CN108492247A - A kind of eye make-up chart pasting method based on distortion of the mesh - Google Patents
A kind of eye make-up chart pasting method based on distortion of the mesh Download PDFInfo
- Publication number
- CN108492247A CN108492247A CN201810246112.3A CN201810246112A CN108492247A CN 108492247 A CN108492247 A CN 108492247A CN 201810246112 A CN201810246112 A CN 201810246112A CN 108492247 A CN108492247 A CN 108492247A
- Authority
- CN
- China
- Prior art keywords
- eye
- control point
- face
- vertex
- make
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000000463 material Substances 0.000 claims abstract description 36
- 210000000887 face Anatomy 0.000 claims description 37
- 238000009877 rendering Methods 0.000 claims description 9
- 210000000720 eyelash Anatomy 0.000 claims description 5
- 210000000744 eyelid Anatomy 0.000 claims description 3
- 210000001747 pupil Anatomy 0.000 claims description 3
- 238000004886 process control Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 10
- 230000009466 transformation Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008407 joint function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
Classifications
-
- 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
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of eye make-up chart pasting method based on distortion of the mesh, including：Standard faces figure and face figure to be detected are obtained, after handling it, obtains First view contouring control point and the second eye profile control point respectively；Region division is carried out to the eye of standard faces figure, grid vertex is generated in the region of division；Warping function is calculated according to First view contouring control point, the second eye profile control point and grid vertex；Local deformation is carried out to the eye make-up material texture sample coordinates in grid vertex using warping function；Triangular mesh face is generated according to grid vertex after deformation；OpenGL vertex caches are created using grid vertex after deformation；OpenGL indexed caches are created using triangular mesh face；According to vertex cache and indexed cache, makeups material is fitted on face figure to be detected.Technical solution provided by the invention can make that eye make-up material is more accurate, is bonded various eye-shapeds naturally, improve makeups effect, meanwhile, it is capable to shorten the makeups time.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of eye make-up chart pasting methods based on distortion of the mesh.
Background technology
In recent years, portrait U.S. face makeups class is liked using deep by young woman user.Eyes are as people's " window of soul
Family ", eye make-up are the parts for being easiest to be perceived by the user.In the application of U.S. face makeups class, the quality of eye make-up effect is in addition to eye make-up element
Outside the validity and creative of material itself, a most important technical indicator be exactly eye make-up material be locally bonded in eye it is accurate
Degree, that is, how can will accurately and be naturally bonded after a kind of eye make-up material application local deformation technology (local warp) each
The different eye-shaped of kind.
The method that existing eye make-up textures method mainly uses eye deformation, i.e., according to the eye profile control point of standard faces
A transformation matrix is calculated with the eye profile control point of face to be detected, eye make-up textures are carried out by the transformation matrix.
Currently used eye deformation method has：Transformation matrix is obtained (for example, affine based on least square method (least squares)
Transformation), transformation matrix is obtained based on optical flow method (optical flow), the homography conversion based on two groups of eye profile control points
Method obtains transformation matrix etc..Since the above method belongs to the global change to eye, partial transformation problem is not accounted for, because
This easy tos produce the distortion of ratio and shape during the fitting of eye make-up, and makeups effect is poor.Also, existing method can needle
Deformation calculating is carried out to each pixel of ocular, and different eye joint functions can be directed to the same deforming position
It sets and is computed repeatedly, therefore, performance cost is apparent, cannot achieve the purpose that be bonded in real time, makeups efficiency is unsatisfactory.
Invention content
The present invention is intended to provide a kind of eye make-up chart pasting method based on distortion of the mesh, can make eye make-up material it is more accurate,
Naturally various eye-shapeds are bonded, makeups effect is improved.
