CN105243137B - A kind of three-dimensional model search viewpoint selection method based on sketch - Google Patents
A kind of three-dimensional model search viewpoint selection method based on sketch Download PDFInfo
- Publication number
- CN105243137B CN105243137B CN201510645547.1A CN201510645547A CN105243137B CN 105243137 B CN105243137 B CN 105243137B CN 201510645547 A CN201510645547 A CN 201510645547A CN 105243137 B CN105243137 B CN 105243137B
- Authority
- CN
- China
- Prior art keywords
- viewpoint
- model
- point
- vertex
- coordinate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Library & Information Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Image Generation (AREA)
- Processing Or Creating Images (AREA)
Abstract
The three-dimensional model search viewpoint selection method based on sketch that the invention discloses a kind of, comprising the following steps: step 1 manually classifies to the model in database；Step 2 determines the complete or collected works of viewpoint by carrying out triangle subdivision to regular dodecahedron；Step 3 calculates each model in the entropy of each viewpoint；Step 4, the number of views that every model I is determined by the calculated result of step 3；Step 5 carries out cluster operation to viewpoint complete or collected works by the calculated result of step 4, determines selected viewpoint；Step 6 generates two-dimensional projection views according to the viewpoint that step 5 generates.The present invention has many advantages, such as that matching result is good, effectively increases the operational efficiency of system.
Description
Technical field
The present invention relates to the three-dimensional model search technologies based on sketch in a kind of calculation machine field of image processing, in particular to
A kind of three-dimensional model search viewpoint selection method based on sketch, the view being mainly used in the three-dimensional model search based on sketch
Point selection.
Background technique
Currently, mainly there are two sides for the strategy of viewpoint selection in the three-dimensional model search viewpoint selection field based on sketch
Method.One is general viewpoint using presetting fixed view as all models.Shao et al. " is passing through healthy and strong model
With carrying out the distinguishing three-dimensional model search based on sketch " in propose: threedimensional model is carried out based on 7 fixed views
The method matched.The advantages of this method, is obvious, and no matter this is a spherical model or an individual model, can all use and predefine
Viewpoint matched, during matched, it is possible to reduce calculation amount in terms of viewpoint selection helps to improve and is
The operational efficiency of system.But its disadvantage is it is also obvious that have ignored different models to the different demands of number of views and viewpoint position, no
It is that each viewpoint can be well reflected the aspect of model, fixed view can influence matching result to a certain extent.
And another viewpoint selection strategy is then, and the matching of sketch is carried out by the viewpoint of viewpoint cluster generation.At present
Research work based on the strategy is seldom.
Summary of the invention
The purpose of the present invention is to overcome the shortcomings of the existing technology and deficiency, provides a kind of threedimensional model inspection based on sketch
Rope viewpoint selection method, the three-dimensional model search viewpoint selection method solve presetting fixed view and cause shadow to matching result
Loud problem carries out the selection of viewpoint using the method for cluster viewpoint.
The purpose of the invention is achieved by the following technical solution: a kind of three-dimensional model search viewpoint selection side based on sketch
Method, comprising the following steps:
Step 1 manually classifies to the model in database；
Step 2 determines the complete or collected works of viewpoint by carrying out triangle subdivision to regular dodecahedron；
Step 3 calculates each model in the entropy of each viewpoint；
Step 4, the number of views that every model I is determined by the calculated result of step 3；
Step 5 carries out cluster operation to viewpoint complete or collected works by the calculated result of step 4, determines selected viewpoint；
Step 6 generates two-dimensional projection views according to the viewpoint that step 5 generates.
The present invention has the following advantages and effects with respect to the prior art:
1, the present invention is then each in every model I by calculating by the way that the model in model database is classified
The complexity of a model determines number of views, determines the viewpoint of final choice finally by the method for cluster.Root of the present invention
According to different models to the different demands of number of views and viewpoint position, make each viewpoint that can be well reflected the aspect of model,
To secure viewpoint, matching result is good, effectively increases the operational efficiency of system.
