CN108765351A - Image processing method, device, electronic equipment and storage medium - Google Patents
Image processing method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN108765351A CN108765351A CN201810551066.8A CN201810551066A CN108765351A CN 108765351 A CN108765351 A CN 108765351A CN 201810551066 A CN201810551066 A CN 201810551066A CN 108765351 A CN108765351 A CN 108765351A
- Authority
- CN
- China
- Prior art keywords
- face
- grid model
- dimensional
- dimensional grid
- target object
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 238000007493 shaping process Methods 0.000 claims abstract description 86
- 239000013598 vector Substances 0.000 claims abstract description 63
- 230000001815 facial effect Effects 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims description 21
- 238000013507 mapping Methods 0.000 claims description 19
- 238000006073 displacement reaction Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 15
- 230000006870 function Effects 0.000 description 8
- 238000012937 correction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000003416 augmentation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002435 rhinoplasty Methods 0.000 description 3
- 210000000216 zygoma Anatomy 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 210000003733 optic disk Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/18—Image warping, e.g. rearranging pixels individually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2021—Shape modification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Architecture (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Processing Or Creating Images (AREA)
Abstract
This application discloses a kind of image processing method, device, electronic equipment and storage mediums.Wherein method includes：Obtain the shaping parameter on preset target object face three-dimensional grid model；Based on the shaping parameter on face three-dimensional grid model, motion vector of each 3D key points in face three-dimensional grid model on three dimensions is calculated；For each key point, the 3D motion vectors of each key point are mapped on two dimensional surface, obtain motion vector of each key point on two dimensional surface；According to the motion vector of face three-dimensional grid model and each key point on two dimensional surface, the facial image after 3D shapings of target object is generated.This method can obtain more that accurately face shaping improves the usage experience of user as a result, improve the accuracy of image deformation.
Description
Technical field
This application involves technical field of image processing more particularly to a kind of image processing method, device, electronic equipment and meters
Calculation machine readable storage medium storing program for executing.
Background technology
Existing facial image shaping technique is normally based on 2D flat images, is moved to the pixel on flat image
Position.In the related technology, it realizes there are two types of main stream approach used in facial image shaping：One is by delimiting pixel displacement
Range sets displacement weight to each pixel within the scope of this, then carries out displacement according to some direction to each pixel；
Another kind be by the way that 2D flat images are divided into multiple triangles, and to each triangular apex as desired direction into line position
It moves, linear stretch then is carried out to the triangle interior after variation, the image after deformation can be obtained.
But presently, there are the problem of be：Above two mode is the acquisition face 2D key points from 2D flat images,
Offset variable is set according to 2D key points, which is the key point relative value on flat image, not due to quantization degree
Height causes image deformation not accurate enough.
Invention content
The purpose of the application is intended to solve above-mentioned one of technical problem at least to a certain extent.
For this purpose, first purpose of the application is to propose a kind of image processing method.This method can obtain more smart
Accurate face shaping improves the usage experience of user as a result, improve the accuracy of image deformation.
Second purpose of the application is to propose a kind of image processing apparatus.
The third purpose of the application is to propose a kind of electronic equipment.
The 4th purpose of the application is to propose a kind of computer readable storage medium.
In order to achieve the above objectives, the image processing method that the application first aspect embodiment proposes, including：Acquisition is set in advance
Shaping parameter on fixed target object face three-dimensional grid model；Based on the shaping ginseng on the face three-dimensional grid model
Number, calculates motion vector of each 3D key points on three dimensions in the face three-dimensional grid model；For each pass
Key point maps to the 3D motion vectors of each key point on two dimensional surface, obtains each key point described two
Motion vector on dimensional plane；According to the face three-dimensional grid model and each key point on the two dimensional surface
Motion vector generates the facial image after 3D shapings of the target object.
In order to achieve the above objectives, the image processing apparatus that the application second aspect embodiment proposes, including：Shaping parameter obtains
Modulus block, for obtaining the shaping parameter on preset target object face three-dimensional grid model；Computing module is used for base
Shaping parameter on the face three-dimensional grid model, each 3D key points calculated in the face three-dimensional grid model exist
Motion vector on three dimensions；Motion vector mapping block, for being directed to each key point, by the 3D of each key point
Motion vector maps on two dimensional surface, obtains motion vector of each key point on the two dimensional surface；Shaping figure
As generation module, for the displacement according to the face three-dimensional grid model and each key point on the two dimensional surface
Vector generates the facial image after 3D shapings of the target object.
In order to achieve the above objectives, the electronic equipment that the application third aspect embodiment proposes, including：Memory, processor
And the computer program that can be run on a memory and on a processor is stored, when the processor executes described program, realize
Image processing method described in the application first aspect embodiment.
In order to achieve the above objectives, the non-transitorycomputer readable storage medium that the application fourth aspect embodiment proposes,
It is stored thereon with computer program, the image described in the application first aspect embodiment is realized when described program is executed by processor
Processing method.
According to the image processing method of the embodiment of the present application, device, electronic equipment and storage medium, the people of setting can be passed through
Shaping parameter on face three-dimensional grid model obtains the 3D motion vectors of face 3D key points, and according to the court of face on image
To goniometer calculating 3D key points motion vector to the mapping relations of 2D planes, to obtain the motion vector in 2D planes and meter
New face key point is calculated, finally carrying out linear stretch to image according to the network of 3D key points can be obtained face
Shaping result.The pixel displacement on facial image is quantified based on face three-dimensional grid model, setting first is three-dimensional
Displacement on grid model, the then mapping in the directions progress 3D to 2D, the pixel displacement amount on 2D images after being quantified,
To obtain more, accurately face shaping improves the usage experience of user as a result, improve the accuracy of image deformation.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains obviously, or recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein：
Fig. 1 is the flow chart according to the image processing method of the application one embodiment；
Fig. 2 is the flow chart according to the method for building up of the face three-dimensional grid model of the embodiment of the present application；
Fig. 3 is the flow chart according to the image processing method of one specific embodiment of the application；
Fig. 4 is the structural schematic diagram according to the image processing apparatus of the application one embodiment；
Fig. 5 is the structural schematic diagram according to the image processing apparatus of one specific embodiment of the application；
Fig. 6 is the structural schematic diagram according to the image processing apparatus of the application another specific embodiment；
Fig. 7 is the structural schematic diagram according to the electronic equipment of the application one embodiment.
Specific implementation mode
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Below with reference to the accompanying drawings the image processing method of the embodiment of the present application, device, electronic equipment and computer-readable are described
Storage medium.
Fig. 1 is the flow chart according to the image processing method of the application one embodiment.It should be noted that the application is real
The image processing method for applying example can be applied to the image processing apparatus of the embodiment of the present application, which can be configured in
On the electronic equipment of the embodiment of the present application.Wherein, which can be mobile terminal, such as mobile phone, tablet computer, individual
Digital assistants etc. have the hardware device of various operating systems.
As shown in Figure 1, the image processing method may include：
S110 obtains the shaping parameter on preset target object face three-dimensional grid model.
Specifically, the shaping parameter on target object face three-dimensional grid model can be preset.As an example, institute
Stating the shaping parameter on face three-dimensional grid model can set in the following manner：Obtain the face of the target object pre-established
Three-dimensional grid model, and the edit operation that target object is directed to the face three-dimensional grid model is received, and grasped according to the editor
Make to determine the shaping parameter on the face three-dimensional grid model.
Optionally, before carrying out shaping to the facial image of target object, the face three of the target object can first be obtained
Tie up grid model.At this point, target object can according to oneself demand and hobby to the face three-dimensional grid model into edlin, example
Such as, thin face, augmentation rhinoplasty can be carried out to the face three-dimensional grid model, reduce the operations such as cheekbone, pad chin.When receiving target object
For the face three-dimensional grid model of oneself edit operation when, the face three-dimensional grid can be determined according to the edit operation
Shaping parameter on model.Wherein, which may include but be not limited to pending pixel and the pending picture
The vegetarian refreshments offset variable to be moved.For example, by taking the edit operation is the operation of thin face as an example, institute is determined according to the thin face operation
State on face three-dimensional grid model which pixel need it is to be processed, and these pixels needs be moved to where etc. information.
In one embodiment of the application, as shown in Fig. 2, the target object can be pre-established by following steps
Face three-dimensional grid model：
S210 obtains the multiple image of target object；
S220 builds the human face three-dimensional model of target object according to multiple image；
S230, the gridding information based on human face three-dimensional model are multiple on facial contour from being extracted in the gridding information
3D key points；
For example, can based on the gridding information of human face three-dimensional model, from extracted in the gridding information on facial contour 296
A 3D key points.
S240 is based on interpolation algorithm, and generating multiple 3D inside face according to multiple 3D key points on facial contour closes
Multiple 3D key points outside key point and facial contour；
S250, according to outside multiple 3D key points on facial contour, multiple 3D key points inside face and facial contour
Multiple 3D key points in portion, establish the face three-dimensional grid model of target object.
For example, 3D key points 33 and people inside face can be obtained according to multiple 3D key points on facial contour, interpolation
Face profile exterior 3D key points 8 constitute new 3D grid models, i.e., the face of the described target object according to these 3D key points
Three-dimensional grid model.
As a result, by target object in advance to the face three-dimensional grid model of itself into edlin, according to the edit operation
The shaping parameter on the face three-dimensional grid model is can determine, in this way, carrying out shaping in the flat image to target object
When, the shaping parameter on the preset face three-dimensional grid model can be obtained, and then can subsequently be based on the shaping parameter
Realize the shaping to the flat image of target object.
S120 calculates each 3D in face three-dimensional grid model based on the shaping parameter on face three-dimensional grid model
Motion vector of the key point on three dimensions.
For example, for carrying out thin face operation to the face three-dimensional grid model, it may be determined that for the thin face operation
Corresponding shaping parameter, for example, the shaping parameter can be which pixel need to be to be processed on face three-dimensional grid model, and this
A little pixels needs be moved to where etc. information, in this way, the face three-dimensional grid mould can be calculated based on the shaping parameter
Motion vector of each 3D key points on three dimensions in type.
The 3D motion vectors of each key point are mapped on two dimensional surface, are obtained each for each key point by S130
Motion vector of the key point on two dimensional surface.
Optionally it is determined that the facial orientation angle on two dimensional surface, and according to the facial orientation angle on the two dimensional surface
The mapping relations for calculating the 3D motion vectors of each key point to the two dimensional surface are spent, and true according to the mapping relations
Fixed motion vector of each key point on the two dimensional surface.
That is, can be according to the facial orientation angle on two-dimensional image, by each 3D key points in three dimensions
On motion vector project on two dimensional surface, obtain projection of the 3D motion vectors of each key point on two dimensional surface to
Amount, which is motion vector of the key point on two dimensional surface.
S140 generates target according to the motion vector of face three-dimensional grid model and each key point on two dimensional surface
The facial image after 3D shapings of object.
As an example, motion vector that can be according to each key point on the two dimensional surface generates plane
Deformed 3D key points on image, and according to the face three-dimensional grid model and the deformed 3D key points to described
Flat image carries out linear stretch, obtains facial image of the target object after 3D shapings.
That is, motion vector that can be according to each key point on the two dimensional surface, is calculated plane
On image each key point will deformed key point position, and according to the face three-dimensional grid model and described every
A key point will deformed key point position, linear stretch is carried out to the flat image, obtains target object warp
Cross the facial image after 3D shapings.
According to the image processing method of the embodiment of the present application, can be joined by the shaping on the face three-dimensional grid model of setting
Number, obtains the 3D motion vectors of face 3D key points, and towards goniometer calculates 3D key point displacements according to face on image
Vector arrives the mapping relations of 2D planes, to obtain the motion vector in 2D planes and calculate new face key point, finally
The shaping result that linear stretch can be obtained face is carried out to image according to the network of 3D key points.It is three-dimensional to be based on face
Grid model quantifies the pixel displacement on facial image, sets the displacement on three-dimensional grid model first, then
Carry out the mapping in 3D to 2D directions, the pixel displacement amount on 2D images after being quantified, to obtain more accurately face
Shaping improves the usage experience of user as a result, improve the accuracy of image deformation.
Fig. 3 is the flow chart according to the image processing method of one specific embodiment of the application.
In order to promote user experience, the image processing method of the embodiment of the present application can be applied under user's self-timer scene, than
Such as when detecting that user uses self-timer mode, can Shape correction be carried out to the image shown in preview interface automatically, in this way, working as
When detecting that user clicks confirmation shooting button, the facial image after Shape correction can be directly obtained.Specifically, such as Fig. 3 institutes
Show, which may include：
S310 is obtained when detecting that user uses self-timer mode on preset user's face three-dimensional grid model
Shaping parameter.
Specifically, the shaping parameter on user's face three-dimensional grid model can be preset.As an example, the people
Shaping parameter on face three-dimensional grid model can be set in the following manner：Obtain the face three-dimensional grid of the user pre-established
Model, and receive user and be directed to the edit operation of the face three-dimensional grid model, and the people is determined according to the edit operation
Shaping parameter on face three-dimensional grid model.
Optionally, before carrying out shaping to the facial image of user, the face three-dimensional grid mould of the user can first be obtained
Type.At this point, user can according to oneself demand and hobby to the face three-dimensional grid model into edlin, for example, can be to the face
Three-dimensional grid model carries out thin face, augmentation rhinoplasty, reduces the operations such as cheekbone, pad chin.It is directed to the face three of oneself when receiving user
When tieing up the edit operation of grid model, the shaping ginseng on the face three-dimensional grid model can be determined according to the edit operation
Number.Wherein, which may include but be not limited to pending pixel and the pending pixel to be moved
Offset variable.For example, by taking the edit operation is the operation of thin face as an example, the face three-dimensional grid is determined according to the thin face operation
Which pixel needs to be processed on model, and these pixels needs be moved to where etc. information.
S320 calculates each 3D in face three-dimensional grid model based on the shaping parameter on face three-dimensional grid model
Motion vector of the key point on three dimensions.
The 3D motion vectors of each key point are mapped on two dimensional surface, are obtained each for each key point by S330
Motion vector of the key point on two dimensional surface.
S340 generates user according to the motion vector of face three-dimensional grid model and each key point on two dimensional surface
The facial image after 3D shapings.
As an example, motion vector that can be according to each key point on the two dimensional surface generates shooting
Deformed 3D key points on flat image in preview interface, and according to the face three-dimensional grid model and the deformation after
3D key points to the flat image carry out linear stretch, obtain facial image of the user after 3D shapings.
Facial image of the user after 3D shapings is included in shooting preview interface by S350.
Optionally, after obtaining facial image of the user after 3D shapings, can include by the facial image
In shooting preview interface, in this way, when detecting that user clicks confirmation shooting button, the people after Shape correction can be directly obtained
Face image.
It can be automatically to pre- when detecting that user uses self-timer mode according to the image processing method of the embodiment of the present application
The image shown of looking on interface carries out Shape correction, in this way, when detect user click confirm shooting button when, can directly obtain
Facial image after Shape correction improves the experience of taking pictures of user.
It should be noted that in one embodiment of the application, the image processing method of the embodiment of the present application can also answer
In scene for carrying out Shape correction to the flat image shot, for example, using the image of the embodiment of the present application
Processing method carries out Shape correction to the self-timer image that user had shot, and obtains the self-timer image after 3D shapings.
Corresponding with the image processing method that above-mentioned several embodiments provide, a kind of embodiment of the application also provides one kind
Image processing apparatus, the image procossing provided with above-mentioned several embodiments due to image processing apparatus provided by the embodiments of the present application
Method is corresponding, therefore is also applied for image procossing dress provided in this embodiment in the embodiment of aforementioned image processing method
It sets, is not described in detail in the present embodiment.Fig. 4 is the structural representation according to the image processing apparatus of the application one embodiment
Figure.As shown in figure 4, the image processing apparatus 400 may include：Shaping parameter acquisition module 410, computing module 420, displacement to
Measure mapping block 430 and shaping image generation module 440.
Specifically, shaping parameter acquisition module 410 is for obtaining preset target object face three-dimensional grid model
On shaping parameter.
Computing module 420 is used to, based on the shaping parameter on face three-dimensional grid model, calculate face three-dimensional grid model
In motion vector of each 3D key points on three dimensions.