In order to achieve the above objectives, the technical solution adopted by the present invention is as follows：
A kind of eye make-up chart pasting method based on distortion of the mesh, including：The standard faces figure to prestore is obtained, to the standard people
Face figure carries out eyes image processing, obtains First view contouring control point；Face figure to be detected is obtained, to the face to be detected
Figure carries out the eyes image processing, obtains the second eye profile control point；Region is carried out to the eye of the standard faces figure
It divides, and grid vertex is generated in the region of division；The attribute of the grid vertex includes：Vertex position, standard drawing texture
Sample coordinate, eye make-up material texture sample coordinates；It is controlled according to First view contouring control point, the second eye profile
Point and the grid vertex calculate warping function using least variance method；Using the warping function to the eye make-up material line
It manages sample coordinate and carries out local deformation, obtain grid vertex after deformation；Network of triangle is generated according to grid vertex after the deformation
Lattice face；OpenGL vertex caches are created using grid vertex after the deformation；OpenGL is created using the triangular mesh face
Indexed cache；According to the vertex cache and the indexed cache, the makeups material to prestore is fitted into the face to be detected
On figure.
Preferably, described that eyes image processing is carried out to the standard faces figure, obtain First view contouring control point packet
It includes：Eye key point location is carried out to the standard faces figure, obtains the eye profile control point of standard faces figure；To the mark
The eye profile control point of quasi- face figure carries out curve fitting, and obtains fitting control point；Described in the addition of the fitting control point
In the eye profile control point of standard faces figure, First view contouring control point is obtained.
Preferably, curve is carried out to the eye profile control point of the standard faces figure using Lagrange's interpolation to intend
It closes, obtains fitting control point；It is clicked through alternatively, being controlled the eye profile of the standard faces figure using Bezier fitting process
Row curve matching obtains fitting control point；Alternatively, using polynomial curve fitting method to the eye profile of the standard faces figure
Control point carries out curve fitting, and obtains fitting control point.
Preferably, the eye to the standard faces figure carries out region division, and generates net in the region of division
The method on lattice vertex is：According to the eye contour edge of the standard faces figure, the eye of the standard faces figure is divided into
Internal periphery region and outer outline area；The Internal periphery region includes pupil portion, and the outer outline area includes eyelid part；
Grid vertex is generated in the Internal periphery region；Grid vertex is generated in the outer outline area.
Preferably, described according to First view contouring control point, the second eye profile control point and the net
Lattice vertex, use least variance method calculate warping function method for：
fcp(x)=xM+T
Wherein, fcp(x) it is warping function, scp(i)For i-th of control point in First view contouring control point, dcp(i)
For i-th of control point in the second eye profile control point, V is the grid vertex.
Preferably, it according to the vertex cache and the indexed cache, will be prestored using OpenGL triangles rendering technique
Makeups material fit on the face figure to be detected.
Preferably, described according to the vertex cache and the indexed cache, it will using OpenGL triangle rendering techniques
The method that the makeups material to prestore fits on the face figure to be detected is：The makeups material to prestore is loaded, according to described pre-
The makeups material deposited creates eye make-up texture resource；According to the vertex cache and the indexed cache, the eye make-up texture is provided
Source is plotted on the face figure to be detected.
Preferably, the eye make-up texture resource includes：Eye shadow texture, informer's texture, eyelashes texture.
Preferably, according to grid vertex after the deformation, triangular mesh is generated using Delaunay Triangulation algorithm
Face.
Eye make-up chart pasting method provided in an embodiment of the present invention based on distortion of the mesh, due to the eye to standard faces figure into
It has gone region division, and grid vertex is generated in the region of division, grid vertex is made to be dispersed in each region of eye, to
Make each region of eye that all there is constraint, therefore during subsequently drawing eye make-up material, is not likely to produce unnatural stretching
Problem so that eye make-up material is bonded more acurrate, more natural on face to be measured.Meanwhile the present invention in grid vertex just for
Ocular, and grid vertex is more sparse, deformation, which calculates, only acts on grid vertex, therefore CPU computation burdens significantly reduce, from
And improve computation rate.Again due in the present invention grid vertex data and eye make-up texture resource be separated from each other, in this way
The calculating process that subsequent other eye joint functions repeat CPU is avoided, is made so as to avoid the multiple functions of eye makeups
At time superposition, further reduced performance cost, improve computation rate.As it can be seen that technical solution provided by the invention, energy
Enough make that eye make-up material is more accurate, is bonded various eye-shapeds naturally, improves makeups effect, meanwhile, it is capable to shorten the makeups time.
Description of the drawings
Fig. 1 is the method flow diagram of the embodiment of the present invention.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with attached drawing, to the present invention into
Row is further described.
Step 101, the standard faces figure to prestore is obtained, eyes image processing is carried out to the standard faces figure, obtains the
Contouring control point at a glance；
Step 102, face figure to be detected is obtained, the eyes image processing is carried out to the face figure to be detected, is obtained
Second eye profile control point；
In the embodiment of the present invention, step 101 and step 102 it is not stringent execute sequence, can successively execute, also can be simultaneously
It executes.But the eyes image processing procedure carried out to standard faces figure and face figure to be measured should be identical.
Specifically, it obtains First view contouring control point and the method at the second eye profile control point is：To the standard
Face figure carries out eye key point location, obtains the eye profile control point s of standard faces figurecp(x,y)；To the face to be measured
Figure carries out eye key point location, obtains the eye profile control point d of face figure to be measuredcp(x,y)；In order to make profile compactness more
Closely, using Lagrange's interpolation, to the eye profile control point s of above-mentioned standard face figurecp(x, y) and face figure to be measured
Eye profile control point dcp(x, y) carries out curve fitting respectively, respectively obtains fitting control point；By above-mentioned two groups of fitting control points
It is separately added into the eye profile control point s of corresponding standard faces figurecpThe eye profile control point of (x, y) and face figure to be measured
dcpIn (x, y), First view contouring control point s (x, y) and the second eye profile control point d (x, y) are respectively obtained.Its
In, the calculation formula of Lagrange's interpolation is as follows：
Certainly, Bezier fitting process can also be used to the eye profile control point of the standard faces figure and to be detected
The eye profile control point of face figure carries out curve fitting, and respectively obtains two groups of fitting control points；Alternatively, using polynomial curve
Fitting process carries out curve to the eye profile control point of the standard faces figure and the eye profile control point of face figure to be detected
Fitting, respectively obtains two groups of fitting control points.
Step 103, region division is carried out to the eye of the standard faces figure, and generates grid top in the region of division
Point；The attribute of the grid vertex includes：Vertex position, standard drawing texture sample coordinates, eye make-up material texture sample coordinates；
In this step, according to the eye contour edge of the standard faces figure, the eye of the standard faces figure is divided
For Internal periphery region, outer outline area and contour edge；The Internal periphery region includes pupil portion, the outer outline area packet
Include eyelid part；According to the actual eye shape of standard faces figure, divide in contour edge, Internal periphery region and outer outline area
Grid vertex is not generated.
Above-mentioned grid vertex data are initialized, and grid vertex is denoted as V (s, t0,t1), wherein s is vertex position, t0
For standard drawing texture sample coordinates, t1For eye make-up material texture sample coordinates.
Step 104, according to First view contouring control point s (x, y), the second eye profile control point d (x, y)
With grid vertex V (s, the t0,t1), warping function f is calculated using least variance methodcp(x)；
Specific method is：
fcp(x)=xM+T
Wherein, fcp(x) it is warping function, scp(i)For i-th of control in First view contouring control point s (x, y)
Point, dcp(i)For i-th of control point in the second eye profile control point d (x, y), V is the grid vertex.
Step 105, using the warping function to the eye make-up material texture sample coordinates t1Local deformation is carried out, is obtained
Grid vertex V (s, t after deformation0,t1 warp)；
Step 106, according to grid vertex V (s, t after the deformation0,t1 warp) generate triangular mesh face Meshindex；It adopts
With grid vertex V (s, t after the deformation0,t1 warp) create OpenGL vertex caches；Using the triangular mesh face
MeshindexCreate OpenGL indexed caches；
In this step, according to grid vertex V (s, t after the deformation0,t1 warp), using Delaunay Triangulation algorithm
Generate triangular mesh face Meshindex。
Step 107, according to the vertex cache and the indexed cache, the makeups material to prestore is fitted to described to be checked
It surveys on face figure.
