CN104463938A - Three-dimensional virtual make-up trial method and device - Google Patents
Three-dimensional virtual make-up trial method and device Download PDFInfo
- Publication number
- CN104463938A CN104463938A CN201410689673.2A CN201410689673A CN104463938A CN 104463938 A CN104463938 A CN 104463938A CN 201410689673 A CN201410689673 A CN 201410689673A CN 104463938 A CN104463938 A CN 104463938A
- Authority
- CN
- China
- Prior art keywords
- grid model
- model
- unique point
- details grid
- details
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Processing Or Creating Images (AREA)
Abstract
The inventor provides a three-dimensional virtual make-up trial method in order to solve a virtual make-up trial problem. The method includes the following steps that an original person image, a standard model and a detail grid model of the standard model are obtained, the detail grid model of the standard model is built according to information of all characteristic points of the standard model, and the detail grid model of the standard model corresponds to the characteristic points one to one; the characteristic points of the standard model and the detail grid model of the standard model are subjected to aligning amendment processing according to information of characteristic points of the original person image, and a person image model and a detail grid model of the person image model are obtained; a rendering instruction is acquired, and rendering processing is performed on the person image model or the detail grid model of the person image model according to the rendering instruction. The invention further provides a corresponding three-dimensional virtual make-up trial device. The three-dimensional virtual make-up trial method and device are high in effect reality sense, information of a certain depth can be provided, and deformation of maps in the skinned animation process is avoided.
Description
Technical field
The present invention relates to Computer Image Processing field, particularly a kind of method and apparatus of three-dimensional examination adornment.
Background technology
Cosmetic is important step indispensable in women's daily life, the hot issue therefore how selecting oneself cosmetics applicable to become female group gradually to pay close attention to.In recent years, along with the development of Computer Simulation, the method utilizing image processing techniques to carry out virtual cosmetic starts to appear in the visual field of people, this examination complete outfit for newlyweds method substantially increases the experience of user compared to traditional actual examination adornment, save the consumption of time and resource, be with a wide range of applications.
The analog virtual examination cosmetic method of a kind of noncontact of the prior art is by analyzing the image gathered, the face-image of examination adornment personnel is detected according to the unique point of face, choose the suitable image comprising face as examination adornment image, then based on the process parameter of virtual cosmetic, image procossing is carried out to examination adornment image according to practical operation and realize virtual adornment; The information that another method for virtual cosmetic extracts cosmetic region from cosmetic template generates the reference position information about facial model, then utilize above-mentioned information to arrange the region that application is made up, finally the application of cosmetic template is realized virtual cosmetic on a predetermined region.Also having a kind of virtual examination cosmetic method based on Facial Feature Analysis, based on utilizing face full face to carry out the analysis of face position, shape facility as input, in the original full face that is then added to by dressing effect, realizing the process of virtual cosmetic.
But virtual examination cosmetic method of the prior art is the virtual make-up technique of conventional two-dimensional and is applied in three-dimensional scenic, there is following Railway Project:
1, UV pinup picture is adopted to carry out the mapping of superficial makings in three-dimensional model, due to as less in details proportions in pinup picture such as eyebrow, eye shadow, eyelashes, U.S. pupils in model, therefore often lose a large amount of detailed information, cause the sense of reality of detail textures after mapping lower.
2, virtual cosmetic based on two dimensional image is difficult to realize being equal to three-dimensional simulated effect of making up, because model has depth information in three-dimensional scenic, therefore when rotating three-dimensional head model, the lateral effect after cosmetic should be able to be observed, as eyebrow, eyelashes etc. by side.
3, in actual applications, the faceform in three-dimensional scenic needs to perform some FA Facial Animation usually, and as smile, nictation etc., traditional pinup picture mapping method can will cause the distortion of pinup picture due to operations such as the stretching of picture, contractions when carrying out Skinned Animation.
Summary of the invention
For this reason, need to provide a kind of sense of reality higher, can provide certain depth information, unlikely in Skinned Animation process, cause pinup picture to be out of shape three-dimensional examination cosmetic method and device.
For achieving the above object, inventor provide a kind of three-dimensional examination cosmetic method, comprise the steps:
Obtain the details grid model of primitive man picture, master pattern and master pattern, the details grid model of described master pattern according to each characteristic point information structure of described master pattern, and with described unique point one_to_one corresponding and position consistency;
The details grid model of characteristic point information to the unique point of master pattern and master pattern according to primitive man's picture makes alignment correcting process, obtains dummy and details grid model thereof;
Obtain render instruction, and according to described render instruction, process is played up to described dummy or its details grid model.
Further, in described three-dimensional examination cosmetic method, after step " obtains the details grid model of primitive man's picture, master pattern and master pattern ", also step is comprised:
Master pattern and the corresponding skeleton point in its details grid model are done to the binding process of same weight.
Further, in described three-dimensional examination cosmetic method, before step " obtains render instruction, and plays up process according to described render instruction to described dummy or its details grid model ", also step is comprised:
Obtain the pinup picture of described dummy and details grid model thereof;
Obtain color density instruction, and regulate and control the transparency of the pinup picture of described details grid model according to described color density instruction;
Mix the pinup picture of described details grid model and the pinup picture of described dummy.
Further, in described three-dimensional examination cosmetic method, step " regulates and controls the transparency of the pinup picture of described details grid model " and specifically comprises according to described color density instruction:
Regulate and control the Alpha passage numerical value of RGBA image in the pinup picture of described details grid model.
Further, in described three-dimensional examination cosmetic method, described step " is played up process according to described render instruction to described dummy or its details grid model " and is specifically comprised:
When object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or
According to the transparent nature determination rendering order of object to be rendered.
Further, in described three-dimensional examination cosmetic method, step " the details grid model of characteristic point information to the unique point of master pattern and master pattern according to primitive man's picture makes alignment correcting process " specifically comprises:
Unique point on described details grid model is changed from the model space and is projected to screen plane;
Unique point in screen space is moved to the position of primitive man as upper character pair point;
Unique point on details grid model after translation is converted back the model space.
Further, in described three-dimensional examination cosmetic method, the unique point on described details grid model " is changed from the model space and is projected to screen plane " and specifically comprising by step:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
The transformation matrix that unique point on details grid model after translation " is converted back the model space " and uses by step is (Model*View*Projection)
-1.
Inventor additionally provides a kind of three-dimensional examination adornment device, comprises input block, unique point alignment unit and rendering unit;
Described input block is for obtaining the details grid model of primitive man's picture, master pattern and master pattern, and the details grid model of described master pattern builds according to each characteristic point information of described master pattern, and with described unique point one_to_one corresponding and position consistency;
Described unique point alignment unit is used for making alignment correcting process according to the details grid model of characteristic point information to the unique point of master pattern and master pattern of primitive man's picture, obtains dummy and details grid model thereof;
Described rendering unit for obtaining render instruction, and plays up process according to described render instruction to described dummy or its details grid model.
Further, in described three-dimensional examination adornment device, bone binding unit is also comprised, for doing the binding process of same weight to master pattern and the corresponding skeleton point in its details grid model.
Further, in described three-dimensional examination adornment device, also comprise color density regulation and control unit, described color density regulation and control unit is used for:
Obtain the pinup picture of described dummy and details grid model thereof;
Obtain color density instruction, and regulate and control the transparency of the pinup picture of described details grid model according to described color density instruction;
Mix the pinup picture of described details grid model and the pinup picture of described dummy.
Further, in described three-dimensional examination adornment device, described in described color density regulation and control unit regulating, the transparency of the pinup picture of details grid model specifically comprises:
Regulate and control the Alpha passage numerical value of RGBA image in the pinup picture of described details grid model.
Further, in described three-dimensional examination adornment device, when described rendering unit plays up process according to described render instruction to described dummy or its details grid model, when object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or
According to the transparent nature determination rendering order of object to be rendered.
Further, in described three-dimensional examination adornment device, described unique point alignment unit specifically comprises according to the details grid model do alignment correcting process of the characteristic point information of primitive man's picture to the unique point of master pattern and master pattern:
Unique point on described details grid model is changed from the model space and is projected to screen plane;
Unique point in screen space is moved to the position of primitive man as upper character pair point;
Unique point on details grid model after translation is converted back the model space.
Further, in described three-dimensional examination adornment device, the unique point on described details grid model is changed from the model space and is projected to screen plane and specifically comprises by described unique point alignment unit:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
It is (Model*View*Projection) that unique point on details grid model after translation is converted back the transformation matrix that the model space uses by described unique point alignment unit
-1.
Be different from prior art, technique scheme carries out virtual adornment by setting up in three dimensions in the model of matching face and detail model, can observe the dressing effect of face according to the needs of user from all directions; And based on each details grid model of the face set up in three dimensions, can show meticulousr dressing effect, and the pinup picture between each face detail is changed and the adjustment of effect is all independently carried out, the efficiency of operation is higher.In addition, in three dimensions, because faceform and face detail model adopt identical skeleton point weight binding, therefore can represent real face action by Skinned Animation, thus enable the faceform after cosmetic realize representing of expression action.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of three-dimensional examination cosmetic method described in an embodiment of the present invention;
Fig. 2 is the structural representation of three-dimensional examination adornment device described in an embodiment of the present invention.
Description of reference numerals:
1-input block
2-unique point alignment unit
3-rendering unit
4-bone binding unit
5-color density regulation and control unit
Embodiment
By describe in detail technical scheme technology contents, structural attitude, realized object and effect, coordinate accompanying drawing to be explained in detail below in conjunction with specific embodiment.
Referring to Fig. 1, is the process flow diagram of three-dimensional examination cosmetic method described in an embodiment of the present invention; Described method comprises the steps:
The details grid model of S1, acquisition primitive man picture, master pattern and master pattern;
Wherein, the details grid model of described master pattern builds according to each characteristic point information of described master pattern, and with described unique point one_to_one corresponding and position consistency.
Specifically, primitive man's picture is the planar picture belonging to individual subscriber of user's input usually.Master pattern is three-dimensional head model.Some preferred embodiment in, described master pattern is the master pattern mated as ethnic group with described primitive man.That is, first analyze according to the characteristic information of different ethnic group, set up different master patterns, such as, for Asian (yellow), by collecting a large amount of Asian face, the information such as its head dummy, contour shape, face comprehensively being analyzed and extracting feature and sets up Asian's head master pattern.The master pattern of other ethnic groups in like manner.Then, according to the kind of the ethnic group confirmed standard model of primitive man's picture, for follow-up matching.
Described details grid model sets up based on the characteristic point information of master pattern.This concept of unique point, mainly refers in Face detection and recognition technology, for calibrating face shape of face, eyebrow, eyes, nose, face etc. appearance being had to the point of prominent feature meaning, being called unique point.Based on different face calibration technical research results, have different unique point models can for selecting, what present embodiment adopted be the unique point system marking off 7 significant features (face exterior contour, left and right eyebrow, right and left eyes, nose, mouth) according to face general knowledge.In other embodiments, other unique point scaling method of the prior art can also be adopted.The unique point of details grid model and master pattern has one-to-one relationship, such as when setting up the mesh details model of facial eyebrow, first need the characteristic point information extracting eyebrow position in standard faces model, the position that it is identical is constructed the details grid model of eyebrow of same shape, size.The grid model at other details positions of face can be constructed according to similar method, as built the details grid model of eyelashes according to the characteristic point information of eye contour, according to the details grid model of contour feature point information architecture eye shadow on eyebrow bottom profiled and eyes, determine facial rouge position according to lower jaw portion profile and nasal contours unique point, thus set up the details grid model of rouge.
S2, master pattern and the corresponding skeleton point in its details grid model are done to the binding process of same weight.
The process of this step is based on such intention: when carrying out the representing of three-dimensional animation, in order to ensure that model does not occur the situations such as torsional deformation when carrying out Skinned Animation, need on skeleton point, bind certain weighted value.Due to the expansion that details grid model is master pattern, therefore in order to make details grid model keep when Skinned Animation carries out and the Movement consistency of master pattern, corresponding skeleton point in master pattern is needed on details grid model to carry out the binding of same weight.Skeleton point then refers to that in unique point, those will produce the point of considerable influence in grid deformation to facial contour and face, the method obtaining bone key point normally carries out Deformation Experiments to face wire frame model, analyze the impact of each feature point pairs grid deformation, what meet default deformation quantity condition is confirmed as skeleton point.
S3, make alignment correcting process according to the characteristic point information of the primitive man's picture details grid model to the unique point of master pattern and master pattern, obtain dummy and details grid model thereof;
Particularly, this step comprises again as follows step by step:
S31, the unique point on described details grid model changed from the model space and is projected to screen plane;
S32, the unique point in screen space is moved to the position of primitive man as upper character pair point;
S33, the unique point on the details grid model after translation is converted back the model space.
Wherein, " unique point on described details grid model is changed from the model space and is projected to screen plane " described in step S31 and specifically comprise again:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
The transformation matrix " unique point on the details grid model after translation being converted back the model space " described in step S33 and use is (Model*View*Projection)
-1.
Unique point alignment described in this step, mainly in actual modeling process, the photo (i.e. primitive man's picture) provided according to user carries out personalized head modeling, and to make model more fit user's practical situation, energy simulate the face characteristic of user personalizedly.
S4, regulation and control pinup picture color density;
Particularly, this step also comprises as follows step by step:
S41, obtain the pinup picture of described dummy and details grid model thereof;
S42, the instruction of acquisition color density, and the transparency of the pinup picture of described details grid model is regulated and controled according to described color density instruction; Concrete mode is, regulates and controls the Alpha passage numerical value of RGBA image in the pinup picture of described details grid model.
S43, mix the pinup picture of described details grid model and the pinup picture of described dummy.
In this step, in order to simulate heavy make-up and light make-up effect better, realize the real-time, tunable of color make-up color density in virtual examination adornment process, need the pinup picture of details grid model and the pinup picture of dummy to carry out mixing to a certain degree, the scheme taked is utilize the Alpha passage of RGBA image to adjust the transparency of details grid model pinup picture, it is made to present the color of variable concentrations, then by realizing real dressing effect with mixing of bottom pinup picture.
S5, acquisition render instruction, and according to described render instruction, process is played up to described dummy or its details grid model.
Particularly, in this step, when object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or according to the transparent nature determination rendering order of object to be rendered.
During owing to carrying out the playing up of multiple details grid model, based on different dressing effects, part details grid model may overlap with dummy (as eye shadow, lip gloss, rouge etc.), and part then may be spliced on dummy (as eyelashes, eyebrow etc.).Rendering order may affect the display effect of some details grid model.So, in order to enable, cosmetic details is clear to be represented truly, the principle that the rendering order that present embodiment defines grid model will be followed, one is play up from the inside to surface, namely first carry out playing up of internal layer object, then carry out playing up of outer object, such as, when playing up the details grid model of rouge, playing up of advanced row dummy, then carry out playing up of rouge details grid model; And when existing for the details grid model of U.S. pupil, eyelashes, playing up of advanced row dummy, then carries out playing up of U.S. pupil details grid model, finally plays up the details grid model of eyelashes simultaneously.Principle be second determine rendering order according to the whether transparent of object to be rendered, namely first play up opaque object, then the object of rendering transparent.
Technique scheme carries out virtual adornment by setting up in three dimensions in the model of matching face and detail model, can observe the dressing effect of face according to the needs of user from all directions; And based on each details grid model of the face set up in three dimensions, can show meticulousr dressing effect, and the pinup picture between each face detail is changed and the adjustment of effect is all independently carried out, the efficiency of operation is higher.In addition, in three dimensions, because faceform and face detail model adopt identical bone weight binding, therefore can represent real face action by Skinned Animation, thus enable the faceform after cosmetic realize representing of expression action.
Refer to Fig. 2, be the structural representation of three-dimensional examination adornment device described in an embodiment of the present invention, described device comprises input block 1, unique point alignment unit 2 and rendering unit 3;
Described input block 1 is for obtaining the details grid model of primitive man's picture, master pattern and master pattern, and the details grid model of described master pattern builds according to each characteristic point information of described master pattern, and with described unique point one_to_one corresponding and position consistency.
Specifically, primitive man's picture is the planar picture belonging to individual subscriber of user's input usually.Master pattern is three-dimensional head model.Some preferred embodiment in, described master pattern is the master pattern mated as ethnic group with described primitive man.That is, first analyze according to the characteristic information of different ethnic group, set up different master patterns, such as, for Asian (yellow), by collecting a large amount of Asian face, the information such as its head dummy, contour shape, face comprehensively being analyzed and extracting feature and sets up Asian's head master pattern.The master pattern of other ethnic groups in like manner.Then, according to the kind of the ethnic group confirmed standard model of primitive man's picture, for follow-up matching.
Described details grid model sets up based on the characteristic point information of master pattern.This concept of unique point, mainly refers in Face detection and recognition technology, for calibrating face shape of face, eyebrow, eyes, nose, face etc. appearance being had to the point of prominent feature meaning, being called unique point.Based on different face calibration technical research results, have different unique point models can for selecting, what present embodiment adopted be the unique point system marking off 7 significant features (face exterior contour, left and right eyebrow, right and left eyes, nose, mouth) according to face general knowledge.In other embodiments, other unique point scaling method of the prior art can also be adopted.The unique point of details grid model and master pattern has one-to-one relationship, such as when setting up the mesh details model of facial eyebrow, first need the characteristic point information extracting eyebrow position in standard faces model, the position that it is identical is constructed the details grid model of eyebrow of same shape, size.The grid model at other details positions of face can be constructed according to similar method, as built the details grid model of eyelashes according to the characteristic point information of eye contour, according to the details grid model of contour feature point information architecture eye shadow on eyebrow bottom profiled and eyes, determine facial rouge position according to lower jaw portion profile and nasal contours unique point, thus set up the details grid model of rouge.
Described unique point alignment unit 2 makes alignment correcting process for the details grid model of characteristic point information to the unique point of master pattern and master pattern according to primitive man's picture, obtains dummy and details grid model thereof;
Further, described unique point alignment unit 2 specifically comprises according to the details grid model do alignment correcting process of the characteristic point information of primitive man's picture to the unique point of master pattern and master pattern:
Unique point on described details grid model is changed from the model space and is projected to screen plane;
Unique point in screen space is moved to the position of primitive man as upper character pair point;
Unique point on details grid model after translation is converted back the model space.
Further, the unique point on described details grid model is changed from the model space and is projected to screen plane and specifically comprises by described unique point alignment unit 2:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
It is (Model*View*Projection) that unique point on details grid model after translation is converted back the transformation matrix that the model space uses by described unique point alignment unit 2
-1.
The unique point registration process that unique point alignment unit 2 is done, mainly in actual modeling process, personalized head modeling is carried out according to the photo (i.e. primitive man's picture) that user provides, to make model more fit user's practical situation, the face characteristic of user can be simulated personalizedly.
Described rendering unit 3 for obtaining render instruction, and plays up process according to described render instruction to described dummy or its details grid model.
Further, when described rendering unit 3 plays up process according to described render instruction to described dummy or its details grid model, when object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or according to the transparent nature determination rendering order of object to be rendered.
During owing to carrying out the playing up of multiple details grid model, based on different dressing effects, part details grid model may overlap with dummy (as eye shadow, lip gloss, rouge etc.), and part then may be spliced on dummy (as eyelashes, eyebrow etc.).Rendering order may affect the display effect of some details grid model.So, in order to enable, cosmetic details is clear to be represented truly, the principle that the rendering order that present embodiment defines grid model will be followed, one is play up from the inside to surface, namely first carry out playing up of internal layer object, then carry out playing up of outer object, such as, when playing up the details grid model of rouge, playing up of advanced row dummy, then carry out playing up of rouge details grid model; And when existing for the details grid model of U.S. pupil, eyelashes, playing up of advanced row dummy, then carries out playing up of U.S. pupil details grid model, finally plays up the details grid model of eyelashes simultaneously.Principle be second determine rendering order according to the whether transparent of object to be rendered, namely first play up opaque object, then the object of rendering transparent.
Preferably, in described three-dimensional examination adornment device, bone binding unit 4 is also comprised, for doing the binding process of same weight to master pattern and the corresponding skeleton point in its details grid model.The function that realizes of bone binding unit 4 is based on such intention: when carrying out the representing of three-dimensional animation, in order to ensure that model does not occur the situations such as torsional deformation when carrying out Skinned Animation, need on bone, bind certain weighted value.Due to the expansion that details grid model is master pattern, therefore in order to make details grid model keep when Skinned Animation carries out and the Movement consistency of master pattern, corresponding skeleton point in master pattern is needed on details grid model to carry out the binding of same weight.Skeleton point refers to that in unique point, those will produce the point of considerable influence in grid deformation to facial contour and face, the method obtaining bone key point normally carries out Deformation Experiments to face wire frame model, analyze the impact of each feature point pairs grid deformation, what meet default deformation quantity condition is confirmed as skeleton point.
Preferably, in described three-dimensional examination adornment device, also comprise color density regulation and control unit 5, described color density regulation and control unit 5 for:
Obtain the pinup picture of described dummy and details grid model thereof;
Obtain color density instruction, and regulate and control the transparency of the pinup picture of described details grid model according to described color density instruction;
Mix the pinup picture of described details grid model and the pinup picture of described dummy.