Motion vector mapping block 430 is used to be directed to each key point, and the 3D motion vectors of each key point are mapped to
On two dimensional surface, motion vector of each key point on two dimensional surface is obtained.As an example, motion vector mapping block
430 can determine the facial orientation angle on the two dimensional surface, and according to the facial orientation angle calculation on the two dimensional surface
The 3D motion vectors of each key point to the two dimensional surface mapping relations, and according to the mapping relations determine described in
Each motion vector of the key point on the two dimensional surface.
Shaping image generation module 440 is used for according to face three-dimensional grid model and each key point on two dimensional surface
Motion vector generates the facial image after 3D shapings of target object.As an example, shaping image generation module
440 can be according to each key point on the two dimensional surface motion vector, generate deformed 3D on flat image and close
Key point, and the flat image is linearly drawn according to the face three-dimensional grid model and the deformed 3D key points
It stretches, obtains facial image of the target object after 3D shapings.
It should be noted that the shaping parameter on target object face three-dimensional grid model can be preset.Optionally, exist
In one embodiment of the application, as shown in figure 5, the image processing apparatus 400 may also include：Shaping parameter presets module
450, for presetting the shaping parameter on the target object face three-dimensional grid model.Wherein, in the implementation of the application
In example, it may include as shown in figure 5, shaping parameter presets module 450：Acquiring unit 451, receiving unit 452 and determining list
Member 453.Wherein, acquiring unit 451 is used to obtain the face three-dimensional grid model of the target object pre-established；It receives single
Member 452 is directed to the edit operation of the face three-dimensional grid model for receiving the target object；Determination unit 453 is used for root
According to the edit operation, the shaping parameter on the face three-dimensional grid model is determined.
It should also be noted that, before carrying out shaping to the facial image of target object, the target object can be first obtained
Face three-dimensional grid model.At this point, target object can carry out the face three-dimensional grid model according to oneself demand and hobby
Editor, for example, thin face, augmentation rhinoplasty can be carried out to the face three-dimensional grid model, reduce the operations such as cheekbone, pad chin.When receiving
When target object is directed to the edit operation of the face three-dimensional grid model of oneself, the face can be determined according to the edit operation
Shaping parameter on three-dimensional grid model.Wherein, which may include but be not limited to pending pixel and described waits for
The pixel of the processing offset variable to be moved.For example, by taking the edit operation is the operation of thin face as an example, grasped according to the thin face
Make to determine which pixel needs to be processed on the face three-dimensional grid model, and these pixels needs be moved to where
Etc. information.
Optionally, in one embodiment of the application, as shown in fig. 6, the image processing apparatus 400 may also include：Mould
Type pre-establishes module 460, the face three-dimensional grid model for pre-establishing the target object.Wherein, the application's
In embodiment, as shown in fig. 6, the model pre-establishes module 460 may include：Acquiring unit 461, first establishing unit 462,
Extraction unit 463, generation unit 464 and second establish unit 465.
Wherein, acquiring unit 461 is used to obtain the multiple image of the target object；First establishing unit 462 is used for root
The human face three-dimensional model of the target object is built according to the multiple image；Extraction unit 463 is used for three-dimensional based on the face
The gridding information of model, from the multiple 3D key points extracted in the gridding information on facial contour；Generation unit 464 is used for base
In interpolation algorithm, multiple 3D key points and face wheel inside face are generated according to multiple 3D key points on the facial contour
Multiple 3D key points outside exterior feature；Second establishes unit 465 for according to multiple 3D key points, described on the facial contour
Multiple 3D key points outside multiple 3D key points and the facial contour inside face, establish the face of the target object
Three-dimensional grid model.
It, can be based on face three-dimensional grid model to the picture on facial image according to the image processing apparatus of the embodiment of the present application
Vegetarian refreshments displacement is quantified, and is set the displacement on three-dimensional grid model first, is then carried out the mapping in the directions 3D to 2D, obtain
The pixel displacement amount on 2D images after quantization, to obtain more accurately face shaping as a result, improving image deformation
Accuracy improves the usage experience of user.
In order to realize that above-described embodiment, the application also proposed a kind of electronic equipment.
Fig. 7 is the structural schematic diagram according to the electronic equipment of the application one embodiment.As shown in fig. 7, the electronic equipment
700 may include：Memory 710, processor 720 and it is stored in the calculating that can be run on memory 710 and on processor 720
Machine program 730 when processor 720 executes described program 730, realizes the image procossing described in any of the above-described a embodiment of the application
Method.
In order to realize that above-described embodiment, the application also proposed a kind of non-transitorycomputer readable storage medium, thereon
It is stored with computer program, is realized when described program is executed by processor at the image described in any of the above-described a embodiment of the application
Reason method.
In the description of the present application, it is to be understood that term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indicating or implies relative importance or implicitly indicate the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In the description of the present application, " multiple "
It is meant that at least two, such as two, three etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discuss suitable
Sequence, include according to involved function by it is basic simultaneously in the way of or in the opposite order, to execute function, this should be by the application
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (system of such as computer based system including processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicating, propagating or passing
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can be for example by carrying out optical scanner to paper or other media, then into edlin, interpretation or when necessary with it
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or combination thereof.Above-mentioned
In embodiment, software that multiple steps or method can in memory and by suitable instruction execution system be executed with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit application-specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, which includes the steps that one or a combination set of embodiment of the method when being executed.
In addition, each functional unit in each embodiment of the application can be integrated in a processing module, it can also
That each unit physically exists alone, can also two or more units be integrated in a module.Above-mentioned integrated mould
The form that hardware had both may be used in block is realized, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and when sold or used as an independent product, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..Although having been shown and retouching above
Embodiments herein is stated, it is to be understood that above-described embodiment is exemplary, and should not be understood as the limit to the application
System, those skilled in the art can be changed above-described embodiment, change, replace and become within the scope of application
Type.
Claims (12)
1. a kind of image processing method, which is characterized in that include the following steps：
Obtain the shaping parameter on preset target object face three-dimensional grid model；
Based on the shaping parameter on the face three-dimensional grid model, each 3D calculated in the face three-dimensional grid model is closed
Motion vector of the key point on three dimensions；
For each key point, the 3D motion vectors of each key point are mapped on two dimensional surface, are obtained described each
Motion vector of the key point on the two dimensional surface；
According to the motion vector of the face three-dimensional grid model and each key point on the two dimensional surface, institute is generated
State the facial image after 3D shapings of target object.
2. image processing method as described in claim 1, which is characterized in that preset the target pair in the following manner
As the shaping parameter on face three-dimensional grid model：
Obtain the face three-dimensional grid model of the target object pre-established；
Receive the edit operation that the target object is directed to the face three-dimensional grid model；
According to the edit operation, the shaping parameter on the face three-dimensional grid model is determined.
3. image processing method as claimed in claim 2, which is characterized in that the face three-dimensional grid model of the target object
It establishes in the following manner：
Obtain the multiple image of the target object；
The human face three-dimensional model of the target object is built according to the multiple image；
It is crucial from the multiple 3D extracted in the gridding information on facial contour based on the gridding information of the human face three-dimensional model
Point；
Based on interpolation algorithm, according to multiple 3D key points on the facial contour generate multiple 3D key points inside face and
Multiple 3D key points outside facial contour；
According to multiple 3D key points on the facial contour, multiple 3D key points inside the face and the facial contour
External multiple 3D key points, establish the face three-dimensional grid model of the target object.
4. image processing method as described in claim 1, which is characterized in that the 3D displacements by each key point to
Amount maps on two dimensional surface, obtains motion vector of each key point on the two dimensional surface, including：
Determine the facial orientation angle on the two dimensional surface；
According to the 3D motion vectors of each key point described in the facial orientation angle calculation on the two dimensional surface to the two dimension
The mapping relations of plane；
Motion vector of each key point on the two dimensional surface is determined according to the mapping relations.
5. image processing method as described in claim 1, which is characterized in that it is described according to the face three-dimensional grid model and
Motion vector of each key point on the two dimensional surface, generates the face after 3D shapings of the target object
Image, including：
According to motion vector of each key point on the two dimensional surface, it is crucial to generate deformed 3D on flat image
Point；
Linear stretch is carried out to the flat image according to the face three-dimensional grid model and the deformed 3D key points,
Obtain facial image of the target object after 3D shapings.
6. a kind of image processing apparatus, which is characterized in that including：
Shaping parameter acquisition module, for obtaining the shaping parameter on preset target object face three-dimensional grid model；
Computing module, for based on the shaping parameter on the face three-dimensional grid model, calculating the face three-dimensional grid mould
Motion vector of each 3D key points on three dimensions in type；
The 3D motion vectors of each key point are mapped to two by motion vector mapping block for being directed to each key point
On dimensional plane, motion vector of each key point on the two dimensional surface is obtained；
Shaping image generation module, for flat in the two dimension according to the face three-dimensional grid model and each key point
Motion vector on face generates the facial image after 3D shapings of the target object.
7. image processing apparatus as claimed in claim 6, which is characterized in that described device further includes：
Shaping parameter presets module, for presetting the ginseng of the shaping on the target object face three-dimensional grid model
Number；
Wherein, the shaping parameter presets module and includes：
Acquiring unit, the face three-dimensional grid model for obtaining the target object pre-established；
Receiving unit is directed to the edit operation of the face three-dimensional grid model for receiving the target object；
Determination unit, for according to the edit operation, determining the shaping parameter on the face three-dimensional grid model.
8. image processing apparatus as claimed in claim 7, which is characterized in that described device further includes：
Model pre-establishes module, the face three-dimensional grid model for pre-establishing the target object；
Wherein, the model pre-establishes module and includes：
Acquiring unit, the multiple image for obtaining the target object；
First establishing unit, the human face three-dimensional model for building the target object according to the multiple image；
Extraction unit is used for the gridding information based on the human face three-dimensional model, facial contour is extracted from the gridding information
On multiple 3D key points；
Generation unit is generated according to multiple 3D key points on the facial contour inside face for being based on interpolation algorithm
Multiple 3D key points outside multiple 3D key points and facial contour；
Second establishes unit, for being closed according to multiple 3D key points on the facial contour, multiple 3D inside the face
Multiple 3D key points outside key point and the facial contour, establish the face three-dimensional grid model of the target object.
9. image processing apparatus as claimed in claim 6, which is characterized in that the motion vector mapping block is specifically used for：
Determine the facial orientation angle on the two dimensional surface；
According to the 3D motion vectors of each key point described in the facial orientation angle calculation on the two dimensional surface to the two dimension
The mapping relations of plane；
Motion vector of each key point on the two dimensional surface is determined according to the mapping relations.
10. image processing apparatus as claimed in claim 6, which is characterized in that the shaping image generation module is specifically used for：
According to motion vector of each key point on the two dimensional surface, it is crucial to generate deformed 3D on flat image
Point；
Linear stretch is carried out to the flat image according to the face three-dimensional grid model and the deformed 3D key points,
Obtain facial image of the target object after 3D shapings.
11. a kind of electronic equipment, which is characterized in that including：Memory, processor and storage are on a memory and can be in processor
The computer program of upper operation when the processor executes described program, is realized as described in any one of claim 1 to 5
Image processing method.
12. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the journey
The image processing method as described in any one of claim 1 to 5 is realized when sequence is executed by processor.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810551066.8A CN108765351B (en) | 2018-05-31 | 2018-05-31 | Image processing method, image processing device, electronic equipment and storage medium |
| CN202011241111.3A CN112330824B (en) | 2018-05-31 | 2018-05-31 | Image processing method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810551066.8A CN108765351B (en) | 2018-05-31 | 2018-05-31 | Image processing method, image processing device, electronic equipment and storage medium |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011241111.3A Division CN112330824B (en) | 2018-05-31 | 2018-05-31 | Image processing method, device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108765351A true CN108765351A (en) | 2018-11-06 |
| CN108765351B CN108765351B (en) | 2020-12-08 |
Family
ID=64001235
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810551066.8A Active CN108765351B (en) | 2018-05-31 | 2018-05-31 | Image processing method, image processing device, electronic equipment and storage medium |
| CN202011241111.3A Active CN112330824B (en) | 2018-05-31 | 2018-05-31 | Image processing method, device, electronic equipment and storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011241111.3A Active CN112330824B (en) | 2018-05-31 | 2018-05-31 | Image processing method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN108765351B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711390A (en) * | 2019-01-17 | 2019-05-03 | 深圳英飞拓科技股份有限公司 | Face scratches the preferred method and device of figure picture |
| CN109741277A (en) * | 2018-12-29 | 2019-05-10 | 广州华多网络科技有限公司 | Image processing method, device, storage medium and server |
| CN110060287A (en) * | 2019-04-26 | 2019-07-26 | 北京迈格威科技有限公司 | Facial image nose shaping methods and device |
| CN110060348A (en) * | 2019-04-26 | 2019-07-26 | 北京迈格威科技有限公司 | Facial image shaping methods and device |
| CN110457846A (en) * | 2019-08-16 | 2019-11-15 | 广东商鼎智能设备有限公司 | Electrical discharge machining parameter generation method, device, electronic equipment and storage medium |
| CN110675489A (en) * | 2019-09-25 | 2020-01-10 | 北京达佳互联信息技术有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111031305A (en) * | 2019-11-21 | 2020-04-17 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device, and storage medium |
| CN111445568A (en) * | 2018-12-28 | 2020-07-24 | 广州市百果园网络科技有限公司 | Character expression editing method and device, computer storage medium and terminal |
| CN111467131A (en) * | 2020-04-30 | 2020-07-31 | 浙江大学 | Automatic design method for 3D printing customized goggles frame |
| CN111754431A (en) * | 2020-06-17 | 2020-10-09 | 北京百度网讯科技有限公司 | Image area replacement method, device, equipment and storage medium |
| CN112241933A (en) * | 2020-07-15 | 2021-01-19 | 北京沃东天骏信息技术有限公司 | Face image processing method and device, storage medium and electronic equipment |
| CN112614228A (en) * | 2020-12-17 | 2021-04-06 | 北京达佳互联信息技术有限公司 | Method and device for simplifying three-dimensional grid, electronic equipment and storage medium |
| CN112669447A (en) * | 2020-12-30 | 2021-04-16 | 网易（杭州）网络有限公司 | Model head portrait creating method and device, electronic equipment and storage medium |
| CN113033341A (en) * | 2021-03-09 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113570634A (en) * | 2020-04-28 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Object three-dimensional reconstruction method and device, electronic equipment and storage medium |
| KR20220044156A (en) | 2020-09-22 | 2022-04-06 | 썬전 그린조이 테크놀로지 컴퍼니 리미티드 | Golf ball overhead detection method, system and storage medium |
| US11450068B2 (en) | 2019-11-21 | 2022-09-20 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for processing image, and storage medium using 3D model, 2D coordinates, and morphing parameter |
| CN115409951A (en) * | 2022-10-28 | 2022-11-29 | 北京百度网讯科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| WO2023001095A1 (en) * | 2021-07-23 | 2023-01-26 | 百果园技术(新加坡)有限公司 | Face key point interpolation method and apparatus, computer device, and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113362431A (en) * | 2021-06-30 | 2021-09-07 | 北京爱奇艺科技有限公司 | Data migration method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739719A (en) * | 2009-12-24 | 2010-06-16 | 四川大学 | Three-dimensional gridding method of two-dimensional front view human face image |
| CN103077553A (en) * | 2012-12-28 | 2013-05-01 | 海纳医信（北京）软件科技有限责任公司 | Three-dimensional coordinate determination method and device |
| US20130173235A1 (en) * | 2010-05-21 | 2013-07-04 | My Orthodontics Pty Ltd | Prediction of post-procedural appearance |
| CN105938627A (en) * | 2016-04-12 | 2016-09-14 | 湖南拓视觉信息技术有限公司 | Processing method and system for virtual plastic processing on face |
| CN106909875A (en) * | 2016-09-12 | 2017-06-30 | 湖南拓视觉信息技术有限公司 | Face shape of face sorting technique and system |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100468465C (en) * | 2007-07-13 | 2009-03-11 | 中国科学技术大学 | Stereo vision three-dimensional human face modelling approach based on dummy image |
| CN101311966A (en) * | 2008-06-20 | 2008-11-26 | 浙江大学 | Three-dimensional human face animations editing and synthesis a based on operation transmission and Isomap analysis |
| CN101561874B (en) * | 2008-07-17 | 2011-10-26 | 清华大学 | Method for recognizing face images |
| CN101320484B (en) * | 2008-07-17 | 2012-01-04 | 清华大学 | Three-dimensional human face recognition method based on human face full-automatic positioning |
| CN101383055B (en) * | 2008-09-18 | 2010-09-29 | 北京中星微电子有限公司 | Three-dimensional human face constructing method and system |
| CN101777195B (en) * | 2010-01-29 | 2012-04-25 | 浙江大学 | Three-dimensional face model adjusting method |
| CN104036546B (en) * | 2014-06-30 | 2017-01-11 | 清华大学 | Method for carrying out face three-dimensional reconstruction at any viewing angle on basis of self-adaptive deformable model |
| CN105787878B (en) * | 2016-02-25 | 2018-12-28 | 杭州格像科技有限公司 | A kind of U.S. face processing method and processing device |
| CN105913416A (en) * | 2016-04-06 | 2016-08-31 | 中南大学 | Method for automatically segmenting three-dimensional human face model area |
| WO2018053703A1 (en) * | 2016-09-21 | 2018-03-29 | Intel Corporation | Estimating accurate face shape and texture from an image |
| US10614633B2 (en) * | 2016-10-18 | 2020-04-07 | Microsoft Technology Licensing, Llc | Projecting a two-dimensional image onto a three-dimensional graphical object |
| CN106570822B (en) * | 2016-10-25 | 2020-10-16 | 宇龙计算机通信科技(深圳)有限公司 | Face mapping method and device |
| CN106503671B (en) * | 2016-11-03 | 2019-07-12 | 厦门中控智慧信息技术有限公司 | The method and apparatus for determining human face posture |
| CN106920274B (en) * | 2017-01-20 | 2020-09-04 | 南京开为网络科技有限公司 | Face modeling method for rapidly converting 2D key points of mobile terminal into 3D fusion deformation |
| CN107464212B (en) * | 2017-07-28 | 2021-01-01 | Oppo广东移动通信有限公司 | Beautifying method, electronic device and computer readable storage medium |
| CN107730465B (en) * | 2017-10-09 | 2020-09-04 | 武汉斗鱼网络科技有限公司 | Face beautifying method and device in image |
| CN107730445B (en) * | 2017-10-31 | 2022-02-18 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, storage medium, and electronic device |
| CN107948499A (en) * | 2017-10-31 | 2018-04-20 | 维沃移动通信有限公司 | A kind of image capturing method and mobile terminal |
| CN107886484B (en) * | 2017-11-30 | 2020-01-10 | Oppo广东移动通信有限公司 | Beautifying method, beautifying device, computer-readable storage medium and electronic equipment |
| CN107944435A (en) * | 2017-12-27 | 2018-04-20 | 广州图语信息科技有限公司 | Three-dimensional face recognition method and device and processing terminal |
-
2018
- 2018-05-31 CN CN201810551066.8A patent/CN108765351B/en active Active
- 2018-05-31 CN CN202011241111.3A patent/CN112330824B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739719A (en) * | 2009-12-24 | 2010-06-16 | 四川大学 | Three-dimensional gridding method of two-dimensional front view human face image |
| US20130173235A1 (en) * | 2010-05-21 | 2013-07-04 | My Orthodontics Pty Ltd | Prediction of post-procedural appearance |
| CN103077553A (en) * | 2012-12-28 | 2013-05-01 | 海纳医信（北京）软件科技有限责任公司 | Three-dimensional coordinate determination method and device |
| CN105938627A (en) * | 2016-04-12 | 2016-09-14 | 湖南拓视觉信息技术有限公司 | Processing method and system for virtual plastic processing on face |
| CN106909875A (en) * | 2016-09-12 | 2017-06-30 | 湖南拓视觉信息技术有限公司 | Face shape of face sorting technique and system |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111445568A (en) * | 2018-12-28 | 2020-07-24 | 广州市百果园网络科技有限公司 | Character expression editing method and device, computer storage medium and terminal |
| CN111445568B (en) * | 2018-12-28 | 2023-08-15 | 广州市百果园网络科技有限公司 | Character expression editing method, device, computer storage medium and terminal |
| CN109741277A (en) * | 2018-12-29 | 2019-05-10 | 广州华多网络科技有限公司 | Image processing method, device, storage medium and server |
| CN109711390A (en) * | 2019-01-17 | 2019-05-03 | 深圳英飞拓科技股份有限公司 | Face scratches the preferred method and device of figure picture |
| CN110060348B (en) * | 2019-04-26 | 2023-08-11 | 北京迈格威科技有限公司 | Face image shaping method and device |
| CN110060287A (en) * | 2019-04-26 | 2019-07-26 | 北京迈格威科技有限公司 | Facial image nose shaping methods and device |
| CN110060348A (en) * | 2019-04-26 | 2019-07-26 | 北京迈格威科技有限公司 | Facial image shaping methods and device |
| CN110457846A (en) * | 2019-08-16 | 2019-11-15 | 广东商鼎智能设备有限公司 | Electrical discharge machining parameter generation method, device, electronic equipment and storage medium |
| CN110457846B (en) * | 2019-08-16 | 2023-08-18 | 广东商鼎智能设备有限公司 | Electric spark machining parameter generation method and device, electronic equipment and storage medium |
| CN110675489B (en) * | 2019-09-25 | 2024-01-23 | 北京达佳互联信息技术有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN110675489A (en) * | 2019-09-25 | 2020-01-10 | 北京达佳互联信息技术有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111031305A (en) * | 2019-11-21 | 2020-04-17 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device, and storage medium |
| KR102406438B1 (en) * | 2019-11-21 | 2022-06-08 | 베이징 센스타임 테크놀로지 디벨롭먼트 컴퍼니 리미티드 | Image processing method and apparatus, image processing apparatus and storage medium |
| WO2021098143A1 (en) * | 2019-11-21 | 2021-05-27 | 北京市商汤科技开发有限公司 | Image processing method and device, image processing apparatus, and storage medium |
| KR20210064113A (en) * | 2019-11-21 | 2021-06-02 | 베이징 센스타임 테크놀로지 디벨롭먼트 컴퍼니 리미티드 | Image processing method and apparatus, image processing apparatus and storage medium |
| US11450068B2 (en) | 2019-11-21 | 2022-09-20 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for processing image, and storage medium using 3D model, 2D coordinates, and morphing parameter |
| TWI750710B (en) * | 2019-11-21 | 2021-12-21 | 中國商北京市商湯科技開發有限公司 | Image processing method and apparatus, image processing device and storage medium |
| CN113570634A (en) * | 2020-04-28 | 2021-10-29 | 北京达佳互联信息技术有限公司 | Object three-dimensional reconstruction method and device, electronic equipment and storage medium |
| CN111467131A (en) * | 2020-04-30 | 2020-07-31 | 浙江大学 | Automatic design method for 3D printing customized goggles frame |
| CN111754431B (en) * | 2020-06-17 | 2023-08-01 | 北京百度网讯科技有限公司 | Image area replacement method, device, equipment and storage medium |
| CN111754431A (en) * | 2020-06-17 | 2020-10-09 | 北京百度网讯科技有限公司 | Image area replacement method, device, equipment and storage medium |
| CN112241933A (en) * | 2020-07-15 | 2021-01-19 | 北京沃东天骏信息技术有限公司 | Face image processing method and device, storage medium and electronic equipment |
| WO2022012085A1 (en) * | 2020-07-15 | 2022-01-20 | 北京沃东天骏信息技术有限公司 | Face image processing method and apparatus, storage medium, and electronic device |
| KR20220044156A (en) | 2020-09-22 | 2022-04-06 | 썬전 그린조이 테크놀로지 컴퍼니 리미티드 | Golf ball overhead detection method, system and storage medium |
| CN112614228A (en) * | 2020-12-17 | 2021-04-06 | 北京达佳互联信息技术有限公司 | Method and device for simplifying three-dimensional grid, electronic equipment and storage medium |
| CN112614228B (en) * | 2020-12-17 | 2023-09-05 | 北京达佳互联信息技术有限公司 | Method, device, electronic equipment and storage medium for simplifying three-dimensional grid |
| CN112669447B (en) * | 2020-12-30 | 2023-06-30 | 网易（杭州）网络有限公司 | Model head portrait creation method and device, electronic equipment and storage medium |
| CN112669447A (en) * | 2020-12-30 | 2021-04-16 | 网易（杭州）网络有限公司 | Model head portrait creating method and device, electronic equipment and storage medium |
| CN113033341A (en) * | 2021-03-09 | 2021-06-25 | 北京达佳互联信息技术有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN113033341B (en) * | 2021-03-09 | 2024-04-19 | 北京达佳互联信息技术有限公司 | Image processing method, device, electronic equipment and storage medium |
| WO2023001095A1 (en) * | 2021-07-23 | 2023-01-26 | 百果园技术(新加坡)有限公司 | Face key point interpolation method and apparatus, computer device, and storage medium |
| CN115409951A (en) * | 2022-10-28 | 2022-11-29 | 北京百度网讯科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112330824A (en) | 2021-02-05 |
| CN108765351B (en) | 2020-12-08 |
| CN112330824B (en) | 2024-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765351A (en) | Image processing method, device, electronic equipment and storage medium | |
| CN109285215B (en) | Human body three-dimensional model reconstruction method and device and storage medium | |
| CN109859296B (en) | Training method of SMPL parameter prediction model, server and storage medium | |
| CN107705333B (en) | Space positioning method and device based on binocular camera | |
| CN107230225B (en) | Method and apparatus for three-dimensional reconstruction | |
| CN111199579B (en) | Method, device, equipment and medium for building three-dimensional model of target object | |
| KR101560508B1 (en) | Method and arrangement for 3-dimensional image model adaptation | |
| US20210241495A1 (en) | Method and system for reconstructing colour and depth information of a scene | |
| US11928778B2 (en) | Method for human body model reconstruction and reconstruction system | |
| CN113643414B (en) | Three-dimensional image generation method and device, electronic equipment and storage medium | |
| CN109740659B (en) | Image matching method and device, electronic equipment and storage medium | |
| CN110443884B (en) | Hand motion reconstruction method and device | |
| CN113538682B (en) | Model training method, head reconstruction method, electronic device, and storage medium | |
| EP3906530B1 (en) | Method for 3d reconstruction of an object | |
| JP2018133059A (en) | Information processing apparatus and method of generating three-dimensional model | |
| Anasosalu et al. | Compact and accurate 3-D face modeling using an RGB-D camera: let's open the door to 3-D video conference | |
| CN112883920A (en) | Point cloud deep learning-based three-dimensional face scanning feature point detection method and device | |
| Oisel et al. | One-dimensional dense disparity estimation for three-dimensional reconstruction | |
| US10861174B2 (en) | Selective 3D registration | |
| JP5400802B2 (en) | Contact simulation method and apparatus using layered depth images | |
| KR20220085694A (en) | A skeleton-based dynamic point cloud estimation system for sequence compression | |
| CN112907733A (en) | Method and device for reconstructing three-dimensional model and three-dimensional model acquisition and reconstruction system | |
| EP4111420A1 (en) | Face mesh deformation with detailed wrinkles | |
| CN113112606B (en) | Face correction method, system and storage medium based on three-dimensional live-action modeling | |
| CN114820923A (en) | High-precision multi-view point cloud reconstruction method and device based on differential projection |
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 |