It, will be pre- using OpenGL triangles rendering technique according to the vertex cache and the indexed cache in this step
The makeups material deposited fits on the face figure to be detected.Specific method is：
Step 1：The makeups material to prestore is loaded, eye make-up texture resource is created according to the makeups material to prestore；It is described
Eye make-up texture resource includes：Eye shadow texture, informer's texture, eyelashes texture；
Step 2：Setting current grid sample texture unit is eye shadow texture；
Step 3：Figure layer mixed mode is set；
Step 4：It, will be on eye shadow texture rendering to face figure to be measured according to above-mentioned vertex cache and indexed cache；
Step 5：Setting current grid sample texture unit is informer's texture；
Step 6：Figure layer mixed mode is set；
Step 7：It, will be on informer's texture rendering to face figure to be measured according to above-mentioned vertex cache and indexed cache；
Step 8：Setting current grid sample texture unit is eyelashes texture；
Step 9：Figure layer mixed mode is set；
Step 10：It, will be on eyelashes texture rendering to face figure to be measured according to above-mentioned vertex cache and indexed cache.
Eye make-up chart pasting method provided in an embodiment of the present invention based on distortion of the mesh, due to the eye to standard faces figure into
It has gone region division, and grid vertex is generated in the region of division, grid vertex is made to be dispersed in each region of eye, to
Make each region of eye that all there is constraint, therefore during subsequently drawing eye make-up material, is not likely to produce unnatural stretching
Problem so that eye make-up material is bonded more acurrate, more natural on face to be measured.Meanwhile the present invention in grid vertex just for
Ocular, and grid vertex is more sparse, deformation, which calculates, only acts on grid vertex, therefore CPU computation burdens significantly reduce.
During follow-up drafting eye make-up material, and take full advantage of GPU (Graphics Processing Unit, graphics processor)
Rendering advantage, i.e., the drawing of eye make-up material is met at into GPU processing, further mitigate CPU computation burden so that CPU
Other eye make-up tasks can be handled simultaneously, to improve computation rate.Again due to the grid vertex data and eye make-up in the present invention
Texture resource is separated from each other, vertex cache and indexed cache recycling, avoids subsequent other eye patches in this way
The calculating process that function repeats CPU is closed, is superimposed, further reduced so as to avoid the time caused by the multiple functions of eye makeups
Performance cost improves computation rate.As it can be seen that technical solution provided by the invention, can make eye make-up material more accurate, natural
Ground is bonded various eye-shapeds, improves makeups effect, meanwhile, it is capable to shorten the makeups time.The present invention agrees with that mobile terminal is practical to be made very much
Well with scene, the especially performance of Android system low and middle-end equipment.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.
Claims (9)
1. a kind of eye make-up chart pasting method based on distortion of the mesh, which is characterized in that including：
The standard faces figure to prestore is obtained, eyes image processing is carried out to the standard faces figure, obtains First view contouring control
Point processed；
Face figure to be detected is obtained, the eyes image processing is carried out to the face figure to be detected, obtains the second eye profile
Control point；
Region division is carried out to the eye of the standard faces figure, and grid vertex is generated in the region of division；The grid
The attribute on vertex includes：Vertex position, standard drawing texture sample coordinates, eye make-up material texture sample coordinates；
According to First view contouring control point, the second eye profile control point and the grid vertex, using minimum
Variance method calculates warping function；
Local deformation is carried out to the eye make-up material texture sample coordinates using the warping function, obtains grid top after deformation
Point；
Triangular mesh face is generated according to grid vertex after the deformation；The tops OpenGL are created using grid vertex after the deformation
Point cache；OpenGL indexed caches are created using the triangular mesh face；
According to the vertex cache and the indexed cache, the makeups material to prestore is fitted on the face figure to be detected.
2. the eye make-up chart pasting method according to claim 1 based on distortion of the mesh, which is characterized in that described to the standard
Face figure carries out eyes image processing, and obtaining First view contouring control point includes：
Eye key point location is carried out to the standard faces figure, obtains the eye profile control point of standard faces figure；
It carries out curve fitting to the eye profile control point of the standard faces figure, obtains fitting control point；
The fitting control point is added in the eye profile control point of the standard faces figure, the First view contouring is obtained
Control point.
3. the eye make-up chart pasting method according to claim 2 based on distortion of the mesh, which is characterized in that inserted using Lagrange
Value method carries out curve fitting to the eye profile control point of the standard faces figure, obtains fitting control point；Alternatively,
It is carried out curve fitting, is fitted to the eye profile control point of the standard faces figure using Bezier fitting process
Control point；Alternatively,
It is carried out curve fitting, is fitted to the eye profile control point of the standard faces figure using polynomial curve fitting method
Control point.
4. the eye make-up chart pasting method according to claim 2 based on distortion of the mesh, which is characterized in that described to the standard
The eye of face figure carries out region division, and the method for generation grid vertex is in the region of division：
According to the eye contour edge of the standard faces figure, by the eye of the standard faces figure be divided into Internal periphery region and
Outer outline area；The Internal periphery region includes pupil portion, and the outer outline area includes eyelid part；
Grid vertex is generated in the Internal periphery region；
Grid vertex is generated in the outer outline area.
5. the eye make-up chart pasting method according to any one of claims 1 to 4, based on distortion of the mesh, which is characterized in that institute
It states according to First view contouring control point, the second eye profile control point and the grid vertex, using minimum side
The method that poor method calculates warping function is：
fcp(x)=xM+T
Wherein, fcp(x) it is warping function, scp(i)For i-th of control point in First view contouring control point, dcp(i)For institute
I-th of control point in the second eye profile control point is stated, V is the grid vertex.
6. the eye make-up chart pasting method according to claim 5 based on distortion of the mesh, which is characterized in that slow according to the vertex
Deposit with the indexed cache, the makeups material to prestore is fitted to by the face to be detected using OpenGL triangles rendering technique
On figure.
7. the eye make-up chart pasting method according to claim 6 based on distortion of the mesh, which is characterized in that described according to the top
Point cache and the indexed cache are fitted to the makeups material to prestore using OpenGL triangles rendering technique described to be detected
Method on face figure is：
The makeups material to prestore is loaded, eye make-up texture resource is created according to the makeups material to prestore；
According to the vertex cache and the indexed cache, the eye make-up texture resource is plotted to the face figure to be detected
On.
8. the eye make-up chart pasting method according to claim 7 based on distortion of the mesh, which is characterized in that the eye make-up texture money
Source includes：Eye shadow texture, informer's texture, eyelashes texture.
9. the eye make-up chart pasting method according to claim 1 based on distortion of the mesh, which is characterized in that after the deformation
Grid vertex generates triangular mesh face using Delaunay Triangulation algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810246112.3A CN108492247A (en) | 2018-03-23 | 2018-03-23 | A kind of eye make-up chart pasting method based on distortion of the mesh |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810246112.3A CN108492247A (en) | 2018-03-23 | 2018-03-23 | A kind of eye make-up chart pasting method based on distortion of the mesh |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108492247A true CN108492247A (en) | 2018-09-04 |
Family
ID=63319495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810246112.3A Pending CN108492247A (en) | 2018-03-23 | 2018-03-23 | A kind of eye make-up chart pasting method based on distortion of the mesh |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108492247A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109063560A (en) * | 2018-06-28 | 2018-12-21 | 北京微播视界科技有限公司 | Image processing method, device, computer readable storage medium and terminal |
| CN109302628A (en) * | 2018-10-24 | 2019-02-01 | 广州虎牙科技有限公司 | A kind of face processing method based on live streaming, device, equipment and storage medium |
| CN109785259A (en) * | 2019-01-09 | 2019-05-21 | 成都品果科技有限公司 | A kind of real-time U.S. pupil method and device |
| CN109859134A (en) * | 2019-01-30 | 2019-06-07 | 珠海天燕科技有限公司 | A kind of processing method and terminal of makeups material |
| CN109903217A (en) * | 2019-01-25 | 2019-06-18 | 北京百度网讯科技有限公司 | Image distortion method and device |
| 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 |
| WO2020001014A1 (en) * | 2018-06-28 | 2020-01-02 | 北京微播视界科技有限公司 | Image beautification method and apparatus, and electronic device |
| CN111179210A (en) * | 2019-12-27 | 2020-05-19 | 浙江工业大学之江学院 | Method and system for generating texture map of face and electronic equipment |
| CN111652807A (en) * | 2019-07-05 | 2020-09-11 | 广州虎牙科技有限公司 | Eye adjustment method, eye live broadcast method, eye adjustment device, eye live broadcast device, electronic equipment and storage medium |
| CN111862287A (en) * | 2020-07-20 | 2020-10-30 | 广州市百果园信息技术有限公司 | Eye texture image generation method, texture mapping method, device and electronic equipment |
| CN112347979A (en) * | 2020-11-24 | 2021-02-09 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
| CN113469914A (en) * | 2021-07-08 | 2021-10-01 | 网易（杭州）网络有限公司 | Animal face beautifying method and device, storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040169663A1 (en) * | 2003-03-01 | 2004-09-02 | The Boeing Company | Systems and methods for providing enhanced vision imaging |
| US20070019882A1 (en) * | 2004-01-30 | 2007-01-25 | Shoji Tanaka | Makeup simulation program, makeup simulation device, and makeup simulation method |
| CN103714221A (en) * | 2014-01-08 | 2014-04-09 | 上海明穆电子科技有限公司 | Method for adjusting deformation of three-dimensional human body by using human body morphological parameters |
| CN104778712A (en) * | 2015-04-27 | 2015-07-15 | 厦门美图之家科技有限公司 | Method and system for pasting image to human face based on affine transformation |
| CN107256555A (en) * | 2017-05-25 | 2017-10-17 | 腾讯科技（上海）有限公司 | A kind of image processing method, device and storage medium |
-
2018
- 2018-03-23 CN CN201810246112.3A patent/CN108492247A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040169663A1 (en) * | 2003-03-01 | 2004-09-02 | The Boeing Company | Systems and methods for providing enhanced vision imaging |
| US20070019882A1 (en) * | 2004-01-30 | 2007-01-25 | Shoji Tanaka | Makeup simulation program, makeup simulation device, and makeup simulation method |
| CN103714221A (en) * | 2014-01-08 | 2014-04-09 | 上海明穆电子科技有限公司 | Method for adjusting deformation of three-dimensional human body by using human body morphological parameters |
| CN104778712A (en) * | 2015-04-27 | 2015-07-15 | 厦门美图之家科技有限公司 | Method and system for pasting image to human face based on affine transformation |
| CN107256555A (en) * | 2017-05-25 | 2017-10-17 | 腾讯科技（上海）有限公司 | A kind of image processing method, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 邱文杰: "基于MLS的图像变形技术研究与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020001014A1 (en) * | 2018-06-28 | 2020-01-02 | 北京微播视界科技有限公司 | Image beautification method and apparatus, and electronic device |
| CN109063560A (en) * | 2018-06-28 | 2018-12-21 | 北京微播视界科技有限公司 | Image processing method, device, computer readable storage medium and terminal |
| CN109302628B (en) * | 2018-10-24 | 2021-03-23 | 广州虎牙科技有限公司 | Live broadcast-based face processing method, device, equipment and storage medium |
| CN109302628A (en) * | 2018-10-24 | 2019-02-01 | 广州虎牙科技有限公司 | A kind of face processing method based on live streaming, device, equipment and storage medium |
| CN109785259A (en) * | 2019-01-09 | 2019-05-21 | 成都品果科技有限公司 | A kind of real-time U.S. pupil method and device |
| CN109903217A (en) * | 2019-01-25 | 2019-06-18 | 北京百度网讯科技有限公司 | Image distortion method and device |
| CN109859134A (en) * | 2019-01-30 | 2019-06-07 | 珠海天燕科技有限公司 | A kind of processing method and terminal of makeups material |
| 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 |
| CN109993689B (en) * | 2019-03-14 | 2023-05-16 | 郑州阿帕斯科技有限公司 | Cosmetic method and device |
| CN111652807A (en) * | 2019-07-05 | 2020-09-11 | 广州虎牙科技有限公司 | Eye adjustment method, eye live broadcast method, eye adjustment device, eye live broadcast device, electronic equipment and storage medium |
| CN111652807B (en) * | 2019-07-05 | 2024-03-08 | 广州虎牙科技有限公司 | Eye adjusting and live broadcasting method and device, electronic equipment and storage medium |
| CN111179210A (en) * | 2019-12-27 | 2020-05-19 | 浙江工业大学之江学院 | Method and system for generating texture map of face and electronic equipment |
| CN111179210B (en) * | 2019-12-27 | 2023-10-20 | 浙江工业大学之江学院 | Face texture map generation method and system and electronic equipment |
| CN111862287A (en) * | 2020-07-20 | 2020-10-30 | 广州市百果园信息技术有限公司 | Eye texture image generation method, texture mapping method, device and electronic equipment |
| CN112347979A (en) * | 2020-11-24 | 2021-02-09 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
| CN112347979B (en) * | 2020-11-24 | 2024-03-15 | 郑州阿帕斯科技有限公司 | Eye line drawing method and device |
| CN113469914A (en) * | 2021-07-08 | 2021-10-01 | 网易（杭州）网络有限公司 | Animal face beautifying method and device, storage medium and electronic equipment |
| CN113469914B (en) * | 2021-07-08 | 2024-03-19 | 网易（杭州）网络有限公司 | Animal face beautifying method and device, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492247A (en) | A kind of eye make-up chart pasting method based on distortion of the mesh | |
| CN109377557B (en) | Real-time three-dimensional face reconstruction method based on single-frame face image | |
| Sheffer et al. | Seamster: inconspicuous low-distortion texture seam layout | |
| CN103208133B (en) | The method of adjustment that in a kind of image, face is fat or thin | |
| CN113269862B (en) | Scene self-adaptive fine three-dimensional face reconstruction method, system and electronic equipment | |
| CN107507216A (en) | The replacement method of regional area, device and storage medium in image | |
| CN106952336B (en) | Feature-preserving human three-dimensional head portrait production method | |
| CN106504329B (en) | Gum deformation simulation method based on mass point spring model of tooth long axis | |
| CN105956997A (en) | Image deformation treatment method and device | |
| CN109584327B (en) | Face aging simulation method, device and equipment | |
| CN105678747B (en) | A kind of tooth mesh model automatic division method based on principal curvatures | |
| CN103559737A (en) | Object panorama modeling method | |
| CN106910102A (en) | The virtual try-in method of glasses and device | |
| CN110751730B (en) | Dressing human body shape estimation method based on deep neural network | |
| CN110418146A (en) | Method of changing face, storage medium, electronic equipment and system applied to live scene | |
| CN105631939B (en) | A kind of three-dimensional point cloud distortion correction method and its system based on curvature filtering | |
| CN107689254B (en) | Digital generation method for outer surface of full-crown prosthesis | |
| CN113111861A (en) | Face texture feature extraction method, 3D face reconstruction method, device and storage medium | |
| CN106709886A (en) | Automatic image retouching method and device | |
| CN108197555B (en) | Real-time face fusion method based on face tracking | |
| CN108805841A (en) | A kind of depth map recovery and View Synthesis optimization method based on cromogram guiding | |
| CN108038900A (en) | Oblique photograph model monomerization approach, system and computer-readable recording medium | |
| CN111652807B (en) | Eye adjusting and live broadcasting method and device, electronic equipment and storage medium | |
| CN113450441B (en) | Rendering method and device of three-dimensional virtual model and electronic equipment | |
| CN110335332A (en) | A kind of human face cartoon automatic drafting method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |