CN104376597B - A kind of hair method for reconstructing based on multi-direction constraint - Google Patents
A kind of hair method for reconstructing based on multi-direction constraint Download PDFInfo
- Publication number
- CN104376597B CN104376597B CN201410740979.6A CN201410740979A CN104376597B CN 104376597 B CN104376597 B CN 104376597B CN 201410740979 A CN201410740979 A CN 201410740979A CN 104376597 B CN104376597 B CN 104376597B
- Authority
- CN
- China
- Prior art keywords
- hair
- point
- field
- grid
- geometry
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/30—Polynomial surface description
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a kind of hair method for reconstructing based on multi-direction constraint, using the hair surface geometry, hair surface direction and head model geometry rebuild from image, reconstructs complete Hair model.Its step is：(1) based on Laplace's equation, the space lattice field of direction of hair is solved using hair surface direction；(2) based on Laplace's equation, using hair surface geometry and the space lattice distance field of head model geometry solving hair；(3) direction field direction according to step (1), the distance field gradient direction of step (2) and known hair surface direction, reconstruct each hair geometry from the equally distributed root of hair point of scalp；(4) the initial geometry for obtaining according to step (3), the direction obtained using step (2), are carried out the optimization based on energy minimization to initial Hair model, obtain final Hair model.The present invention can reconstruct hair growth distribution uniformly, the Hair model of appearance and collection image similarity.
Description
Technical field
The invention belongs to virtual reality technology field, specifically, a kind of hair based on multi-direction constraint is rebuild.
Background technology
In computer graphics, the correct modeling to virtual portrait, the always important problem of researcher.Nothing
By the field for being film special efficacy, video-game, virtual reality or other graphics correlations, vision real character's modeling technique
All it is widely used.And hair is then a key character of personage, the form of hair varies with each individual, and even distinguishes sometimes
The key character of different people.Meanwhile, the hair for constituting hair is very more, the moulding of hair, the optical characteristics moved and its have
All sufficiently complex, the scalp electroacupuncture of the sense of reality becomes a Research Challenges of computer graphics.
In film, animation or field of virtual reality, the Geometric Modeling of three-dimensional Hair model is always a loaded down with trivial details job.
At present, Most models are still relied on artist and are carried out the work of forming hair and modeling using interactive tool by hand.In recent years,
The method for constantly beginning with researcher's trial automation, rebuilds from view data and the akin model of true hair.Base
In the scalp electroacupuncture method of image, it is typically based on image information and obtains preliminary hair geometrical constraint and direction and constrain, then therefrom
Reconstruct complete Hair model.The three-dimensional hair method for reconstructing generally individually acquisition hair surface first for being currently based on image is several
What, and the direction of hair surface is reconstructed by the directional information for analyzing each two-dimensional image.Subsequently, a class method, directly by table
The face field of direction is diffused into whole space, rebuilds hair, the hair for obtaining uniform but profile enough and figure using the uniform field of direction
Aberration is not larger；Another kind of side rebuilds outside hair first, then is connected to scalp, the hair profile for obtaining and image phase
Seemingly, but cannot ensure that hair uniformly cannot also rebuild internal structure.
Traditional two methods are compared, the advantage of two class methods is combined by the present invention so that being grown in for hair is interior
Portion is grown by uniform direction, is grown by surface direction outside, is combined the advantage of two methods.
Therefore, the present invention is directed to the great Research Significance of work and application prospect of the scalp electroacupuncture for giving image.
The content of the invention
The technology solve problem of the present invention：Overcome some limitation of prior art, there is provided a kind of to be based on multi-direction constraint
Hair method for reconstructing, the hair geometry of hair is effectively rebuild after preliminary hair surface data are obtained, vision is obtained true
Hair model.
The technical solution of the present invention：With hair surface geometry, hair surface direction, head model geometry as input, base
Rebuild in the hair of multi-direction constraint, hair reconstruction is constrained jointly using the field of direction and hair surface direction of gridding, so as to
Rebuild Hair model.It is characterized in that following steps：
(1) the hair field of direction of spatial gridding is rebuild according to the hair surface direction of input；
(2) distance field according to the hair surface geometry and head model geometrical reconstruction spatial gridding being input into；
(3) field of direction obtained by (1), the hair surface direction of input and distance field obtained by (2) is utilized to rebuild hair geometry；
(4) field of direction obtained by utilization (1), is optimized to the Hair model obtained by (3)；
It is an advantage of the current invention that：
1st, the process of reconstruction of the hair hair designed by the present invention, hair uniformly grow from scalp, are grown into the end
Face is delivered, hair is evenly distributed rationally, the hair direction of growth nature under the constraint in space lattice direction.
2nd, the process of reconstruction of the hair hair designed by the present invention, when hair growth is close to scalp, will be by hair surface side
To growth, collection image outside hair, is close to.
3rd, the hair of the multi-direction constraint designed by the present invention is rebuild so that keep outer while natural on-off cycles of hair growth is evenly distributed
Portion's form is true to nature, is easy to the reuse for reconstruction model.
Description of the drawings
Data flowcharts of the Fig. 1 for the inventive method.
Specific embodiment
With reference to the accompanying drawings and detailed description the present invention is described in further detail.
The broad flow diagram of the inventive method is as shown in figure 1, possessing hair surface geometry, hair surface direction, head mould
Under type geometry is for input, comprise the following steps that：
(1) the spatial gridding hair field of direction is solved.
In the present invention, the spatial gridding hair field of direction is solved, and provides the grid side of continuous distributed for whole reconstruction regions
To field.First according to the point in the hair surface geometry and head model geometry of input, the bounding box of whole region is calculated, set
Whole region is evenly divided into cube grid, realizes spatial gridding by certain grid cell size.Subsequently, set up and draw
Laplace equation, grid are contained within the direction that the grid direction of hair surface geometry is set to the hair geometry, bounding box border net
Lattice are set to Di Li Crays border, and remaining grid is unknown direction.Finally, Laplace's equation is solved, obtains the net of space smoothing
The lattice field of direction.
(2) spatial gridding distance field；
In order that natural on-off cycles of hair growth is gradually drawn close to hair surface from scalp, the present invention provides related direction about using distance field
Beam.First with the grid obtained by the gridding in the step (1), bag in Laplace's equation, grid is set up in space
Grid distance value containing hair surface geometry is set to 0, and the grid distance value comprising head model geometric jacquard patterning unit surface is set to -1, space
The grid on bounding box border is set to 1.Subsequently, the Laplace's equation is solved, hair surface distance continuous in space is obtained
, hair surface is 0, is negative inside hair, for just outside hair.
(3) rebuild based on multidirectional hair.
This step is the core procedure of the present invention, starts to rebuild each hair from scalp.First, user refers on head model surface
Determine natural on-off cycles of hair growth region, uniform sampling goes out root of hair point in the zone, the direction of growth of the root of hair of hair is set to change the time in head model
Direction direction and away from certain proportion between the tangential direction of hair parting line.Then begin to pointwise and reconstruct whole hair,
Represent a hair with ξ, ξ is made up of each point ξ (0) thereon, ξ (1) ... .. ξ (N), the reconstruction of hair from the beginning of root of hair ξ (0), by
Point is rebuild, and every ξ (i) is rebuild, and is determined by formula (1).
ξ (i)=ξ (i-1)+α1V(ξ(i-1))+α2▽(D(ξ(i-1)))+α3Ο(ξ(i-1))+α4S(ξ(i-1))(1)
Wherein, ξ (i-1) the i.e. positions of ξ (i) former points, sides of the V (ξ (i-1)) for (1) of ξ (i-1) position
To field be worth, distance field values of the D (ξ (i-1)) for (2) of ξ (i-1) position, ▽ (D (ξ (i-1))) the i.e. positions away from
From gradient direction, Ο (ξ (i-1)) is the direction of growth of ξ (i-1), and by aforementioned determination, remaining is then by ξ (i-1)-ξ in root node direction
(i-2) determine, S (ξ (i-1)) is apart from the direction of ξ (i-1) nearest hair surface geometry.α in formula1, α2, α3, α4For each
The weight of direction constraint, α1, α2Bigger, the α apart from the nearlyer weight of scalp4Bigger, the α apart from the nearlyer weight of hair surface3For constant.
For every hair, when distance field value D (ξ (i)) of its new reconstruction point ξ (i) is more than certain threshold value, or hair
Total length be more than certain threshold value when, hair rebuild terminate.
(4) hair based on energy minimization optimizes.
Hair optimization based on energy minimization is rebuild all hairs for obtaining to the step (3) and is optimized.Optimization
Realized by the minimum to ENERGY E, E is determined by formula (2).
Wherein, ξ0I () rebuilds the initial hair point for obtaining for the step (3), ξ (i) is required point, and the direction of V, Ο contains
It is adopted identical with the step (3), i.e. V (ξ0(i-i) it is) ξ0(i-i) field of direction value of (1) of position, Ο (ξ0(i-
I) it is) ξ0(i-1) the direction of growth.N(ξ0(i)) for all apart from ξ0Apart from ξ on (i) each hair near enough0I () is nearest
The point set of point.w(ξ0 n(in)) it is to uniform by the weight apart from the Gauss for calculating, αreg, αort, αnFor each energy term coefficient,
It is constant.
The content not being described in detail in description of the invention belongs to prior art known to professional and technical personnel in the field.
The foregoing is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
This is considered as protection scope of the present invention.
Claims (3)
1. a kind of hair method for reconstructing based on multi-direction constraint, its input is hair surface geometry, the hair surface field of direction and
Head model, it is characterised in that comprise the following steps：
1) the spatial gridding hair field of direction is solved；
2) spatial gridding distance field is solved；
3) rebuild based on multidirectional hair；
4) Hair model based on energy minimization optimizes；
The step 1) in the spatial gridding hair field of direction solve, its step is：It is spatial discretization first, according to input
Hair geometry and head model, calculate the spatial surrounding box of rebuild 3D region, and press Unified Element by space uniform discretization
For grid；Secondly, the field of direction that Laplace's equation solves hair gridding, the grid side respectively comprising hair surface direction are set up
To the surface direction is set to, the boundary condition of space lattice is set to Di Li Crays border；Finally, by solving the Laplce side
Journey obtains the direction of each locality grid, so as to obtain the hair field of direction；
The step 3) in, to be rebuild based on multidirectional hair, its step is：First, user specifies natural on-off cycles of hair growth area in scalp
Domain；Secondly, uniformly in growth district sampling root of hair point, the initial growth direction of per takes the normal direction by a certain percentage and cuts
To between；Subsequently, using the multiple each hair of direction constraint reestablishing, hair is rebuild from the pointwise of root of hair point position, and one new to send out
Direction of the position of silk point by former point, grid direction field direction, grid distance field gradient direction are nearest apart from former point
Hair surface direction constrains determination jointly, and this process is realized using equation below：
α in formula1, α2, α3, α4For the weight of all directions constraint, α1, α2Bigger, the α apart from the nearlyer weight of scalp4Apart from hair surface
Nearlyer weight is bigger, α3For constant, ξ represents a hair, and ξ is made up of each point ξ (0) thereon, ξ (1) ... .. ξ (N), and ξ (i) is i.e.
I-th point, ξ (i-1) the i.e. positions of ξ (i) former points, V (ξ (i-1)) are the step 1 of ξ (i-1) position) direction
Value, D (ξ (i-1)) is the step 2 of ξ (i-1) position) distance field value,I.e. the position away from
From gradient direction, Ο (ξ (i-1)) is the direction of growth of ξ (i-1), and S (ξ (i-1)) is several apart from the nearest hair surfaces of ξ (i-1)
What direction；Finally, when each hair grows to maximum length, or the distance value of new hair point stops more than certain threshold value hair
Growth.
2. a kind of hair method for reconstructing based on multi-direction constraint according to claim 1, it is characterised in that：The step
2) in, spatial gridding distance field is solved, and its step is as follows：First, using the step 1) in identical discretization grid build
Vertical Laplace's equation, the grid distance comprising hair surface geometry are set to 0, and the grid distance comprising head surface is set to -1, net
The distance on lattice border is set to 1.
3. a kind of hair method for reconstructing based on multi-direction constraint according to claim 1, it is characterised in that：The step
4) in, the Hair model based on energy minimization optimizes, and its key step is as follows：With the step 3) each hair point for reconstructing
It is optimized for initial position, is constrained to suffered by each point：Various point locations and the initial position are close to, at the beginning of each point direction and the point
The grid direction field value of beginning position is close to, the weighting direction of each point direction and the initial position neighborhood other hair closest approaches connects
Closely.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740979.6A CN104376597B (en) | 2014-12-05 | 2014-12-05 | A kind of hair method for reconstructing based on multi-direction constraint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410740979.6A CN104376597B (en) | 2014-12-05 | 2014-12-05 | A kind of hair method for reconstructing based on multi-direction constraint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104376597A CN104376597A (en) | 2015-02-25 |
| CN104376597B true CN104376597B (en) | 2017-03-29 |
Family
ID=52555486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410740979.6A Expired - Fee Related CN104376597B (en) | 2014-12-05 | 2014-12-05 | A kind of hair method for reconstructing based on multi-direction constraint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104376597B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105405163B (en) * | 2015-12-28 | 2017-12-15 | 北京航空航天大学 | A kind of static scalp electroacupuncture method true to nature based on multi-direction field |
| CN107886516B (en) * | 2017-11-30 | 2020-05-15 | 厦门美图之家科技有限公司 | Method and computing equipment for computing hair trend in portrait |
| CN108629834B (en) * | 2018-05-09 | 2020-04-28 | 华南理工大学 | Three-dimensional hair reconstruction method based on single picture |
| CN109087377B (en) * | 2018-08-03 | 2019-11-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN109685876B (en) * | 2018-12-21 | 2020-11-03 | 北京达佳互联信息技术有限公司 | Hair rendering method and device, electronic equipment and storage medium |
| CN113763228B (en) * | 2020-06-01 | 2024-03-19 | 北京达佳互联信息技术有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN112465943B (en) * | 2020-12-04 | 2023-05-30 | 上海米哈游天命科技有限公司 | Color rendering method and device, electronic equipment and storage medium |
| CN115661375B (en) * | 2022-12-27 | 2023-04-07 | 北京百度网讯科技有限公司 | Three-dimensional hair style generation method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419868A (en) * | 2010-09-28 | 2012-04-18 | 三星电子株式会社 | Device and method for modeling 3D (three-dimensional) hair based on 3D hair template |
| CN102800129A (en) * | 2012-06-20 | 2012-11-28 | 浙江大学 | Hair modeling and portrait editing method based on single image |
| CN103035030A (en) * | 2012-12-10 | 2013-04-10 | 西北大学 | Hair model modeling method |
| CN103606186A (en) * | 2013-02-02 | 2014-02-26 | 浙江大学 | Virtual hair style modeling method of images and videos |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7098910B2 (en) * | 2003-05-14 | 2006-08-29 | Lena Petrovic | Hair rendering method and apparatus |
-
2014
- 2014-12-05 CN CN201410740979.6A patent/CN104376597B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419868A (en) * | 2010-09-28 | 2012-04-18 | 三星电子株式会社 | Device and method for modeling 3D (three-dimensional) hair based on 3D hair template |
| CN102800129A (en) * | 2012-06-20 | 2012-11-28 | 浙江大学 | Hair modeling and portrait editing method based on single image |
| CN103035030A (en) * | 2012-12-10 | 2013-04-10 | 西北大学 | Hair model modeling method |
| CN103606186A (en) * | 2013-02-02 | 2014-02-26 | 浙江大学 | Virtual hair style modeling method of images and videos |
Non-Patent Citations (3)
| Title |
|---|
| A Hybrid Image-CAD Based System for Modeling Realistic Hairstyles;Xuan Yu 等;《Conference: Proceedings of the 18th meeting of the ACM SIGGRAPH Symposium on Interactive 3D》;20140331;第63-70页 * |
| Dynamic Hair Capture using Spacetime Optimization;Zexiang Xu 等;《ACM Transactions on Graphics（TOG）-Proceedings of ACM SIGGRAPH》;20141130;第33卷(第6期);正文第1节、第5.1-5.3节 * |
| 基于动力学的头发造型方法;宋金莲 等;《中国科学院研究生院学报》;20120731;第29卷(第4期);第543-548页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104376597A (en) | 2015-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104376597B (en) | A kind of hair method for reconstructing based on multi-direction constraint | |
| CN107316340B (en) | Rapid face modeling method based on single photo | |
| CN103606190B (en) | Method for automatically converting single face front photo into three-dimensional (3D) face model | |
| De Aguiar et al. | Automatic conversion of mesh animations into skeleton‐based animations | |
| CN105405163B (en) | A kind of static scalp electroacupuncture method true to nature based on multi-direction field | |
| CN102339475B (en) | Rapid hair modeling method based on surface grids | |
| CN103310481B (en) | A kind of point cloud compressing method based on fuzzy entropy iteration | |
| WO2014117447A1 (en) | Virtual hairstyle modeling method of images and videos | |
| CN101719140A (en) | Figure retrieving method | |
| CN106960465A (en) | A kind of single image hair method for reconstructing based on the field of direction and spiral lines matching | |
| CN103530907A (en) | Complicated three-dimensional model drawing method based on images | |
| CN103366402A (en) | Fast attitude synchronization method of three-dimensional virtual clothing | |
| CN103093488A (en) | Virtual haircut interpolation and tweening animation producing method | |
| CN111524226A (en) | Method for detecting key point and three-dimensional reconstruction of ironic portrait painting | |
| Bao et al. | A survey of image-based techniques for hair modeling | |
| CN105957154B (en) | A kind of the threedimensional model edit methods and system of data-driven | |
| CN103383778B (en) | A kind of three-dimensional cartoon human face generating method and system | |
| Yu et al. | A hybrid image-cad based system for modeling realistic hairstyles | |
| CN105957141B (en) | A kind of three-dimensional flower modeling method based on symmetrical structure | |
| Orbay et al. | Sketch-based modeling of smooth surfaces using adaptive curve networks | |
| CN107146273A (en) | It is a kind of towards the self-adapting float tangent line matching process based on image scalp electroacupuncture | |
| Bao et al. | Realistic hair modeling from a hybrid orientation field | |
| CN105046727A (en) | Generation method of product effect picture | |
| CN109741454A (en) | A kind of sketch formula three-dimensional cartoon model formative method based on component combination and deformation | |
| CN112634458B (en) | Oral model point cloud simplifying method based on feature significance evaluation |
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: 20170329 Termination date: 20201205 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |