CN106650654A - Three-dimensional hairline extraction method based on colorful point cloud model of human head - Google Patents
Three-dimensional hairline extraction method based on colorful point cloud model of human head Download PDFInfo
- Publication number
- CN106650654A CN106650654A CN201611163972.8A CN201611163972A CN106650654A CN 106650654 A CN106650654 A CN 106650654A CN 201611163972 A CN201611163972 A CN 201611163972A CN 106650654 A CN106650654 A CN 106650654A
- Authority
- CN
- China
- Prior art keywords
- point
- head
- point cloud
- dimensional
- hair line
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Abstract
The invention discloses a three-dimensional hairline extraction method based on a colorful point cloud model of a human head. The method comprises the steps that the human head is scanned to acquire the dense head colorful point cloud model; a facial local coordinate system is established, and the point cloud model is converted into the established facial local coordinate system; a nose tip point is extracted; a deep color part of the head is extracted; point cloud of the deep color part is layered in the vertical direction, and the layers are sequenced in the horizontal direction; border line points of the point cloud of the deep color part are extracted; noise is removed, and hairline points are obtained; fitting is performed to obtain a three-dimensional hairline. According to the method, the colorful three-dimensional head point cloud model is utilized, the hairline points are extracted through a layer-by-layer sequencing analysis method based on the difference between hair color and skin color and human facial features, and the hairline is obtained through fitting; the three-dimensional hairline can be directly extracted, the method is convenient and easy to implement, algorithm complexity is low, data is easy to save and transmit, applicability is high, and the method has very high application value in face perception application systems, human engineering, reverse engineering, plastic surgery and other aspects.
Description
Technical field
The present invention relates to a kind of hair line extracting method.It is more particularly to a kind of based on human body head colour point clouds model
Three-dimensional hair line extracting method.
Background technology
Hair line is a key character of human body head, and hair line is extracted in facial aware application system, human body work
The aspects such as effect, reverse-engineering, plastic surgery have critically important Research Significance and using value.
In 3D video display, change the outfit the aspects such as game, and three-dimensional virtual hair is one of hot topic, is gained fame and fortune line by extraction three-dimensional,
The simulated effect of three-dimensional hair can be made more life-like;In wig production and sales field, carried by the real-time three-dimensional of hair line
Take, it is possible to achieve the private customization of hair net;In haircut hairdressing, tried on by virtual hair style, customer can be allowed omnibearing
Check that different hair styles, in oneself head model wearing effect, improve satisfaction of the customer to hair style;In plastic surgery, hair line
Extraction contribute to the determination of hair line Adjusted Option, on three-dimensional point cloud model, on the one hand, patient can in advance check adjustment
Line change of gaining fame and fortune in front and back, offers one's comment Xiang doctor, and on the other hand, doctor is gained fame and fortune by relatively more primary trace and design
The position of line, shape, can calculate Xian Shou areas area of gaining fame and fortune, and calculate hair follicle demand, so as to judge the difficulty of the operation
Easy degree, and make rational operation plan.Meanwhile, colored head point cloud model is stored in electronic databank, realize
The data sharing in the whole world, it is easier to obtain the mass data of each race, by extracting three-dimensional hair line, to hair line qualitative, quantitative
Analysis, can obtain more more specifically hair line characteristics, to facial perception, human engineering etc. with very big Research Significance.
At present the existing method for extracting hair line point on 2d, recycles the mapping relations of 2 d-to-3 d, will
Hair line is transformed on threedimensional model, and process is numerous and diverse.
The content of the invention
The technical problem to be solved is to provide and a kind of directly can extract three-dimensional from colored point cloud model
Gain fame and fortune the three-dimensional hair line extracting method based on human body head colour point clouds model of line.
The technical solution adopted in the present invention is:A kind of three-dimensional hairline line drawing based on human body head colour point clouds model
Method, comprises the steps:
1) human body head is scanned, obtains dense head colour point clouds model;
2) face local coordinate system is set up, and point cloud model is transformed in set up face local coordinate system;
3) prenasale is extracted;
4) head dark parts are extracted;
5) dark parts point cloud is layered according to vertical direction, and is sorted according to horizontal direction;
6) the boundary line point of dark parts point cloud is extracted;
7) noise is removed, obtains hair line point;
8) fitting obtains three-dimensional hair line.
Step 2) include:With the lofty perch of left and right ear or close at lofty perch, and on the basis of glabella point, set up face office
Portion's coordinate system, by translating and rotating under head colour point clouds model conversion to face local coordinate system, and makes to work as face office
When portion's coordinate system overlaps with earth coordinates, head colour point clouds model faces front;Face local coordinate system is colored with head
The left of point cloud model is X-axis positive direction, and the top of head colour point clouds model is Y-axis positive direction, head colour point clouds model
Front be Z axis positive direction.
Step 4) it is to extract head dark parts, including skull, eyebrow and eyeball using RGB information.
Step 5) be included in face local coordinate system, to the dark parts point cloud that extracts according to Y-coordinate value at equal intervals
Layering, is divided into into n-layer, and the point cloud to each layer sorts successively from small to large according to X-coordinate value.
Step 6) in each layer of point cloud, the X-coordinate difference between each consecutive points is calculated respectively, when two of which it is adjacent
When X-coordinate difference between point exceedes certain threshold value, that is, think that the two points are the boundary line point of dark parts.
Step 7) on the basis of prenasale, with reference to the statistical value of facial size, remove the eyebrow and eye in the point of boundary line
Ball portion, obtains hair line point.
Step 8) in, using bounding box method to step 7) the hair line point that obtains simplifies, and it is bent using cubic B-spline
Line fitting obtains three-dimensional hair line.
The present invention a kind of three-dimensional hair line extracting method based on human body head colour point clouds model, the characteristics of maximum
In using colored three-dimensional head point cloud model, based on color development and the difference and human body facial feature of the colour of skin, by successively sorting
Analytic approach extracts hair line point, and is fitted to hair line.It is an advantage of the current invention that can extracting directly three-dimensional hair line, it is easy
Easy, algorithm complex is low, and data are easy to preserve and transmit, and applicability is wide, facial aware application system, human engineering,
The aspects such as reverse-engineering, plastic surgery have critically important using value.
Description of the drawings
Fig. 1 is a kind of flow chart of the three-dimensional hair line extracting method based on human body head colour point clouds model of the present invention;
Fig. 2 a are the left front views of head colour point clouds model;
Fig. 2 b are the positive front views of head colour point clouds model;
Fig. 2 c are the right front views of head colour point clouds model;
Fig. 3 is that face local coordinate system sets up schematic diagram;
Fig. 4 is the transition diagram of different coordinates;
Fig. 5 a are the result exemplary plots that head colour point clouds model shows in original coordinate system;
Fig. 5 b are the result exemplary plots that head colour point clouds model shows in face local coordinate system;
Fig. 6 is the extraction result schematic diagram of dark parts;
Fig. 7 is the schematic diagram being layered according to Y-coordinate value;
Fig. 8 is the schematic diagram sorted according to X-coordinate value to i layers point cloud;
Fig. 9 a are the result exemplary plots of three-dimensional hair line fitting;
Fig. 9 b are the exemplary plots of three-dimensional hair line Relative distribution in head point cloud model of fitting.
Specific embodiment
With reference to a kind of three-dimensional hairline based on human body head colour point clouds model of embodiment and accompanying drawing to the present invention
Line drawing method is described in detail.
According to correlation study, generally, color development, wink and are undergone mutation than the color depth of the colour of skin in boundary color, i.e. RGB
Abrupt change of information.Therefore, a kind of three-dimensional hair line extracting method based on human body head colour point clouds model of the invention, extracts
The part of head RGB information mutation, the i.e. border at head dark color position, mainly contain hair line, eyebrow and eyeball position
Border;Further according to human body facial feature, the border of eyebrow and eyeball position is removed, line boundary of as gaining fame and fortune.
As shown in figure 1, a kind of three-dimensional hair line extracting method based on human body head colour point clouds model of the present invention, bag
Include following steps:
1) human body head is scanned, obtains dense head colour point clouds model.
Using color three dimension scanner scanning human body head, dense head colour point clouds model is obtained.The present invention is implemented
Example is to adopt color three dimension laser scanner, including three dimension system and color system.Wherein, three dimension system is based on laser triangulation
Method, drives scan module (including laser instrument and black-white CCD) to be swept by the way of moving up and down using One-dimensional Vertical motion guide rail
Retouch, Jing data processing modules, obtain the three-dimensional coordinate information of human body head;Color system is by colored CCD and data processing module
Composition, the main colour information for obtaining human body head, using the mapping relations of the three-dimensional coordinate and two-dimensional color information demarcated,
The three-dimensional information of matching head, obtains three-dimensional colour point cloud model.Data reduction compression, denoising, hole are carried out to point cloud model
The pretreatment such as filling, obtains preferably smooth head colour point clouds model.As shown in Fig. 2 a, Fig. 2 b, Fig. 2 c, as head is color
Color dot cloud model example.
2) face local coordinate system is set up, and point cloud model is transformed in set up face local coordinate system.Including:
For the head point cloud model random problem in position in a coordinate system, with the lofty perch of left and right ear or close at lofty perch, and
On the basis of glabella point, face local coordinate system is set up, by translating and rotating head colour point clouds model conversion to face office
Under portion's coordinate system, and make when face local coordinate system overlaps with earth coordinates, head colour point clouds model faces front;People
Face local coordinate system with the left of head colour point clouds model as X-axis positive direction, the top of head colour point clouds model be Y-axis just
Direction, the front of head colour point clouds model is Z axis positive direction.
The three-dimensional system of coordinate of different spatial digitizer definition is different, and when position, angle are sent out in same scanner
During changing, the three-dimensional coordinate of gained model also can be different, it is impossible to enough realize automatically extracting for characteristic point.Therefore, one is set up
New face local coordinate system, and point cloud model is transformed under the coordinate system so that when face local coordinate system is sat with the earth
When mark system overlaps, the point cloud model of human body head is in the orientation for facing front.In head point cloud model so as to before facing
Side, is extracted in same level and non-colinear at 3 points, and face local coordinate system can be set up as datum mark.Profit of the invention
Face local coordinate system is set up with automanual method.
According to human body facial feature, when human body head faces front, lofty perch and the glabella point of left and right ear are substantially at
Same level.Such as Fig. 3, with the point of proximity P of the lofty perch of left and right ear1、P2And glabella point P3On the basis of set up face local coordinate
System.Specific practice:
(1) P is connected1P2, X-axis is designated as, and with the left of head colour point clouds model as positive direction;
(2) by P3To P1P2Make vertical line, the point that hangs down is coordinate origin O, and remembers straight line OP3For Z axis, with head colour point clouds
The front of model is positive direction;
(3) according to right-handed coordinate system rule, Y-axis is judged, the top with head colour point clouds model is as positive direction.
In order to obtain the position of three points of left and right ear lofty perch and glabella point, can select to be in phase by the person of scanning in scanning
Answer position labelling thing and recognize, it is also possible to after point cloud model is obtained, this 3 points of position is selected manually.
Newly-established face local coordinate system and former coordinate system are misaligned, by translating to point cloud model, rotating, are obtained
Point cloud model under face local coordinate system.Fig. 4 is transition diagram of the point cloud model under different coordinates.Fig. 5 a, figure
5b is the result exemplary plot that head colour point clouds model shows in original coordinate system and face local coordinate system.
3) prenasale is extracted;
It is well known that nose is in the positive forefront of face.It can be seen from step S2, in face local coordinate system, nose
The Z values of cusp are maximum, and prenasale can be extracted accordingly.
4) head dark parts are extracted, specifically extracts head dark parts, including skull, eyebrow using RGB information
And eyeball;
It is general in human body face, hair, eyeball color than skin color depth, characteristic accordingly, in colour point clouds mould
In type, according to the concrete difference of color development and the colour of skin, a gray threshold (i.e. threshold value a) in Fig. 1, and select all gray scales is set
Value extracts dark parts less than the point of the threshold value, mainly including parts such as skull, eyebrow and eyeballs, acquired results example
See Fig. 6.
5) dark parts point cloud is layered according to vertical direction, and is sorted according to horizontal direction;It is included in face local to sit
In mark system, the dark parts point cloud to extracting is layered at equal intervals according to Y-coordinate value, is divided into into n-layer, and Fig. 7 is according to Y value point
The schematic diagram of layer.And the point cloud to each layer sorts successively from small to large according to X-coordinate value, Fig. 8 is m to i-th layer and clicks through
The schematic diagram of row sequence.The interlayer that this example is adopted is divided into 2mm.
6) the boundary line point of dark parts point cloud, as can be seen from Figure 8, the X value differences between most of consecutive points are extracted
Value all very littles, only have the difference comparsion between point j and (j+1) big, and the point of point j and (j+1) exactly boundary.Accordingly, it is right
Each layer of point cloud, calculates respectively the X-coordinate difference between each consecutive points, when the X-coordinate difference between two of which consecutive points
(the threshold value b) in Fig. 1 thinks that the two points are the boundary line point of dark parts during more than certain threshold value.This example is adopted
Difference threshold is 8mm.
7) noise is removed, obtains hair line point.On the basis of prenasale, with reference to facial size statistical value (such as nose length, eye
Length, eye spacing etc.), the eyebrow and ball portions in the point of boundary line is removed, obtain hair line point.
8) it is fitted to obtain three-dimensional hair line.The hair line point for extracting can go out often due to model or the defect of algorithm
The situation of existing data redundancy, so, computational efficiency is not high, and the curve for fitting is also rough, or even error is larger.Therefore, exist
On the basis of retaining the original feature of hair line point, need first to simplify hair line point, then be fitted.The present invention is to utilize bounding box
Method is to step 7) the hair line point that obtains is simplified, and obtain three-dimensional hair line using B-spline Curve fitting.
Traditional bounding box method is used for reference, with a certain size spatial surrounding box obligatory point cloud, to being distributed in each bounding box
In all point datas seek coordinate mean value, and replace the point data in whole bounding box.The algorithm is simple, and speed is fast, and protects
The feature of original hair line is held.The bounding box size that this example is adopted is for 8*8*8mm3。
Trace points of sending out after to simplifying are fitted using B-spline Curve, line of gaining fame and fortune are obtained, with recursion, locality
The characteristics such as matter, differentiability, convex-hull property.Fig. 9 a, Fig. 9 b are the result example of three-dimensional hair line fitting.
Claims (7)
1. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model, it is characterised in that including following step
Suddenly:
1) human body head is scanned, obtains dense head colour point clouds model;
2) face local coordinate system is set up, and point cloud model is transformed in set up face local coordinate system;
3) prenasale is extracted;
4) head dark parts are extracted;
5) dark parts point cloud is layered according to vertical direction, and is sorted according to horizontal direction;
6) the boundary line point of dark parts point cloud is extracted;
7) noise is removed, obtains hair line point;
8) fitting obtains three-dimensional hair line.
2. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
It is characterised by, step 2) include:With the lofty perch of left and right ear or close at lofty perch, and on the basis of glabella point, set up face
Local coordinate system, by translating and rotating under head colour point clouds model conversion to face local coordinate system, and makes to work as face
When local coordinate system overlaps with earth coordinates, head colour point clouds model faces front;Face local coordinate system is color with head
The left of color dot cloud model is X-axis positive direction, and the top of head colour point clouds model is Y-axis positive direction, head colour point clouds mould
The front of type is Z axis positive direction.
3. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
It is characterised by, step 4) it is to extract head dark parts, including skull, eyebrow and eyeball using RGB information.
4. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
Be characterised by, step 5) be included in face local coordinate system, to the dark parts point cloud that extracts according to Y-coordinate value at equal intervals
Layering, is divided into into n-layer, and the point cloud to each layer sorts successively from small to large according to X-coordinate value.
5. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
Be characterised by, step 6) in each layer of point cloud, the X-coordinate difference between each consecutive points is calculated respectively, when two of which phase
When X-coordinate difference between adjoint point exceedes certain threshold value, that is, think that the two points are the boundary line point of dark parts.
6. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
Be characterised by, step 7) on the basis of prenasale, with reference to the statistical value of facial size, remove the eyebrow and eye in the point of boundary line
Ball portion, obtains hair line point.
7. a kind of three-dimensional hair line extracting method based on human body head colour point clouds model according to claim 1, its
It is characterised by, step 8) in, using bounding box method to step 7) the hair line point that obtains is simplified, and utilize cubic B-spline
Curve matching obtains three-dimensional hair line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611163972.8A CN106650654B (en) | 2016-12-15 | 2016-12-15 | A kind of three-dimensional hair line extracting method based on human body head colour point clouds model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611163972.8A CN106650654B (en) | 2016-12-15 | 2016-12-15 | A kind of three-dimensional hair line extracting method based on human body head colour point clouds model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106650654A true CN106650654A (en) | 2017-05-10 |
CN106650654B CN106650654B (en) | 2019-11-22 |
Family
ID=58822914
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611163972.8A Expired - Fee Related CN106650654B (en) | 2016-12-15 | 2016-12-15 | A kind of three-dimensional hair line extracting method based on human body head colour point clouds model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106650654B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107221025A (en) * | 2017-05-31 | 2017-09-29 | 天津大学 | A kind of synchronous system and method for obtaining body surface three-dimensional colour point clouds model |
CN107621880A (en) * | 2017-09-29 | 2018-01-23 | 南京邮电大学 | A kind of robot wheel chair interaction control method based on improvement head orientation estimation method |
CN109559288A (en) * | 2018-11-30 | 2019-04-02 | 深圳市脸萌科技有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
CN111031848A (en) * | 2017-08-15 | 2020-04-17 | 真发有限责任公司 | Method and system for generating 3D digital models for use in wig manufacture |
CN111295664A (en) * | 2018-02-28 | 2020-06-16 | 华为技术有限公司 | Method and device for positioning hairline contour and computer readable storage medium |
CN117389676A (en) * | 2023-12-13 | 2024-01-12 | 成都白泽智汇科技有限公司 | Intelligent hairstyle adaptive display method based on display interface |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663820A (en) * | 2012-04-28 | 2012-09-12 | 清华大学 | Three-dimensional head model reconstruction method |
CN102799901A (en) * | 2012-07-10 | 2012-11-28 | 辉路科技(北京)有限公司 | Method for multi-angle face detection |
CN103473564A (en) * | 2013-09-29 | 2013-12-25 | 公安部第三研究所 | Front human face detection method based on sensitive area |
CN104318234A (en) * | 2014-10-23 | 2015-01-28 | 东南大学 | Three-dimensional extraction method of human face wrinkles shown in point cloud data and device thereof |
-
2016
- 2016-12-15 CN CN201611163972.8A patent/CN106650654B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663820A (en) * | 2012-04-28 | 2012-09-12 | 清华大学 | Three-dimensional head model reconstruction method |
CN102799901A (en) * | 2012-07-10 | 2012-11-28 | 辉路科技(北京)有限公司 | Method for multi-angle face detection |
CN103473564A (en) * | 2013-09-29 | 2013-12-25 | 公安部第三研究所 | Front human face detection method based on sensitive area |
CN104318234A (en) * | 2014-10-23 | 2015-01-28 | 东南大学 | Three-dimensional extraction method of human face wrinkles shown in point cloud data and device thereof |
Non-Patent Citations (1)
Title |
---|
OTHMAN A ETC: ""A novel approach for 3D head segmentation and facial feature points extraction"", 《PROCEEDINGS OF THE 2013 INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING AND SOFTWARE APPLICATIONS (ICEESA)》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107221025A (en) * | 2017-05-31 | 2017-09-29 | 天津大学 | A kind of synchronous system and method for obtaining body surface three-dimensional colour point clouds model |
CN107221025B (en) * | 2017-05-31 | 2020-01-03 | 天津大学 | System and method for synchronously acquiring three-dimensional color point cloud model of object surface |
CN111031848A (en) * | 2017-08-15 | 2020-04-17 | 真发有限责任公司 | Method and system for generating 3D digital models for use in wig manufacture |
CN111031848B (en) * | 2017-08-15 | 2023-09-01 | 真发有限责任公司 | Method and system for generating 3D digital model for use in wig manufacture |
CN107621880A (en) * | 2017-09-29 | 2018-01-23 | 南京邮电大学 | A kind of robot wheel chair interaction control method based on improvement head orientation estimation method |
CN111295664A (en) * | 2018-02-28 | 2020-06-16 | 华为技术有限公司 | Method and device for positioning hairline contour and computer readable storage medium |
CN111295664B (en) * | 2018-02-28 | 2022-06-07 | 荣耀终端有限公司 | Method and device for positioning hairline contour and computer readable storage medium |
CN109559288A (en) * | 2018-11-30 | 2019-04-02 | 深圳市脸萌科技有限公司 | Image processing method, device, electronic equipment and computer readable storage medium |
CN117389676A (en) * | 2023-12-13 | 2024-01-12 | 成都白泽智汇科技有限公司 | Intelligent hairstyle adaptive display method based on display interface |
CN117389676B (en) * | 2023-12-13 | 2024-02-13 | 成都白泽智汇科技有限公司 | Intelligent hairstyle adaptive display method based on display interface |
Also Published As
Publication number | Publication date |
---|---|
CN106650654B (en) | 2019-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106650654B (en) | A kind of three-dimensional hair line extracting method based on human body head colour point clouds model | |
US11735306B2 (en) | Method, system and computer readable storage media for creating three-dimensional dental restorations from two dimensional sketches | |
CN103208133B (en) | The method of adjustment that in a kind of image, face is fat or thin | |
CN101339670B (en) | Computer auxiliary three-dimensional craniofacial rejuvenation method | |
CN108875633A (en) | Expression detection and expression driving method, device and system and storage medium | |
CN103606190B (en) | Method for automatically converting single face front photo into three-dimensional (3D) face model | |
CN101814196B (en) | Method for designing three-dimensional cartoon toys based on pictures | |
CN101324961B (en) | Human face portion three-dimensional picture pasting method in computer virtual world | |
WO2017029488A2 (en) | Methods of generating personalized 3d head models or 3d body models | |
CN105913416A (en) | Method for automatically segmenting three-dimensional human face model area | |
CN109377557A (en) | Real-time three-dimensional facial reconstruction method based on single frames facial image | |
CN106920277A (en) | Simulation beauty and shaping effect visualizes the method and system of online scope of freedom carving | |
CN111833236B (en) | Method and device for generating three-dimensional face model for simulating user | |
US9202312B1 (en) | Hair simulation method | |
CN103324860A (en) | Intelligent integrated costume designing and fitting system | |
CN108171789A (en) | A kind of virtual image generation method and system | |
CN101853523A (en) | Method for adopting rough drawings to establish three-dimensional human face molds | |
CN109284778A (en) | Face face value calculating method, computing device and electronic equipment | |
CN108564619A (en) | A kind of sense of reality three-dimensional facial reconstruction method based on two photos | |
CN107343148A (en) | Image completion method, apparatus and terminal | |
Zhang et al. | Styleavatar3d: Leveraging image-text diffusion models for high-fidelity 3d avatar generation | |
CN111179411A (en) | Visual facial cosmetology plastic simulation method, system and equipment based on social platform | |
CN108288299A (en) | A kind of method and system of expression data driving three-dimensional image expression | |
Liu et al. | Interactive modeling of trees using VR devices | |
CN109064547A (en) | A kind of single image hair method for reconstructing based on data-driven |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191122 Termination date: 20201215 |
|
CF01 | Termination of patent right due to non-payment of annual fee |