3 spin matrix R are finally found out as follows: by formula (1)
Middle Rn2iIt indicates are as follows:
Finally required optimal spin matrix isWherein, Q isCorresponding 4
× 4 matrixes:
Wherein,
In this way, the present embodiment can obtain the optimal rotation between the fragment model to be moved and target debris model
Matrix R.
Further, on the basis of the above embodiments, " the fragment model to be moved is obtained again in the step S2
Optimal t " between target debris model may include:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBPlace
The set of some points, calculates separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference
The intra-office point drawn game exterior point concept of stochastical sampling consistency algorithm, traverses and calculates V2Whether ' middle all the points are intra-office point, packet
It includes: to V2' in s-th of point V2s', s=1 ..., m ', m ' are V2The quantity at ' midpoint calculates distance V2s' nearest V1In
Two o'clock h1And h2, calculate V2s′h1With V2s′h2Angle, if V2s′h1With V2s′h2Angle be more than or equal to preset threshold, then V2s′
For point not in the know, otherwise V2s' it is intra-office point；Calculate V2The ratio of ' middle intra-office point；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current not in the know
Point V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: most apart from each point not in the know
Close V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, described in return
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2The ratio of ' middle intra-office point
Example is less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s′
Nearest V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
In this way, the present embodiment can obtain the optimal translation between the fragment model to be moved and target debris model
Vector t.
Fracture object joining method provided in an embodiment of the present invention can realize fracture object under three-dimensional virtual environment
Automatic Mosaic, can effectively improve splicing efficiency, and splicing accuracy is high.
Fig. 2 shows a kind of structural schematic diagrams for fracture object splicing apparatus that one embodiment of the invention provides, such as Fig. 2 institute
Show, the present embodiment is broken object splicing apparatus, comprising: import modul 21 obtains module 22 and splicing module 23；Wherein:
The import modul 21, it is described two for importing the two three dimensional fragment models formed after target object fracture
Three dimensional fragment model is respectively fragment model and target debris model to be moved；
The acquisition module 22, for by first obtaining spin matrix R and translation vector t decoupling described to be moved broken
Optimal R between piece model and target debris model, then obtain between the fragment model to be moved and target debris model
Optimal t；
The splicing module 23, for by the plane of disruption in the fragment model to be moved using the optimal R and
Optimal t splices the plane of disruption of the plane of disruption of the fragment model to be moved and the target debris model.
Specifically, the two three dimensional fragment models formed after the importing of the import modul 21 target object fracture, described two
A three dimensional fragment model is respectively fragment model and target debris model to be moved；The acquisition module 22 is by by spin matrix
R and translation vector t decoupling, first obtains the optimal R between the fragment model to be moved and target debris model, then obtain institute
State the optimal t between fragment model and target debris model to be moved；The splicing module 23 passes through described to be moved broken
The plane of disruption of piece model uses the optimal R and optimal t, by the plane of disruption of the fragment model to be moved and the target
The plane of disruption of fragment model is spliced.
It should be noted that fracture object splicing apparatus described in the present embodiment is applied to processor.
It is understood that two fragments (fragment and target debris i.e. to be moved) can be formed after target object fracture,
In a particular application, the import modul 21 can be by the CT data of acquisition fragment to be moved, according to the CT of fragment to be moved
Data generate fragment model to be moved, and the CT data by obtaining target debris, raw according to the CT data of target debris
At target debris model, and then the fragment model to be moved and the target debris model are imported in three-dimensional virtual environment.
It is understood that decoupling is that the math equation containing multiple variables is instigated to become that single variable can be used in mathematics
The equation group of expression, i.e. variable no longer while jointly directly affect an equation as a result, to Simplified analysis calculate；By suitable
When control amount selection, a multi-variable system turns to the mathematics of multiple independent single-variable systems by the means such as coordinate transform
The coupling between variable unless each of model, i.e. solution.
It is understood that the acquisition module 22 is by way of by spin matrix R and translation vector t decoupling, first
Obtain the optimal R between the fragment model to be moved and target debris model, then obtain the fragment model to be moved and
Optimal t between target debris model, with the subsequent plane of disruption in the fragment model to be moved using the optimal R and
Optimal t realizes the splicing of the plane of disruption to the plane of disruption and target debris model of the fragment model to be moved.
It is understood that the splicing module 23 the fragment model to be moved the plane of disruption using described optimal
Spin matrix R and optimal translation vector t can be realized the plane of disruption and the target debris to the fragment model to be moved
The splicing of the plane of disruption of model.
It is understood that the present embodiment is (i.e. to be moved for two three dimensional fragment models under three-dimensional virtual environment
Fragment model and target debris model), by way of by spin matrix R and translation vector t decoupling, first obtain described to be moved
Optimal R between fragment model and target debris model, then obtain the fragment model to be moved and target debris model it
Between optimal t, then use the optimal R and optimal t in the plane of disruption of the fragment model to be moved, will it is described to
The plane of disruption of mobile fragment model and the plane of disruption of the target debris model are spliced, can be real under three-dimensional virtual environment
Now it is broken the automatic Mosaic of object.
Fracture object splicing apparatus provided in an embodiment of the present invention can realize fracture object under three-dimensional virtual environment
Automatic Mosaic, can effectively improve splicing efficiency, and splicing accuracy is high.
Further, on the basis of the above embodiments, it is described obtain in module 22 " by by spin matrix R peace
Vector t decoupling is moved, the optimal R " between the fragment model to be moved and target debris model is first obtained, may include:
The plane of disruption for extracting target debris model respectively is formed by edge wheel profile EdgeAWith fragment model to be moved
The plane of disruption is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is N1, EdgeBPlace
The normal vector list for having tri patch is N2, EdgeAThe spatial position list that there is tri patch in place is P1, EdgeBPlace has three
The spatial position list of edged surface piece is P2, connects all the points forming curves C1 in P1, connects all the points forming curves in P2
C2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector column respectively
Table n1 and normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11i
With i-th of normal vector n in n22iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain between the fragment model to be moved and target debris model most
Excellent R；
Wherein, the preset relation are as follows:
It is understood that in EdgeACurved surface outside encirclement can be denoted asIn EdgeBCurved surface outside encirclement can be denoted as WithIt is exactly the original surface information of breaking part；If the fragment model to be moved and target debris
After model splicing,WithContinuity is preferable, and SurfAAnd SurfBIt is non-intersecting, then illustrate to splice successfully.
For above-mentioned formula (1), it is to be understood that assuming that normal vector point set n2 using after optimal R, then n1 and
Corresponding normal vector angle will be minimum in n2, and since all normal vectors are all unit vectors, angle minimum is just represented pair
Answer normal vector dot product maximum.That is R be it is optimal when, to i-th of unit normal vector in n2 vector lists be multiplied by after 3 × 3 matrix R again with
I-th of unit normal vector dot product of n1 vector lists executes identical operation to all m group normal vectors, and sums, at this time and most
Greatly.Formula (1) gives the way of restraint of a global optimum, participates in calculating with the normal vector in all lists, avoids only making
With local triangle dough sheet normal information to fall into local optimum.
Although having found the constraint relationship formula that optimal R meets, it includes nine unknown numbers that R, which has altogether, it is desirable to directly
It is relatively difficult to solve R, it is therefore, further, described by enabling n1 and n2 meet preset relation, obtain the fragment mould to be moved
Optimal R between type and target debris model may include:
Replace R to solve to the preset relation using quaternary number operation rule using quaternary number, obtain it is described to
Optimal R between mobile fragment model and target debris model.
Specifically, above-mentioned formula (1) can be rewritten as to following formula (2):
Wherein,WithIndicate unit quaternion,It isConjugation.According to quaternary number operation rule, above-mentioned formula (2)
It can be written as formula (3):
Due to n1iWith n2iIt is all unit normal vector, if n1i=(x1i,y1i,z1i), n2i=(x2i,y2i,z2i), in formula (3)It is writeable are as follows:
In formula (3)It is writeable are as follows:
After formula (4) and formula (5) replacement formula (3), formula (6) can be obtained:
According to quaternary number algorithm, formula (6) can be rewritten as to formula (7):
According to linear algebra knowledge, as long asIt is maximum eigenvalue N character pair vector, then the value of formula (7) is maximum.It asks
The corresponding feature vector of maximum eigenvalue N outLater, 3 × 3 spin matrix R are finally found out as follows: by formula (1)
Middle Rn2iIt indicates are as follows:
Finally required optimal spin matrix isWherein, Q isCorresponding 4
× 4 matrixes:
Wherein,
In this way, the present embodiment can obtain the optimal rotation between the fragment model to be moved and target debris model
Matrix R.
Further, on the basis of the above embodiments, described obtain in module 22 " obtains the fragment to be moved again
Optimal t " between model and target debris model may include:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBPlace
The set of some points, calculates separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference
The intra-office point drawn game exterior point concept of stochastical sampling consistency algorithm, traverses and calculates V2' in all the points whether be intra-office point, packet
It includes: to V2' in s-th of point V2s', s=1 ..., m ', m ' are V2The quantity at ' midpoint calculates distance V2s' nearest V1In
Two o'clock h1And h2, calculate V2s′h1With V2s′h2Angle, if V2s′h1With V2s′h2Angle be more than or equal to preset threshold, then V2s′
For point not in the know, otherwise V2s' it is intra-office point；Calculate V2' in intra-office point ratio；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current not in the know
Point V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: most apart from each point not in the know
Close V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, described in return
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2The ratio of ' middle intra-office point
Example is less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s′
Nearest V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
In this way, the present embodiment can obtain the optimal translation between the fragment model to be moved and target debris model
Vector t.
Fracture object splicing apparatus provided in an embodiment of the present invention can realize fracture object under three-dimensional virtual environment
Automatic Mosaic, can effectively improve splicing efficiency, and splicing accuracy is high.
Fracture object splicing apparatus provided in an embodiment of the present invention, can be used for executing the technical side of preceding method embodiment
Case, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 3 shows the entity structure schematic diagram of a kind of electronic equipment of one embodiment of the invention offer, as shown in figure 3,
The electronic equipment may include memory 302, processor 301 and be stored on memory 302 and can run on processor 301
Computer program, the step of processor 301 realizes the above method when executing described program, for example, import target
The two three dimensional fragment models formed after object fracture, described two three dimensional fragment models are respectively fragment model and mesh to be moved
Mark fragment model；By first obtaining the fragment model to be moved and target debris for spin matrix R and translation vector t decoupling
Optimal R between model, then obtain the optimal t between the fragment model to be moved and target debris model；By
The plane of disruption of the fragment model to be moved uses the optimal R and optimal t, by the fracture of the fragment model to be moved
The plane of disruption of face and the target debris model is spliced.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, is stored thereon with computer program, should
The step of above method is realized when computer program is executed by processor, for example, formed after importing target object fracture
Two three dimensional fragment models, described two three dimensional fragment models are respectively fragment model and target debris model to be moved；Pass through
Spin matrix R and translation vector t is decoupled, is first obtained optimal between the fragment model to be moved and target debris model
R, then obtain the optimal t between the fragment model to be moved and target debris model；By in the fragment mould to be moved
The plane of disruption of type uses the optimal R and optimal t, by the plane of disruption and the target debris of the fragment model to be moved
The plane of disruption of model is spliced.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of fracture object joining method characterized by comprising
The two three dimensional fragment models formed after target object fracture are imported, described two three dimensional fragment models are respectively to be moved
Fragment model and target debris model；
By first obtaining spin matrix R and translation vector t decoupling between the fragment model to be moved and target debris model
Optimal R, then obtain the optimal t between the fragment model to be moved and target debris model；
The optimal R and optimal t is used by the plane of disruption in the fragment model to be moved, by the fragment to be moved
The plane of disruption of the plane of disruption of model and the target debris model is spliced.
2. fracture object joining method according to claim 1, which is characterized in that described by the way that spin matrix R is peaceful
Vector t decoupling is moved, the optimal R between the fragment model to be moved and target debris model is first obtained, comprising:
The plane of disruption for extracting target debris model respectively is formed by edge wheel profile EdgeAWith the fracture of fragment model to be moved
Face is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is N1, EdgeBPlace has three
The normal vector list of edged surface piece is N2, EdgeAThe spatial position list that there is tri patch in place is P1, EdgeBThere is triangular facet in place
The spatial position list of piece is P2, connects all the points forming curves C1 in P1, connects all the points forming curves C2 in P2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector list n1 respectively
With normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11iWith n2
In i-th of normal vector n2iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain optimal between the fragment model to be moved and target debris model
R；
Wherein, the preset relation are as follows:
3. fracture object joining method according to claim 2, which is characterized in that described default by enabling n1 and n2 meet
Relationship obtains the optimal R between the fragment model to be moved and target debris model, comprising:
It replaces R to solve using quaternary number operation rule to the preset relation using quaternary number, obtains described to be moved
Optimal R between fragment model and target debris model.
4. fracture object joining method according to claim 2, which is characterized in that described to obtain the fragment to be moved again
Optimal t between model and target debris model, comprising:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBThe point that place has
Set, calculate separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference is random
The intra-office point drawn game exterior point concept for sampling consistency algorithm, traverses and calculates V2' in all the points whether be intra-office point, comprising:
To V2' in s-th of point V2s', s=1 ..., m', m' V2' midpoint quantity, calculate distance V2s' nearest V1In two o'clock
h1And h2, calculate V2s'h1With V2s'h2Angle, if V2s'h1With V2s'h2Angle be more than or equal to preset threshold, then V2s' it is office
Exterior point, otherwise V2s' it is intra-office point；Calculate V2' in intra-office point ratio；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current point not in the know
V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: nearest apart from each point not in the know
V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, return described
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2' in intra-office point ratio
Less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' most
Close V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
5. a kind of fracture object splicing apparatus characterized by comprising
Import modul, for importing the two three dimensional fragment models formed after target object fracture, described two three dimensional fragment moulds
Type is respectively fragment model and target debris model to be moved；
Module is obtained, for by first obtaining the fragment model to be moved and mesh for spin matrix R and translation vector t decoupling
The optimal R between fragment model is marked, then obtains the optimal t between the fragment model to be moved and target debris model；
Splicing module will for using the optimal R and optimal t by the plane of disruption in the fragment model to be moved
The plane of disruption of the fragment model to be moved and the plane of disruption of the target debris model are spliced.
6. fracture object splicing apparatus according to claim 5, which is characterized in that described by the way that spin matrix R is peaceful
Vector t decoupling is moved, the optimal R between the fragment model to be moved and target debris model is first obtained, comprising:
The plane of disruption for extracting target debris model respectively is formed by edge wheel profile EdgeAWith the fracture of fragment model to be moved
Face is formed by edge wheel profile EdgeBIf EdgeAThe normal vector list that there is tri patch in place is N1, EdgeBPlace has three
The normal vector list of edged surface piece is N2, EdgeAThe spatial position list that there is tri patch in place is P1, EdgeBThere is triangular facet in place
The spatial position list of piece is P2, connects all the points forming curves C1 in P1, connects all the points forming curves C2 in P2；
Compare the similitude of C1 and C2, to filter out the correspondence normal vector pair in N1 and N2, is denoted as normal vector list n1 respectively
With normal vector list n2, wherein include m normal vector in n1 and n2, m is positive integer, i-th of normal vector n in n11iWith n2
In i-th of normal vector n2iIt is corresponding, i=1 ..., m；
By enabling n1 and n2 meet preset relation, obtain optimal between the fragment model to be moved and target debris model
R；
Wherein, the preset relation are as follows:
7. fracture object splicing apparatus according to claim 6, which is characterized in that described default by enabling n1 and n2 meet
Relationship obtains the optimal R between the fragment model to be moved and target debris model, comprising:
It replaces R to solve using quaternary number operation rule to the preset relation using quaternary number, obtains described to be moved
Optimal R between fragment model and target debris model.
8. fracture object splicing apparatus according to claim 6, which is characterized in that described to obtain the fragment to be moved again
Optimal t between model and target debris model, comprising:
If V1It is the Edge of target debris modelAThe set for the point that place has, V2It is the Edge of target debris modelBThe point that place has
Set, calculate separately V1Center of gravityAnd V2Center of gravityObtain a preliminary translational movement
It is translated according to the plane of disruption of the current translational movement t to the fragment model to be moved, remembers V2Become V2', reference is random
The intra-office point drawn game exterior point concept for sampling consistency algorithm, traverses and calculates V2Whether ' middle all the points are intra-office point, comprising:
To V2' in s-th of point V2s', s=1 ..., m', m' V2' midpoint quantity, calculate distance V2s' nearest V1In two o'clock
h1And h2, calculate V2s'h1With V2s'h2Angle, if V2s'h1With V2s'h2Angle be more than or equal to preset threshold, then V2s' it is office
Exterior point, otherwise V2s' it is intra-office point；Calculate V2' in intra-office point ratio；
If V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' nearest V1In two o'clock h1And h2To current point not in the know
V2s' distance average value, it is assumed that have m2A point not in the know then updates current translational movement t are as follows: nearest apart from each point not in the know
V1In two o'clock h1And h2To the distance of the point not in the know average value summation divided by point not in the know quantity, return described
The step of being translated according to the plane of disruption of the current translational movement t to the fragment model to be moved；If V2' in intra-office point ratio
Less than preset ratio, then iteration terminates, if otherwise returning to the V2s' it is point not in the know, then calculate the current point V not in the know of distance2s' most
Close V1In two o'clock h1And h2To current point V not in the know2s' distance average value the step of.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized when executing described program such as any one of Claims 1-4 the method
Step.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer
It is realized when program is executed by processor such as the step of any one of Claims 1-4 the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910681901.4A CN110415361B (en) | 2019-07-26 | 2019-07-26 | Method and device for splicing broken objects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910681901.4A CN110415361B (en) | 2019-07-26 | 2019-07-26 | Method and device for splicing broken objects |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110415361A true CN110415361A (en) | 2019-11-05 |
| CN110415361B CN110415361B (en) | 2020-05-15 |
Family
ID=68363457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910681901.4A Active CN110415361B (en) | 2019-07-26 | 2019-07-26 | Method and device for splicing broken objects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415361B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884653A (en) * | 2021-03-01 | 2021-06-01 | 西北大学 | Broken terracotta warriors fragment splicing method and system based on fracture surface information |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955939A (en) * | 2014-05-16 | 2014-07-30 | 重庆理工大学 | Boundary feature point registering method for point cloud splicing in three-dimensional scanning system |
| CN104299211A (en) * | 2014-09-25 | 2015-01-21 | 周翔 | Free-moving type three-dimensional scanning method |
| CN104915993A (en) * | 2015-06-29 | 2015-09-16 | 北京东方艾迪普科技发展有限公司 | Three-dimensional stretching modeling method and device |
| CN105869149A (en) * | 2016-03-24 | 2016-08-17 | 大连理工大学 | Principal vector analysis based broken bone section segmentation and broken bone model registration method |
| US9589182B2 (en) * | 2013-10-08 | 2017-03-07 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating orientation of body, and computer readable storage medium of recording the method |
| CN108154525A (en) * | 2017-11-21 | 2018-06-12 | 四川大学 | A kind of matched bone fragments joining method of feature based |
| CN108257163A (en) * | 2017-12-08 | 2018-07-06 | 西安电子科技大学 | A kind of 2 point cloud registration methods under known scanning element position |
| CN108961429A (en) * | 2018-06-08 | 2018-12-07 | 大连理工大学 | A kind of cultural relic fragments model divides automatically and joining method |
| CN109242774A (en) * | 2018-08-29 | 2019-01-18 | 浙江大学 | A kind of flat-type part point cloud method based on hyperspace invariant features |
| US10258412B2 (en) * | 2014-02-07 | 2019-04-16 | Episurf Ip-Management Ab | Method and node for manufacturing a surgical kit for cartilage repair |
-
2019
- 2019-07-26 CN CN201910681901.4A patent/CN110415361B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9589182B2 (en) * | 2013-10-08 | 2017-03-07 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating orientation of body, and computer readable storage medium of recording the method |
| US10258412B2 (en) * | 2014-02-07 | 2019-04-16 | Episurf Ip-Management Ab | Method and node for manufacturing a surgical kit for cartilage repair |
| CN103955939A (en) * | 2014-05-16 | 2014-07-30 | 重庆理工大学 | Boundary feature point registering method for point cloud splicing in three-dimensional scanning system |
| CN104299211A (en) * | 2014-09-25 | 2015-01-21 | 周翔 | Free-moving type three-dimensional scanning method |
| CN104915993A (en) * | 2015-06-29 | 2015-09-16 | 北京东方艾迪普科技发展有限公司 | Three-dimensional stretching modeling method and device |
| CN105869149A (en) * | 2016-03-24 | 2016-08-17 | 大连理工大学 | Principal vector analysis based broken bone section segmentation and broken bone model registration method |
| CN108154525A (en) * | 2017-11-21 | 2018-06-12 | 四川大学 | A kind of matched bone fragments joining method of feature based |
| CN108257163A (en) * | 2017-12-08 | 2018-07-06 | 西安电子科技大学 | A kind of 2 point cloud registration methods under known scanning element position |
| CN108961429A (en) * | 2018-06-08 | 2018-12-07 | 大连理工大学 | A kind of cultural relic fragments model divides automatically and joining method |
| CN109242774A (en) * | 2018-08-29 | 2019-01-18 | 浙江大学 | A kind of flat-type part point cloud method based on hyperspace invariant features |
Non-Patent Citations (5)
| Title |
|---|
| CONSTANTIN P.等: "Efficient solution to the 3D problem of automatic wall paintings reassembly", 《COMPUTERS AND MATHEMATICS WITH APPLICATIONS》 * |
| MOUNA A.等: "Efficient Initial Guess Determination Based on 3D Point Cloud Projection for ICP Algorithms", 《2017 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS)》 * |
| 刘伟: "散乱点云数据的拼接技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 方黎勇 等: "面向ICT切片图像复杂轮廓数据的三角网格拼接", 《机械设计与制造》 * |
| 李群辉 等: "以轮廓曲线为特征的断裂面匹配", 《西安交通大学学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884653A (en) * | 2021-03-01 | 2021-06-01 | 西北大学 | Broken terracotta warriors fragment splicing method and system based on fracture surface information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110415361B (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816769A (en) | Scene based on depth camera ground drawing generating method, device and equipment | |
| CN106846497B (en) | Method and device for presenting three-dimensional map applied to terminal | |
| CN109754417A (en) | The System and method for of unsupervised learning geometry from image | |
| CN104933755A (en) | Static object reconstruction method and system | |
| CN105229703A (en) | For the system and method using the position data of sensing to carry out generating three-dimensional models | |
| US20220343603A1 (en) | Three-dimensional reconstruction method, three-dimensional reconstruction apparatus, device and storage medium | |
| CN108876893A (en) | Method, apparatus, system and the computer storage medium of three-dimensional facial reconstruction | |
| EP3876204A2 (en) | Method and apparatus for generating human body three-dimensional model, device and storage medium | |
| CN110443222A (en) | Method and apparatus for training face's critical point detection model | |
| CN110211223A (en) | A kind of increment type multiview three-dimensional method for reconstructing | |
| CN109754464B (en) | Method and apparatus for generating information | |
| CN110889901B (en) | Large-scene sparse point cloud BA optimization method based on distributed system | |
| CN109979013A (en) | Three-dimensional face chart pasting method and terminal device | |
| CN115018992B (en) | Method and device for generating hair style model, electronic equipment and storage medium | |
| CN110245671A (en) | A kind of endoscopic images characteristic point matching method and system | |
| CN115131476A (en) | Bone binding migration method, device, equipment and storage medium of virtual object | |
| CN114677572B (en) | Object description parameter generation method and deep learning model training method | |
| CN113936090A (en) | Three-dimensional human body reconstruction method and device, electronic equipment and storage medium | |
| KR102488517B1 (en) | A method, a device, an electronic equipment and a storage medium for changing hairstyle | |
| CN110415361A (en) | It is broken object joining method and device | |
| CN109697748A (en) | Model compression processing method, model pinup picture processing method device, storage medium | |
| EP4086853A2 (en) | Method and apparatus for generating object model, electronic device and storage medium | |
| CN109816791B (en) | Method and apparatus for generating information | |
| CN115239892B (en) | Method, device and equipment for constructing three-dimensional blood vessel model and storage medium | |
| CN115965736A (en) | Image processing method, device, equipment and storage medium |
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 |