Further, the transparency that described color density regulation and control unit 5 regulates and controls the pinup picture of described details grid model specifically comprises: the Alpha passage numerical value regulating and controlling RGBA image in the pinup picture of described details grid model.
The function that color density regulation and control unit 5 realizes is mainly in order to simulate heavy make-up and light make-up effect better, realize the real-time, tunable of color make-up color density in virtual examination adornment process, therefore, need the pinup picture of details grid model and the pinup picture of dummy to carry out mixing to a certain degree, the scheme taked is utilize the Alpha passage of RGBA image to adjust the transparency of details grid model pinup picture, it is made to present the color of variable concentrations, then by realizing real dressing effect with mixing of bottom pinup picture.In other embodiments, the technical scheme realizing adjustment pinup picture mixed transparent degree can also be adopted in other prior aries.
Technique scheme carries out virtual adornment by setting up in three dimensions in the model of matching face and detail model, can observe the dressing effect of face according to the needs of user from all directions; And based on each details grid model of the face set up in three dimensions, can show meticulousr dressing effect, and the pinup picture between each face detail is changed and the adjustment of effect is all independently carried out, the efficiency of operation is higher.In addition, in three dimensions, because faceform and face detail model adopt identical bone weight binding, therefore can represent real face action by Skinned Animation, thus enable the faceform after cosmetic realize representing of expression action.
It should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or terminal device and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or terminal device.When not more restrictions, the key element limited by statement " comprising ... " or " comprising ... ", and be not precluded within process, method, article or the terminal device comprising described key element and also there is other key element.In addition, in this article, " be greater than ", " being less than ", " exceeding " etc. be interpreted as and do not comprise this number; " more than ", " below ", " within " etc. be interpreted as and comprise this number.
Those skilled in the art should understand, the various embodiments described above can be provided as method, device or computer program.These embodiments can adopt the form of complete hardware embodiment, completely software implementation or the embodiment in conjunction with software and hardware aspect.The hardware that all or part of step in the method that the various embodiments described above relate to can carry out instruction relevant by program has come, described program can be stored in the storage medium that computer equipment can read, for performing all or part of step described in the various embodiments described above method.Described computer equipment, includes but not limited to: personal computer, server, multi-purpose computer, special purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, intelligent home device, wearable intelligent equipment, vehicle intelligent equipment etc.; Described storage medium, includes but not limited to: the storage of RAM, ROM, magnetic disc, tape, CD, flash memory, USB flash disk, portable hard drive, storage card, memory stick, the webserver, network cloud storage etc.
The various embodiments described above describe with reference to the process flow diagram of method, equipment (system) and computer program according to embodiment and/or block scheme.Should understand can by the combination of the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or square frame.These computer program instructions can being provided to the processor of computer equipment to produce a machine, making the instruction performed by the processor of computer equipment produce device for realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be stored in can in the computer equipment readable memory that works in a specific way of vectoring computer equipment, the instruction making to be stored in this computer equipment readable memory produces the manufacture comprising command device, and this command device realizes the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
These computer program instructions also can be loaded on computer equipment, make to perform sequence of operations step on a computing device to produce computer implemented process, thus the instruction performed on a computing device is provided for the step realizing the function of specifying in process flow diagram flow process or multiple flow process and/or block scheme square frame or multiple square frame.
Although be described the various embodiments described above; but those skilled in the art are once obtain the basic creative concept of cicada; then can make other change and amendment to these embodiments; so the foregoing is only embodiments of the invention; not thereby scope of patent protection of the present invention is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in other relevant technical fields, be all in like manner included within scope of patent protection of the present invention.
Claims (14)
1. a three-dimensional examination cosmetic method, comprises the steps:
Obtain the details grid model of primitive man picture, master pattern and master pattern, the details grid model of described master pattern according to each characteristic point information structure of described master pattern, and with described unique point one_to_one corresponding and position consistency;
The details grid model of characteristic point information to the unique point of master pattern and master pattern according to primitive man's picture makes alignment correcting process, obtains dummy and details grid model thereof;
Obtain render instruction, and according to described render instruction, process is played up to described dummy or its details grid model.
2., in three-dimensional examination cosmetic method as claimed in claim 1, after step " obtains the details grid model of primitive man's picture, master pattern and master pattern ", also comprise step:
Master pattern and the corresponding skeleton point in its details grid model are done to the binding process of same weight.
3., in three-dimensional examination cosmetic method as claimed in claim 1 or 2, before step " obtains render instruction, and plays up process according to described render instruction to described dummy or its details grid model ", also comprise step:
Obtain the pinup picture of described dummy and details grid model thereof;
Obtain color density instruction, and regulate and control the transparency of the pinup picture of described details grid model according to described color density instruction;
Mix the pinup picture of described details grid model and the pinup picture of described dummy.
4., in three-dimensional examination cosmetic method as claimed in claim 3, step " regulates and controls the transparency of the pinup picture of described details grid model " and specifically comprises according to described color density instruction:
Regulate and control the Alpha passage numerical value of RGBA image in the pinup picture of described details grid model.
5., in three-dimensional examination cosmetic method as claimed in claim 1 or 2, described step " is played up process according to described render instruction to described dummy or its details grid model " and is specifically comprised:
When object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or
According to the transparent nature determination rendering order of object to be rendered.
6., in three-dimensional examination cosmetic method as claimed in claim 1 or 2, step " the details grid model of characteristic point information to the unique point of master pattern and master pattern according to primitive man's picture makes alignment correcting process " specifically comprises:
Unique point on described details grid model is changed from the model space and is projected to screen plane;
Unique point in screen space is moved to the position of primitive man as upper character pair point;
Unique point on details grid model after translation is converted back the model space.
7., in three-dimensional examination cosmetic method as claimed in claim 6, the unique point on described details grid model " is changed from the model space and is projected to screen plane " and specifically comprising by step:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
The transformation matrix that unique point on details grid model after translation " is converted back the model space " and uses by step is (Model*View*Projection)
-1.
8. a three-dimensional examination adornment device, comprises input block, unique point alignment unit and rendering unit;
Described input block is for obtaining the details grid model of primitive man's picture, master pattern and master pattern, and the details grid model of described master pattern builds according to each characteristic point information of described master pattern, and with described unique point one_to_one corresponding and position consistency;
Described unique point alignment unit is used for making alignment correcting process according to the details grid model of characteristic point information to the unique point of master pattern and master pattern of primitive man's picture, obtains dummy and details grid model thereof;
Described rendering unit for obtaining render instruction, and plays up process according to described render instruction to described dummy or its details grid model.
9., in three-dimensional examination adornment device as claimed in claim 8, also comprise bone binding unit, for doing the binding process of same weight to master pattern and the corresponding skeleton point in its details grid model.
10. three-dimensional tries in adornment device as claimed in claim 8 or 9, also comprises color density regulation and control unit, and described color density regulation and control unit is used for:
Obtain the pinup picture of described dummy and details grid model thereof;
Obtain color density instruction, and regulate and control the transparency of the pinup picture of described details grid model according to described color density instruction;
Mix the pinup picture of described details grid model and the pinup picture of described dummy.
In 11. three-dimensional examination adornment devices as claimed in claim 10, described in described color density regulation and control unit regulating, the transparency of the pinup picture of details grid model specifically comprises:
Regulate and control the Alpha passage numerical value of RGBA image in the pinup picture of described details grid model.
In 12. three-dimensional examination adornment devices as claimed in claim 8 or 9, when described rendering unit plays up process according to described render instruction to described dummy or its details grid model, when object to be rendered is no less than two, according to hierarchical relationship determination rendering order inside and outside object to be rendered; Or
According to the transparent nature determination rendering order of object to be rendered.
In 13. three-dimensional examination adornment devices as claimed in claim 8 or 9, described unique point alignment unit specifically comprises according to the details grid model do alignment correcting process of the characteristic point information of primitive man's picture to the unique point of master pattern and master pattern:
Unique point on described details grid model is changed from the model space and is projected to screen plane;
Unique point in screen space is moved to the position of primitive man as upper character pair point;
Unique point on details grid model after translation is converted back the model space.
In 14. three-dimensional examination adornment devices as claimed in claim 13, the unique point on described details grid model is changed from the model space and is projected to screen plane and specifically comprises by described unique point alignment unit:
Utilize model matrix Model that the unique point on described details grid model is transformed into world coordinate system from model space coordinate system;
Observation matrix View is utilized further described unique point to be transformed into visual coordinate system from world coordinate system;
Projection matrix Projection is utilized further described unique point to be projeced into screen plane by rectangular projection; And
It is (Model*View*Projection) that unique point on details grid model after translation is converted back the transformation matrix that the model space uses by described unique point alignment unit
-1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410689673.2A CN104463938A (en) | 2014-11-25 | 2014-11-25 | Three-dimensional virtual make-up trial method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410689673.2A CN104463938A (en) | 2014-11-25 | 2014-11-25 | Three-dimensional virtual make-up trial method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104463938A true CN104463938A (en) | 2015-03-25 |
Family
ID=52909920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410689673.2A Pending CN104463938A (en) | 2014-11-25 | 2014-11-25 | Three-dimensional virtual make-up trial method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104463938A (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127830A (en) * | 2016-09-06 | 2016-11-16 | 成都通甲优博科技有限责任公司 | The making of a kind of virtual beauty pupil pupil sheet and display packing |
| CN106791775A (en) * | 2016-11-15 | 2017-05-31 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN106909538A (en) * | 2015-12-21 | 2017-06-30 | 腾讯科技（北京）有限公司 | Using effect methods of exhibiting and device |
| CN107220960A (en) * | 2017-05-27 | 2017-09-29 | 无限极（中国）有限公司 | One kind examination cosmetic method, system and equipment |
| CN107481310A (en) * | 2017-08-14 | 2017-12-15 | 迈吉客科技（北京）有限公司 | A kind of image rendering method and system |
| CN107705240A (en) * | 2016-08-08 | 2018-02-16 | 阿里巴巴集团控股有限公司 | Virtual examination cosmetic method, device and electronic equipment |
| CN108022285A (en) * | 2017-11-30 | 2018-05-11 | 杭州电魂网络科技股份有限公司 | Map rendering intent and device |
| CN108280803A (en) * | 2018-01-22 | 2018-07-13 | 盎锐（上海）信息科技有限公司 | Image generating method and device based on 3D imagings |
| CN108364355A (en) * | 2018-02-12 | 2018-08-03 | 成都睿码科技有限责任公司 | A kind of AR rendering intents of fitting facial expression |
| CN108509846A (en) * | 2018-02-09 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
| CN108664884A (en) * | 2018-03-17 | 2018-10-16 | 广州帕克西软件开发有限公司 | A kind of virtually examination cosmetic method and device |
| CN108805090A (en) * | 2018-06-14 | 2018-11-13 | 广东工业大学 | A kind of virtual examination cosmetic method based on Plane Gridding Model |
| CN109389682A (en) * | 2017-08-09 | 2019-02-26 | 上海影子智能科技有限公司 | A kind of three-dimensional face model automatic adjusting method |
| CN109671142A (en) * | 2018-11-23 | 2019-04-23 | 南京图玩智能科技有限公司 | A kind of intelligence makeups method and intelligent makeups mirror |
| CN109993689A (en) * | 2019-03-14 | 2019-07-09 | 珠海天燕科技有限公司 | A kind of makeups method and apparatus |
| CN110111417A (en) * | 2019-05-15 | 2019-08-09 | 浙江商汤科技开发有限公司 | Generation method, device and the equipment of three-dimensional partial body's model |
| CN110120053A (en) * | 2019-05-15 | 2019-08-13 | 北京市商汤科技开发有限公司 | Face's dressing processing method, device and equipment |
| CN110136272A (en) * | 2018-02-09 | 2019-08-16 | 英属开曼群岛商玩美股份有限公司 | For the system and method to remote user's virtual application color make-up effect |
| CN110264566A (en) * | 2019-06-03 | 2019-09-20 | 杭州小伊智能科技有限公司 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
| CN113643397A (en) * | 2021-08-05 | 2021-11-12 | 广州帕克西软件开发有限公司 | Virtual makeup trying method based on face recognition |
| CN113780047A (en) * | 2021-01-11 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Virtual makeup trying method and device, electronic equipment and storage medium |
| CN113838189A (en) * | 2021-09-13 | 2021-12-24 | 厦门美图之家科技有限公司 | Eyelash rendering method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222363A (en) * | 2011-07-19 | 2011-10-19 | 杭州实时数码科技有限公司 | Method for fast constructing high-accuracy personalized face model on basis of facial images |
| CN103268623A (en) * | 2013-06-18 | 2013-08-28 | 西安电子科技大学 | Static human face expression synthesizing method based on frequency domain analysis |
| CN103606190A (en) * | 2013-12-06 | 2014-02-26 | 上海明穆电子科技有限公司 | Method for automatically converting single face front photo into three-dimensional (3D) face model |
| CN103646416A (en) * | 2013-12-18 | 2014-03-19 | 中国科学院计算技术研究所 | Three-dimensional cartoon face texture generation method and device |
-
2014
- 2014-11-25 CN CN201410689673.2A patent/CN104463938A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222363A (en) * | 2011-07-19 | 2011-10-19 | 杭州实时数码科技有限公司 | Method for fast constructing high-accuracy personalized face model on basis of facial images |
| CN103268623A (en) * | 2013-06-18 | 2013-08-28 | 西安电子科技大学 | Static human face expression synthesizing method based on frequency domain analysis |
| CN103606190A (en) * | 2013-12-06 | 2014-02-26 | 上海明穆电子科技有限公司 | Method for automatically converting single face front photo into three-dimensional (3D) face model |
| CN103646416A (en) * | 2013-12-18 | 2014-03-19 | 中国科学院计算技术研究所 | Three-dimensional cartoon face texture generation method and device |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909538A (en) * | 2015-12-21 | 2017-06-30 | 腾讯科技（北京）有限公司 | Using effect methods of exhibiting and device |
| CN107705240A (en) * | 2016-08-08 | 2018-02-16 | 阿里巴巴集团控股有限公司 | Virtual examination cosmetic method, device and electronic equipment |
| CN107705240B (en) * | 2016-08-08 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Virtual makeup trial method and device and electronic equipment |
| CN106127830A (en) * | 2016-09-06 | 2016-11-16 | 成都通甲优博科技有限责任公司 | The making of a kind of virtual beauty pupil pupil sheet and display packing |
| CN106791775A (en) * | 2016-11-15 | 2017-05-31 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN107220960A (en) * | 2017-05-27 | 2017-09-29 | 无限极（中国）有限公司 | One kind examination cosmetic method, system and equipment |
| CN109389682A (en) * | 2017-08-09 | 2019-02-26 | 上海影子智能科技有限公司 | A kind of three-dimensional face model automatic adjusting method |
| CN107481310A (en) * | 2017-08-14 | 2017-12-15 | 迈吉客科技（北京）有限公司 | A kind of image rendering method and system |
| CN107481310B (en) * | 2017-08-14 | 2020-05-08 | 迈吉客科技（北京）有限公司 | Image rendering method and system |
| CN108022285A (en) * | 2017-11-30 | 2018-05-11 | 杭州电魂网络科技股份有限公司 | Map rendering intent and device |
| CN108022285B (en) * | 2017-11-30 | 2021-04-20 | 杭州电魂网络科技股份有限公司 | Map rendering method and device |
| CN108280803A (en) * | 2018-01-22 | 2018-07-13 | 盎锐（上海）信息科技有限公司 | Image generating method and device based on 3D imagings |
| CN110136272A (en) * | 2018-02-09 | 2019-08-16 | 英属开曼群岛商玩美股份有限公司 | For the system and method to remote user's virtual application color make-up effect |
| CN108509846B (en) * | 2018-02-09 | 2022-02-11 | 腾讯科技（深圳）有限公司 | Image processing method, image processing apparatus, computer device, storage medium, and computer program product |
| CN108509846A (en) * | 2018-02-09 | 2018-09-07 | 腾讯科技（深圳）有限公司 | Image processing method, device, computer equipment and storage medium |
| CN110136272B (en) * | 2018-02-09 | 2023-05-30 | 英属开曼群岛商玩美股份有限公司 | System and method for virtually applying makeup effects to remote users |
| CN108364355A (en) * | 2018-02-12 | 2018-08-03 | 成都睿码科技有限责任公司 | A kind of AR rendering intents of fitting facial expression |
| CN108364355B (en) * | 2018-02-12 | 2022-12-09 | 成都睿码科技有限责任公司 | AR rendering method fitting facial expressions |
| CN108664884A (en) * | 2018-03-17 | 2018-10-16 | 广州帕克西软件开发有限公司 | A kind of virtually examination cosmetic method and device |
| CN108664884B (en) * | 2018-03-17 | 2022-07-08 | 广州帕克西软件开发有限公司 | Virtual makeup trial method and device |
| CN108805090A (en) * | 2018-06-14 | 2018-11-13 | 广东工业大学 | A kind of virtual examination cosmetic method based on Plane Gridding Model |
| CN109671142B (en) * | 2018-11-23 | 2023-08-04 | 南京图玩智能科技有限公司 | Intelligent cosmetic method and intelligent cosmetic mirror |
| CN109671142A (en) * | 2018-11-23 | 2019-04-23 | 南京图玩智能科技有限公司 | A kind of intelligence makeups method and intelligent makeups mirror |
| CN109993689A (en) * | 2019-03-14 | 2019-07-09 | 珠海天燕科技有限公司 | A kind of makeups method and apparatus |
| CN110120053A (en) * | 2019-05-15 | 2019-08-13 | 北京市商汤科技开发有限公司 | Face's dressing processing method, device and equipment |
| US11367236B2 (en) | 2019-05-15 | 2022-06-21 | Zhejiang Sensetime Technology Development Co., Ltd | Method, apparatus and device for generating three-dimensional local human body model |
| TWI748432B (en) * | 2019-05-15 | 2021-12-01 | 大陸商浙江商湯科技開發有限公司 | Method, apparatus, device and computer readable storage medium for rendering three-dimensional partial human body model |
| CN110111417A (en) * | 2019-05-15 | 2019-08-09 | 浙江商汤科技开发有限公司 | Generation method, device and the equipment of three-dimensional partial body's model |
| CN110264566A (en) * | 2019-06-03 | 2019-09-20 | 杭州小伊智能科技有限公司 | A kind of device and method of the multihead display based on the replacement of face AI color make-up |
| CN113780047A (en) * | 2021-01-11 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Virtual makeup trying method and device, electronic equipment and storage medium |
| CN113643397A (en) * | 2021-08-05 | 2021-11-12 | 广州帕克西软件开发有限公司 | Virtual makeup trying method based on face recognition |
| CN113838189A (en) * | 2021-09-13 | 2021-12-24 | 厦门美图之家科技有限公司 | Eyelash rendering method and device |
| CN113838189B (en) * | 2021-09-13 | 2024-02-02 | 厦门美图之家科技有限公司 | Eyelash rendering method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104463938A (en) | Three-dimensional virtual make-up trial method and device | |
| CN107316340B (en) | Rapid face modeling method based on single photo | |
| CN107274493B (en) | Three-dimensional virtual trial type face reconstruction method based on mobile platform | |
| CN105184249B (en) | Method and apparatus for face image processing | |
| CN104376594B (en) | Three-dimensional face modeling method and device | |
| CN101755288B (en) | Method and apparatus for realistic simulation of wrinkle aging and de-aging | |
| CN109377544A (en) | A kind of face three-dimensional image generating method, device and readable medium | |
| CN103606190A (en) | Method for automatically converting single face front photo into three-dimensional (3D) face model | |
| TWI532006B (en) | Method and system of simulating hair on 3d model | |
| CN107680167A (en) | A kind of three-dimensional (3 D) manikin creation method and system based on user image | |
| CN104331164A (en) | Gesture movement smoothing method based on similarity threshold value analysis of gesture recognition | |
| CN101556699A (en) | Face-based facial aging image synthesis method | |
| CN109035381B (en) | Cartoon picture hair rendering method and storage medium based on UE4 platform | |
| CN109147023A (en) | Three-dimensional special efficacy generation method, device and electronic equipment based on face | |
| CN106447739A (en) | Method for generating makeup region dynamic image and beauty makeup assisting method and device | |
| CN109584153A (en) | Modify the methods, devices and systems of eye | |
| CN103854306A (en) | High-reality dynamic expression modeling method | |
| Li | Film and TV animation production based on artificial intelligence AlphaGd | |
| Yan et al. | A non-photorealistic rendering method based on Chinese ink and wash painting style for 3D mountain models | |
| Xu | Face reconstruction based on multiscale feature fusion and 3d animation design | |
| Liu et al. | Three-dimensional cartoon facial animation based on art rules | |
| Gu et al. | Online fashion design education supported by digital three dimensions technologies | |
| CN110473276A (en) | A kind of high efficiency three-dimensional cartoon production method | |
| CN108509855B (en) | System and method for generating machine learning sample picture through augmented reality | |
| CN114581288A (en) | Image generation method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150325 |
|
| RJ01 | Rejection of invention patent application after publication |