2, it in existing three-dimensional model search field viewpoint selection part, there is no to the viewpoint based on cluster viewpoint
The research of selection, the present invention use the viewpoint selection method based on cluster viewpoint, have filled up this respect technological gap.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Fig. 2 is Loop subdivision algorithm analysis chart of the invention.
Specific embodiment
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment
As shown in Figure 1, a kind of three-dimensional model search viewpoint selection method based on sketch, comprising the following steps:
Step 1 manually classifies to the model in database；
Step 2 determines the complete or collected works of viewpoint by carrying out triangle subdivision to regular dodecahedron.
Step 2 specifically includes the following steps:
Step 2-1, it is positive the centre of sphere of icosahedral circumsphere with the origin of three-dimensional cartesian coordinate system, radius is 2 to draw
One regular dodecahedron；
Step 2-2, the subdivision in face is realized by the way that 1 gore is split into 4 small gores.
According to the different modes generated, the point generated after subdivision can be divided into two classes:
(1) first kind point: the point being calculated by the side of original triangle, such as Vq, Vp and Vr point in Fig. 2；
(2) second class points: the point being calculated by original vertex of a triangle, such as the V in Fig. 21’、V2' and V3' point；
For above first kind point and the second class point these two types point, whether it is boundary according to its affiliated side, is divided into two kinds
Situation calculates the coordinate of newly-generated point:
For first kind point:
(1) if the side of former triangle is boundary edge, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V1、V2Respectively two vertex of boundary edge.By formula (1), it is known that,
(2) if the non-boundary edge in side of former triangle, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V2、V3It is two vertex of the non-boundary edge, V1、V4Be with the two vertex all intersect on the non-boundary
While two sides and in this while nearest two vertex.By formula (2), it is known that:
For the second class point:
(1) if the side of former triangle is boundary edge, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V1It is corresponding vertex, V in original triangle shape2、V3It is two tops that V1 is adjacent in original triangle shape respectively
Point.By formula (3), it is known that:
If the non-boundary edge in side of former triangle, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein,
As n=3,As n > 3,ViIt represents in the former polygon for thering is a line to be connected with V
Vertex.From formula (4) and (5):
Step 3 calculates each model in the entropy of each viewpoint.Step 3 specifically includes the following steps:
Step 3-1: model x is in viewpoint pjThe calculation formula of the entropy at place is as follows:
Wherein, E indicates that entropy of the model at the viewpoint, m indicate the quantity in the face of the model, AiIndicate i-th of face
Effective area under the viewpoint, S indicate the gross area in the model rendering region (due to by the scaling of model to unit ball
It is interior, therefore S can be indicated on an equal basis with the area of unit circle)；A0Indicate that the area of background parts, i.e. rendering region gross area S subtract
Remove the gross area of the model projection on the face, as A0.The value of E is bigger, indicates that the complexity of the model is also bigger, general next
It says, the viewpoint number needed also can be more.
Step 3-2:A (x-x0)+B(y-y0)+C(z-z0)=0, (9)
Wherein, A, B, C are respectively equal to xn、yn、zn, i.e. the three-dimensional coordinate of the normal vector of the plane, x0, y0,z0It indicates at this
The coordinate of some known point in plane, the plane equation can be used to indicate the plane equation on perspective plane.
For each vertex v of modeli(xi,yi,zi), the point can be calculated and normal vector and viewpoint normal vector phase
Same linear equation.Due to being general perspective, thus vertex and its can be considered as in the normal vector of the straight line of perspective plane mapping point: view
Point pi(xp,yp,zp) with the center p on perspective planei’(x0,y0,z0) the method phasor that constitutes, therefore its space line equation can indicate
Are as follows:
Wherein, xi、yi、ziFor the coordinate of each vertex v i, m, n, r are the normal vector of straight line, by the derivation of equation (9) with
The solution of equations that formula (10) is formed, the mapping point v of the available vertex on the projection surfacei’(xi’,yi’,zi'), again
Generate vertex, mapping the f ' (v of face on the projection surface1’,v2’,v3’)。
Step 3-3: if find p ' in the plane one group cross p ' and orthogonal base vector e1、e2(with this two groups
Base vector).For the point q (x on perspective planeq,yq,zq), it is calculated in two-dimensional coordinate the q ' (x on perspective planeq’,yq') can
To be calculated with following formula:
PQ=PO+OQ, (12)
Wherein, PQ, PO, OQ are respectively p to q, the vector of p to o, o to q.
That is:
Xq'*e1+yq*e2=PO+OQ, (13)
Wherein, e1 is the base vector of q x-axis direction on this plane, and e2 is the base vector in the y-axis direction on this plane q.
It is all known, e on the right of formula in formula (12)1、e2It can also calculate.The formula can be regarded as at this time
About xq’、yq' linear equation in two unknowns.Both members can be distinguished into dot product e1、e2, it may be assumed that
Xq'*e1e1+yq*e2e1=(PO+OQ) e1,
Xq'*e1e2+yq*e2e2=(PO+OQ) e2,
Wherein, e1 is the base vector of q x-axis direction on this plane, and e2 is the base vector in the y-axis direction on this plane q.
PQ, OQ are respectively p to q, the vector of o to q；
Due to e1、e2It is orthogonal, therefore e2·e1=0, it is possible thereby to calculate separately to obtain xq’、yq', i.e. Q is on the projection surface
It take P ' as the coordinate of origin；
Step 3-4: built-in function --- the polybool for calculating two polygon unions in Matlab.It is defined such as
Under:
[x, y]=function (operation, x1,y1,x2,y2)；
Wherein, x, y are the return value of function, and x is two polygon (x1, y1)、(x2、y2) ask the polygon top after union
The x-axis direction coordinate of the sequence clockwise of point, y are its coordinate in the y-axis direction.Two polygons are held in operation expression
When capable operation, when the operation of input is ' union ', that is, seek the union of two polygons.
Step 4, the number of views that every model I is determined by the calculated result of step 3, step 4 specifically include following step
It is rapid:
Step 4-1: the average entropy E of all viewpoints of each model is calculated firstm, it is every that each model is then calculated again
One viewpoint is relative to average entropy EmStandard deviation Sd。
Step 4-2: Euclidean distance C=sqrt (Sd^2+Em^2).Wherein, Sd、EmIt respectively indicates through every a kind of mould
Value after the maximum value of respective value is normalized in type.
Step 4-3:Nc=a*C*N0 (14)
Wherein, N0It is the complete or collected works that feature viewpoint is extracted, herein, N0For the half of 42 viewpoints, i.e., 21.A is one normal
Amount due to only considering the half of view region, therefore enables a be equal to 0.5.C is found out by step 4-2, indicates model complexity.NCI.e.
For final number of views.
Step 5 carries out cluster operation to viewpoint complete or collected works by the calculated result of step 4, determines selected viewpoint.Step 5 tool
Body the following steps are included:
(1) input: k (cluster number) and p=m*n matrix randomly choose k initial cluster center, such as: enabling q=k*
N, q (i :)=p (i :)；
(2) for each object in p, p (i :), by it, the distance of (i :) is compared with q respectively, if its by its
Be added in the matrix of another r=k*n, under be designated as r (i, j)；
(3) it for every a line in matrix r, recalculates to be the matter of element in lower target p with the element in a line in r
Then the heart exchanges the value of q (i :) with the value；
(4) (2) (3) are repeated, until the variation of all q (i :) value is less than given threshold value；
Step 6, the viewpoint generated by step 5 generate the two-dimensional projection views in these viewpoint drags.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (3)
1. a kind of three-dimensional model search viewpoint selection method based on sketch, which comprises the following steps:
Step 1 manually classifies to the model in database；
Step 2 determines the complete or collected works of viewpoint by carrying out triangle subdivision to regular dodecahedron；
Step 3 calculates each model in the entropy of each viewpoint；
Step 4, the number of views that every model I is determined by the calculated result of step 3；
Step 5 carries out cluster operation to viewpoint complete or collected works by the calculated result of step 4, determines selected viewpoint；
Step 6 generates two-dimensional projection views according to the viewpoint that step 5 generates；
The step 2 the following steps are included:
Step 2-1, it is positive the centre of sphere of icosahedral circumsphere with the origin of three-dimensional cartesian coordinate system, radius is 2 to draw one
Regular dodecahedron；
Step 2-2, the subdivision in face is realized by the way that 1 gore is split into 4 small gores；
According to the different modes generated, the point generated after subdivision is divided into two classes:
(3) first kind point: the point being calculated by the side of original triangle；
(4) second class points: the point being calculated by original vertex of a triangle；
Whether it is boundary according to its affiliated side for the first kind point and the second class point, it is newly-generated is divided into two kinds of situations calculating
The coordinate of point:
For first kind point:
(1) if the side of former triangle is boundary edge, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V1、V2Respectively two vertex of boundary edge, by formula (1) it is found that
(2) if the non-boundary edge in side of former triangle, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V2、V3It is two vertex of the non-boundary edge, V1、V4Be with the two vertex all intersect in the non-boundary edge two
Side and two vertex nearest apart from the side, from formula (2):
For the second class point:
If the side of former triangle is boundary edge, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein, V1It is corresponding vertex, V in original triangle shape1、V3It is two vertex that V1 is adjacent in original triangle shape respectively, by
Formula (3), it is known that:
If the non-boundary edge in side of former triangle, the calculation formula of the coordinate of newly-generated point are as follows:
Wherein,
As n=3,As n > 3,ViThe vertex in the former polygon for having a line to be connected with V is represented,
From formula (4) and formula (5):
Wherein, Vi=V2, V3 or V5；
The step 3 the following steps are included:
Step 3-1, model x is in viewpoint pjThe calculation formula of the entropy at place is as follows:
Wherein, E indicates that entropy of the model at the viewpoint, m indicate the quantity in the face of the model, AiIndicate i-th of face in the view
Effective area under point, S indicates the gross area in the model rendering region, due to by the scaling of model to unit ball, therefore
S is indicated on an equal basis with the area of unit circle；A0Indicate that the area of background parts, i.e. rendering region gross area S subtract model throwing
The gross area of the shadow on the face, as A0；The value of E is bigger, indicates that the complexity of the model is also bigger, the viewpoint number needed
It can be more；
Step 3-2, A (x-X0)+B(y-y0)+C(z-z0)=0, (9)
Wherein, A, B, C are respectively equal to xn、yn、zn, i.e. the three-dimensional coordinate of the normal vector of the plane, (x0, y0, z0) indicate flat at this
The coordinate of some known point on face, the plane equation can be used to indicate the plane equation on perspective plane；
For each vertex v of modeli(xi, yi, zi), the point can be calculated and normal vector is identical with viewpoint normal vector straight
Line equation；Due to being general perspective, thus vertex and its can be considered as in the normal vector of the straight line of perspective plane mapping point: viewpoint pi
(xp, yp, zp) with the center p on perspective planei’(x0, y0, z0) the method phasor that constitutes, therefore its space line equation can indicate are as follows:
Wherein, xi、yi、ziFor the coordinate of each vertex v i, m, n, r are the normal vector of straight line, pass through the derivation of equation (9) and formula
(10) solution of equations formed, the mapping point v of the available vertex on the projection surfacei’(xi', yi', zi'), it regenerates
Mapping the f ' (v of vertex, face on the projection surface1', v2', v3')；
Step 3-3: if find p ' in the plane one group cross p ' and orthogonal base vector e1、e2?；For projection
A point q (x on faceq, yq, zq), it is calculated in two-dimensional coordinate the q ' (x on perspective planeq', yq') can be calculated with following formula:
PQ=PO+OQ, (12)
PQ, PO, OQ are respectively p to q, the vector of p to o, o to q；
That is:
Xq ' * e1+yq*e2=PO+OQ, (13)
Wherein, e1 is the base vector of q x-axis direction on this plane, and e2 is the base vector in the y-axis direction on this plane q；
It is all known, e on the right of formula in formula (12)1、e2It can also calculate；At this time the formula can regard as about
xq’、yq' linear equation in two unknowns；Both members can be distinguished into dot product e1、e2, it may be assumed that
Xq ' * e1e1+yq*e2e1=(PO+OQ) e1,
Xq ' * e1e2+yq*e2e2=(PO+OQ) e2,
Wherein, e1 is the base vector of q x-axis direction on this plane, and e2 is the base vector in the y-axis direction on this plane q；PQ,OQ
The vector of respectively p to q, o to q；
Due to e1、e2It is orthogonal, therefore e2·e1=0, it is possible thereby to calculate separately to obtain xq’、yq', i.e. Q is on the projection surface with P '
For the coordinate of origin；
Step 3-4: the built-in function polybool for calculating two polygon unions in Matlab, the polybool's determines
Justice is as follows:
[x, y]=function (operation, x1, y1, x2, y2)；
Wherein, x, y are the return value of function, and x is two polygon (x1, y1)、(x2、y2) seek the suitable of the polygon vertex after union
The x-axis direction coordinate of hour hands sequence, y are its coordinate in the y-axis direction；Operantion indicates the behaviour executed to two polygons
Make, when the operation of input is ' union ' when, that is, seek the union of two polygons.
2. the three-dimensional model search viewpoint selection method based on sketch as described in claim 1, which is characterized in that the step
4 the following steps are included:
Step 4-1: the average entropy E of all viewpoints of each model is calculated firstm, then calculate again each model each
Viewpoint is relative to average entropy EmStandard deviation Sd；
Step 4-2: Euclidean distance C=sqrt (Sd^2+Em^2)；Wherein, Sd、EmIt respectively indicates by right in every model I
The maximum value that should be worth be normalized after value；
Step 4-3:Nc=a*C*N0, (14)
Wherein, N0It is the complete or collected works that feature viewpoint is extracted, enables N0For the half of 42 viewpoints, it may be assumed that N0=21；A is a constant, by
In the half of only consideration view region, therefore a is enabled to be equal to 0.5；C is found out by step 4-2, indicates model complexity, NCAs most
Whole number of views.
3. the three-dimensional model search viewpoint selection method based on sketch as described in claim 1, which is characterized in that the step
5 the following steps are included:
(1) input: cluster number k and p=m*n matrix randomly chooses k initial cluster center, enables q=k*n, q (i :)=
P (i :)；
(2) for each object in p, p (i :), by it, the distance of (i :) is compared with q respectively, if it is added into
In the matrix of another r=k*n, under be designated as r (i, j)；
(3) it for every a line in matrix r, recalculates to be the mass center of element in lower target p with the element in a line in r,
Then the value of q (i :) is exchanged with the value；
(4) (2) (3) are repeated, until the variation of all q (i :) value is less than given threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645547.1A CN105243137B (en) | 2015-09-30 | 2015-09-30 | A kind of three-dimensional model search viewpoint selection method based on sketch |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645547.1A CN105243137B (en) | 2015-09-30 | 2015-09-30 | A kind of three-dimensional model search viewpoint selection method based on sketch |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105243137A CN105243137A (en) | 2016-01-13 |
| CN105243137B true CN105243137B (en) | 2018-12-11 |
Family
ID=55040785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510645547.1A Expired - Fee Related CN105243137B (en) | 2015-09-30 | 2015-09-30 | A kind of three-dimensional model search viewpoint selection method based on sketch |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105243137B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018117587A1 (en) * | 2016-12-19 | 2018-06-28 | Samsung Electronics Co., Ltd. | Method and system for producing 360 degree content on rectangular projection in electronic device |
| CN108171794B (en) * | 2018-01-19 | 2022-04-05 | 东莞市燕秀信息技术有限公司 | Plane view projection method, device, equipment and medium based on three-dimensional model |
| CN108537887A (en) * | 2018-04-18 | 2018-09-14 | 北京航空航天大学 | Sketch based on 3D printing and model library 3-D view matching process |
| CN109213884B (en) * | 2018-11-26 | 2021-10-19 | 北方民族大学 | Cross-modal retrieval method based on sketch retrieval three-dimensional model |
| CN113032613B (en) * | 2021-03-12 | 2022-11-08 | 哈尔滨理工大学 | Three-dimensional model retrieval method based on interactive attention convolution neural network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004748A (en) * | 2006-10-27 | 2007-07-25 | 北京航空航天大学 | Method for searching 3D model based on 2D sketch |
| CN101281545A (en) * | 2008-05-30 | 2008-10-08 | 清华大学 | Three-dimensional model search method based on multiple characteristic related feedback |
| CN104850633A (en) * | 2015-05-22 | 2015-08-19 | 中山大学 | Three-dimensional model retrieval system and method based on parts division of hand-drawn draft |
-
2015
- 2015-09-30 CN CN201510645547.1A patent/CN105243137B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004748A (en) * | 2006-10-27 | 2007-07-25 | 北京航空航天大学 | Method for searching 3D model based on 2D sketch |
| CN101281545A (en) * | 2008-05-30 | 2008-10-08 | 清华大学 | Three-dimensional model search method based on multiple characteristic related feedback |
| CN104850633A (en) * | 2015-05-22 | 2015-08-19 | 中山大学 | Three-dimensional model retrieval system and method based on parts division of hand-drawn draft |
Non-Patent Citations (2)
| Title |
|---|
| "A comparison of methods for sketch-based 3D shape retrieval";Bo Li etc，;《Computer Vision and Image Understanding》;20141231;第57-80页 * |
| "Sketch-Based 3D Model Retrieval by Viewpoint Entropy-Based Adaptive View Clustering";Bo Li etc,;《Eurographics Workshop on 3d Object Retrieval. Eurographics Association》;20130511;第1-8页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105243137A (en) | 2016-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105243137B (en) | A kind of three-dimensional model search viewpoint selection method based on sketch | |
| CN102792302B (en) | For the formation of the method and apparatus of surface treatment data | |
| CN110226806B (en) | Sole gluing track generation method and device | |
| CN110220493A (en) | A kind of binocular distance measuring method and its device | |
| KR20100125106A (en) | Apparatus and method for three-dimensional modeling using lattice structure | |
| CN104346824A (en) | Method and device for automatically synthesizing three-dimensional expression based on single facial image | |
| CN106652015B (en) | Virtual character head portrait generation method and device | |
| CN101877146B (en) | Method for extending three-dimensional face database | |
| CN111671518B (en) | Processing and generating method and device for hip joint femoral head spherical center and computer equipment | |
| CN105931298A (en) | Automatic selection method for low relief position based on visual significance | |
| CN110489778A (en) | Pattern dividing method, laser ablation control system towards laser ablation processing | |
| CN107680168A (en) | Lattice simplified method based on plane fitting in three-dimensional reconstruction | |
| JP6863596B6 (en) | Data processing device and data processing method | |
| CN104143209B (en) | Method for engraving three-dimensional model based on line pattern | |
| CN103810750A (en) | Human body section ring based parametric deformation method | |
| CN104361625A (en) | Ray principle based cloud data compaction algorithm with boundary reservation | |
| CN110837326B (en) | Three-dimensional target selection method based on object attribute progressive expression | |
| CN114169022A (en) | Method and system for engraving 3D surface of engraving target on blank | |
| CN104809318B (en) | A kind of quality of materials and centroid algorithm of the built-in engineering of ship's space | |
| CN106408654B (en) | A kind of creation method and system of three-dimensional map | |
| CN102682473A (en) | Virtual clothing real-time physical modeling method | |
| CN103489220A (en) | Method for building statistical shape model for three-dimensional object | |
| CN110222583A (en) | A kind of facial generation technique based on face recognition | |
| CN105957141B (en) | A kind of three-dimensional flower modeling method based on symmetrical structure | |
| CN104794747A (en) | Three-dimensional point cloud data simplification algorithm based on ray theory |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181211 Termination date: 20210930 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |