CN107578469A - A kind of 3D human body modeling methods and device based on single photo - Google Patents
A kind of 3D human body modeling methods and device based on single photo Download PDFInfo
- Publication number
- CN107578469A CN107578469A CN201710803000.9A CN201710803000A CN107578469A CN 107578469 A CN107578469 A CN 107578469A CN 201710803000 A CN201710803000 A CN 201710803000A CN 107578469 A CN107578469 A CN 107578469A
- Authority
- CN
- China
- Prior art keywords
- photo
- human body
- key point
- model
- point
- 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
Landscapes
- Processing Or Creating Images (AREA)
- Image Generation (AREA)
Abstract
The embodiment of the invention discloses a kind of 3D human body modeling methods based on single photo and device, method to include：A photo is obtained, photo is parsed, marks the key point of human body in photo, calculates the space coordinates of key point；After the distance for obtaining the key point in the skeleton point and photo in the standardized human body's model being pre-created, alignment skeleton point after key point with generating basic manikin；The basic textures in the standardized human body's model being pre-created are obtained, after the dermatoglyph of face in basic textures and photo is carried out into mathematic interpolation, are merged using edge gateway, generate base texture data；According to basic manikin and base texture data generation 3D manikins.The embodiment of the present invention can realize 3D Human Modelings by a photo, and have bone and muscle systems support in model, can produce expression and action, can also carry out secondary editor, and modeling speed is fast, and reduction degree precision is high.
Description
Technical field
The present invention relates to technical field of computer vision, more particularly to a kind of 3D human body modeling methods based on single photo
And device.
Background technology
Stereo face recognition is current computer graphics and computer vision field is most basic one of studies a question.Three
Dimension manikin is widely used in identity discriminating, medical auxiliary, production of film and TV, game making, digital art etc..
In the prior art, 3D models are generated using single photo, limited to by reduction degree effect, can be only applied to cartoon joy
Happy aspect..Prior art also has a kind of single image modeling, relatively true on reduction degree, but model is not editable, simply
The key node of photo is reduced, and is changeless in these crucial mesh points, it is impossible to produces secondary editor, it is impossible to produce
Raw displacement, is more supported, therefore model is one fixed, will not produce expression and action without bone and muscle systems.Cause
Single photo generates 3D modeling technology in the prior art for this, reduces poor accuracy, the model accuracy of reduction is low, the place of textures texture
Reason details is few, and the 3D models generated can not be edited, and inconvenience is brought to establish accurate manikin.
The content of the invention
For above-mentioned technical problem, the embodiments of the invention provide a kind of 3D human body modeling methods based on single photo and
Device, single photo 3D modeling technology reduction poor accuracy of the prior art is can solve the problem that, to establish accurate manikin
Bring the technical problem of inconvenience.
The first aspect of the embodiment of the present invention provides a kind of 3D human body modeling methods based on single photo, including：
A photo is obtained, the photo is parsed, marks the key point of human body in the photo, calculates the pass
The space coordinates of key point；
After the distance for obtaining the skeleton point and the key point in the photo in the standardized human body's model being pre-created, alignment
The skeleton point after the key point with generating basic manikin；
The basic textures in the standardized human body's model being pre-created are obtained, by the basic textures and human body in the photo
Dermatoglyph carry out mathematic interpolation after, merged using edge gateway, generate base texture data；
According to the basic manikin and base texture data generation 3D manikins.
Alternatively, one photo of the acquisition, parses to the photo, marks the key of human body in the photo
Point, before the space coordinates for calculating the key point, in addition to：
It is pre-created a standardized human body's model for including skeleton point.
Alternatively, one photo of the acquisition includes：
Obtain a photo of shooting or obtain the photo imported, the photo includes human body information.
Alternatively, the key point for marking human body in the photo, calculating the space coordinates of the key point includes：
According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；
The difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created
Result of calculation, obtain the space coordinates of key point.
Alternatively, one photo of the acquisition also includes：
The scan data of somatic data is obtained, photo is generated according to the scan data.
Second aspect of the embodiment of the present invention provides a kind of 3D Human Modeling devices based on single photo, including：
Key point acquisition module, for obtaining a photo, the photo is parsed, marks human body in the photo
Key point, calculate the space coordinates of the key point；
Basic model establishes module, for obtaining in skeleton point and the photo in the standardized human body's model being pre-created
Key point distance after, generate basic manikin after the align skeleton point and the key point；
Data texturing generation module, for obtaining the basic textures in the standardized human body's model being pre-created, by the base
After the dermatoglyph of this textures and human body in the photo carries out mathematic interpolation, merged using edge gateway, generation basis
Data texturing；
3D manikin generation modules, for generating 3D people according to the basic manikin and the base texture data
Body Model.
Alternatively, described device also includes：
Module is pre-created, for being pre-created a standardized human body's model for including skeleton point
Alternatively, the key point acquisition module is used for：
Shoot a photo or import a photo, the photo includes human body information.
Alternatively, the key point acquisition module is additionally operable to：
According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；
The difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created
Result of calculation, obtain the space coordinates of key point.
The third aspect of the embodiment of the present invention provides a kind of non-volatile computer readable storage medium storing program for executing, it is characterised in that
The non-volatile computer readable storage medium storing program for executing is stored with computer executable instructions, and the computer executable instructions are by one
Or during multiple computing devices, it may be such that the above-mentioned 3D human bodies based on single photo of one or more of computing devices are built
Mould method.
It is and pre- after the coordinate by obtaining the key point in single photo in technical scheme provided in an embodiment of the present invention
First create, after the distance of the key point in skeleton point and photo in standardized human body's model, after alignment skeleton point and key point
Basic manikin is generated, further according to base texture data corresponding with the dermatoglyph of face in photo are obtained, according to basis
Manikin and base texture data generation 3D manikins, therefore can pass through one relative to prior art, the embodiment of the present invention
Open photo and realize 3D Human Modelings, and have bone and muscle systems support in model, expression and action can be produced, can also be entered
The secondary editor of row, modeling speed is fast, and reduction degree precision is high.
Brief description of the drawings
Fig. 1 is a kind of flow of one embodiment of the 3D human body modeling methods based on single photo in the embodiment of the present invention
Schematic diagram；
Fig. 2 is a kind of another embodiment program mould of the 3D Human Modeling devices based on single photo in the embodiment of the present invention
Block schematic diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, the every other implementation that those skilled in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is an a kind of reality of the 3D human body modeling methods based on single photo in the embodiment of the present invention
Apply the schematic flow sheet of example.As shown in figure 1, including：
Step 100, a photo is obtained, the photo is parsed, marks the key point of human body in the photo, counted
Calculate the space coordinates of the key point；
Skeleton point in step 200, standardized human body's model for being pre-created of acquisition and the key point in the photo away from
From rear, the skeleton point that aligns after the key point with generating basic manikin；
Basic textures in standardized human body's model that step 300, acquisition are pre-created, by the basic textures and the photograph
After the dermatoglyph of human body carries out mathematic interpolation in piece, merged using edge gateway, generate base texture data；
Step 400, according to the basic manikin and the base texture data generate 3D manikins.
When it is implemented, the photo obtained in step 100, the wherein somatic data in photo must be in view-finders just
Centre, the shadow relation of photo is uniform, and brightness meets certain luminance threshold, and luminance threshold can voluntarily be set.The shooting of photo
Angle is positioned at 90 degree of human body front, the angle of level shooting, is then inputted photo in the standardized human body's model being pre-created,
A progress bar occurs in terminal, generates a 3D model in a short time, and in the application scenarios, the mould of generation
Type can control the angle of screen touch point Controlling model with 360 ° of rotations.
Marked automatically based on human body key message point in step 200, the 3D that information point is analyzed by calculating is three-dimensional
Space coordinates, (landmark) information point is marked to be projected back in 3D surfaces 2D.Under the guiding marked automatically, 3D models constantly change
Generation deformation, with each 3D faces grid of accurate matched data collection.
It is introduced in step 300 so that human body is face as an example, in facial textures texture processing, in locations of structures relation
All in the case of matching accurately, allow you to go out the basic textures of model and carry out mathematic interpolation with the dermatoglyph in the photo obtained,
Merged using edge gateway, generation and the close dermatoglyph of photo, and illumination relation.I.e.：Face texture is first obtained,
One and the approximate basic textures of face texture and color value are automatically generated on the basis of face texture, carries out UV automatic drafting
And fusion；UV corresponds to each key message point of face automatically.Wherein UV refers to the texture in three-dimensional modeling.In three-dimensional modeling
" UV " can be regarded as " skin " of three-dimensional model, " skin " is deployed and then carried out the drafting on two dimensional surface and assigns object
Real 3D faceforms are built by model and data texturing in step 400.
Alternatively, before step 100, in addition to：It is pre-created a standardized human body's model for including skeleton point.Specifically
Ground, can pre-establish one includes skeletal system and the basic model of complete texture mapping.The basic model can be selected existing
One standardized human body's model.
Alternatively, a photo is obtained in step 100 includes：
Obtain a photo of shooting or obtain the photo imported, the photo includes human body information.Specifically, lead to
Cross mobile phone terminal or other computer equipment terminals, self-timer or import a photo, photo include human body information include bone and
Data texturing.
Alternatively, the key point of human body in the photo is marked in step 100, calculates the space coordinates bag of the key point
Include：
According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；
The difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created
Result of calculation, obtain the space coordinates of key point.
When it is implemented, because the information of the acquisition of a photo is inadequate, so we add deep learning algorithm, lead to
The study of 200 sample numbers is crossed, infers the position relationship of inaccurate key point, mathematic interpolation is carried out, obtains the standard of key point
True position relationship, so as to realize that 3D models are identical with the facial structure in photo.
Alternatively, a photo is obtained in step 100 also includes：
The scan data of somatic data is obtained, photo is generated according to the scan data.Specifically, scanner pair can be passed through
Face and human body are scanned, or according to technologies such as camera array or infrared scans, realize and the personage in reality is carried out
Two modelings.
The 3D human body modeling methods based on single photo in the embodiment of the present invention are described above, below to this
The 3D Human Modeling devices based on single photo in inventive embodiments are described, referring to Fig. 2, Fig. 2 is implementation of the present invention
A kind of another embodiment program module schematic diagram of the 3D Human Modeling devices based on single photo in example, including：
Key point acquisition module 100, for obtaining a photo, the photo is parsed, marked in the photo
The key point of human body, calculate the space coordinates of the key point；
Basic model establishes module 200, for obtaining the skeleton point in the standardized human body's model being pre-created and the photograph
After the distance of key point in piece, the skeleton point that aligns after the key point with generating basic manikin；
Data texturing generation module 300, for obtaining the basic textures in the standardized human body's model being pre-created, by described in
After the dermatoglyph of basic textures and human body in the photo carries out mathematic interpolation, merged using edge gateway, generate base
Plinth data texturing；
3D manikins generation module 400, for being generated according to the basic manikin and the base texture data
3D manikins.
When it is implemented, the photo obtained, the wherein somatic data in photo must be in view-finder middle, photo
Shadow relation it is uniform, brightness meets certain luminance threshold, and luminance threshold can voluntarily be set.The shooting angle of photo is to be located at
90 degree of human body front, the angle of level shooting, then photo is inputted in the standardized human body's model being pre-created, the meeting in terminal
There is a progress bar, generate a 3D model in a short time, and in the application scenarios, the model of generation can be with 360 °
Rotation, it can control the angle of screen touch point Controlling model.
Marked automatically based on human body key message point, the 3D solid space coordinates of information point analyzed by calculating,
(landmark) information point is marked to be projected back in 3D surfaces 2D.Under the guiding marked automatically, the continuous iterative deformation of 3D models, with
Each 3D faces grid of accurate matched data collection.
It is introduced so that human body is face as an example, in facial textures texture processing, standard is all matched in locations of structures relation
In the case of really, allow you to go out the basic textures of model and carry out mathematic interpolation with the dermatoglyph in the photo obtained, use edge
Passage is merged, generation and the close dermatoglyph of photo, and illumination relation.I.e.：Face texture is first obtained, in facial line
One and the approximate basic textures of face texture and color value are automatically generated on the basis of reason, carries out UV automatic drafting and fusion；
UV corresponds to each key message point of face automatically.
Real 3D faceforms are built by model and data texturing.
Alternatively, described device also includes：
Module is pre-created, for being pre-created a standardized human body's model for including skeleton point.Specifically, can build in advance
Vertical one includes skeletal system and the basic model of complete texture mapping.An existing standardized human body can be selected in the basic model
Model.
Alternatively, the key point acquisition module is used for：
Shoot a photo or import a photo, the photo includes human body information.Specifically, by mobile phone terminal or
Other computer equipment terminals, one photo of self-timer or importing, photo, which includes human body information, includes bone and data texturing.
Alternatively, the key point acquisition module is additionally operable to：
According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；
The difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created
Result of calculation, obtain the space coordinates of key point.
When it is implemented, because the information of the acquisition of a photo is inadequate, so we add deep learning algorithm, lead to
The study of 200 sample numbers is crossed, infers the position relationship of inaccurate key point, mathematic interpolation is carried out, obtains the standard of key point
True position relationship, so as to realize that 3D models are identical with the facial structure in photo.
The embodiments of the invention provide a kind of non-volatile computer readable storage medium storing program for executing, computer-readable recording medium is deposited
Computer executable instructions are contained, the computer executable instructions are executed by one or more processors, for example, being retouched more than performing
Method and step S100 to step S400 in the Fig. 1 stated, realize the function of the module 100-400 in Fig. 2.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
The present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each implementation
Technical scheme described in example is modified, or carries out equivalent substitution to which part technical characteristic；And these modification or
Replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
- A kind of 1. 3D human body modeling methods based on single photo, it is characterised in that including：A photo is obtained, the photo is parsed, marks the key point of human body in the photo, calculates the key point Space coordinates；After the distance for obtaining the skeleton point and the key point in the photo in the standardized human body's model being pre-created, described in alignment Skeleton point after the key point with generating basic manikin；The basic textures in the standardized human body's model being pre-created are obtained, by the skin of the basic textures and human body in the photo After skin texture carries out mathematic interpolation, merged using edge gateway, generate base texture data；According to the basic manikin and base texture data generation 3D manikins.
- 2. the 3D human body modeling methods according to claim 1 based on single photo, it is characterised in that described to obtain one Photo, the photo is parsed, marks the key point of human body in the photo, calculate the key point space coordinates it Before, in addition to：It is pre-created a standardized human body's model for including skeleton point.
- 3. the 3D human body modeling methods according to claim 2 based on single photo, it is characterised in thatOne photo of the acquisition includes：Obtain a photo of shooting or obtain the photo imported, the photo includes human body information.
- 4. the 3D human body modeling methods according to claim 3 based on single photo, it is characterised in that described in the mark The key point of human body in photo, calculating the space coordinates of the key point includes：According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；The calculating of the difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created As a result, the space coordinates of key point is obtained.
- 5. the 3D human body modeling methods according to claim 4 based on single photo, it is characterised in that described to obtain one Photo also includes：The scan data of somatic data is obtained, photo is generated according to the scan data.
- A kind of 6. 3D Human Modeling devices based on single photo, it is characterised in that including：Key point acquisition module, for obtaining a photo, the photo is parsed, marks the pass of human body in the photo Key point, calculate the space coordinates of the key point；Basic model establishes module, for obtaining the skeleton point in the standardized human body's model being pre-created and the pass in the photo After the distance of key point, the skeleton point that aligns after the key point with generating basic manikin；Data texturing generation module, for obtaining the basic textures in the standardized human body's model being pre-created, by the basic patch After the dermatoglyph of figure and human body in the photo carries out mathematic interpolation, merged using edge gateway, generate base texture Data；3D manikin generation modules, for generating 3D human moulds according to the basic manikin and the base texture data Type.
- 7. the 3D Human Modeling devices according to claim 6 based on single photo, it is characterised in that described device is also wrapped Include：Module is pre-created, for being pre-created a standardized human body's model for including skeleton point.
- 8. the 3D Human Modeling devices according to claim 7 based on single photo, it is characterised in that the key point obtains Modulus block is used for：Shoot a photo or import a photo, the photo includes human body information.
- 9. the 3D Human Modeling devices according to claim 8 based on single photo, it is characterised in that the key point obtains Modulus block is additionally operable to：According to the study of several key point samples, the space coordinates of inaccurate key point is simulated；The calculating of the difference of skeleton point in the position relationship of inaccurate key point and the standardized human body's model being pre-created As a result, the space coordinates of key point is obtained.
- A kind of 10. non-volatile computer readable storage medium storing program for executing, it is characterised in that the non-volatile computer readable storage medium Matter is stored with computer executable instructions, when the computer executable instructions are executed by one or more processors, may be such that institute State the 3D human body modeling methods based on single photo described in one or more processors perform claim requirement any one of 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710803000.9A CN107578469A (en) | 2017-09-08 | 2017-09-08 | A kind of 3D human body modeling methods and device based on single photo |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710803000.9A CN107578469A (en) | 2017-09-08 | 2017-09-08 | A kind of 3D human body modeling methods and device based on single photo |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107578469A true CN107578469A (en) | 2018-01-12 |
Family
ID=61031559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710803000.9A Pending CN107578469A (en) | 2017-09-08 | 2017-09-08 | A kind of 3D human body modeling methods and device based on single photo |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107578469A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196679A (en) * | 2018-01-23 | 2018-06-22 | 河北中科恒运软件科技股份有限公司 | Gesture-capture and grain table method and system based on video flowing |
| CN110136243A (en) * | 2019-04-09 | 2019-08-16 | 五邑大学 | A kind of three-dimensional facial reconstruction method and its system, device, storage medium |
| CN110189408A (en) * | 2019-06-04 | 2019-08-30 | 西安科技大学 | It is a kind of that the system and method for human body appearance data is obtained according to human body photo |
| CN110443872A (en) * | 2019-07-22 | 2019-11-12 | 北京科技大学 | A kind of countenance synthesis method having dynamic texture details |
| CN111861822A (en) * | 2020-06-03 | 2020-10-30 | 四川大学华西医院 | Patient model construction method, equipment and medical education system |
| CN113111861A (en) * | 2021-05-12 | 2021-07-13 | 北京深尚科技有限公司 | Face texture feature extraction method, 3D face reconstruction method, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968892A (en) * | 2009-07-28 | 2011-02-09 | 上海冰动信息技术有限公司 | Method for automatically adjusting three-dimensional face model according to one face picture |
| CN103942829A (en) * | 2014-04-02 | 2014-07-23 | 上海交通大学 | Single-image human body three-dimensional posture reconstruction method |
| CN104376594A (en) * | 2014-11-25 | 2015-02-25 | 福建天晴数码有限公司 | Three-dimensional face modeling method and device |
| US20150186713A1 (en) * | 2013-12-31 | 2015-07-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for emotion and behavior recognition |
| CN105719326A (en) * | 2016-01-19 | 2016-06-29 | 华中师范大学 | Realistic face generating method based on single photo |
-
2017
- 2017-09-08 CN CN201710803000.9A patent/CN107578469A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968892A (en) * | 2009-07-28 | 2011-02-09 | 上海冰动信息技术有限公司 | Method for automatically adjusting three-dimensional face model according to one face picture |
| US20150186713A1 (en) * | 2013-12-31 | 2015-07-02 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for emotion and behavior recognition |
| CN103942829A (en) * | 2014-04-02 | 2014-07-23 | 上海交通大学 | Single-image human body three-dimensional posture reconstruction method |
| CN104376594A (en) * | 2014-11-25 | 2015-02-25 | 福建天晴数码有限公司 | Three-dimensional face modeling method and device |
| CN105719326A (en) * | 2016-01-19 | 2016-06-29 | 华中师范大学 | Realistic face generating method based on single photo |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108196679A (en) * | 2018-01-23 | 2018-06-22 | 河北中科恒运软件科技股份有限公司 | Gesture-capture and grain table method and system based on video flowing |
| CN110136243A (en) * | 2019-04-09 | 2019-08-16 | 五邑大学 | A kind of three-dimensional facial reconstruction method and its system, device, storage medium |
| CN110189408A (en) * | 2019-06-04 | 2019-08-30 | 西安科技大学 | It is a kind of that the system and method for human body appearance data is obtained according to human body photo |
| CN110443872A (en) * | 2019-07-22 | 2019-11-12 | 北京科技大学 | A kind of countenance synthesis method having dynamic texture details |
| CN111861822A (en) * | 2020-06-03 | 2020-10-30 | 四川大学华西医院 | Patient model construction method, equipment and medical education system |
| CN111861822B (en) * | 2020-06-03 | 2023-11-21 | 四川大学华西医院 | Patient model construction method, equipment and medical education system |
| CN113111861A (en) * | 2021-05-12 | 2021-07-13 | 北京深尚科技有限公司 | Face texture feature extraction method, 3D face reconstruction method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107578469A (en) | A kind of 3D human body modeling methods and device based on single photo | |
| US11037281B2 (en) | Image fusion method and device, storage medium and terminal | |
| CN109872397B (en) | Three-dimensional reconstruction method of airplane parts based on multi-view stereo vision | |
| CN107705355A (en) | A kind of 3D human body modeling methods and device based on plurality of pictures | |
| CN107067429A (en) | Video editing system and method that face three-dimensional reconstruction and face based on deep learning are replaced | |
| CN103971408B (en) | Three-dimensional facial model generating system and method | |
| WO2015188684A1 (en) | Three-dimensional model reconstruction method and system | |
| JP5206366B2 (en) | 3D data creation device | |
| CN107484428B (en) | Method for displaying objects | |
| CN109003325A (en) | A kind of method of three-dimensional reconstruction, medium, device and calculate equipment | |
| WO2023284713A1 (en) | Three-dimensional dynamic tracking method and apparatus, electronic device and storage medium | |
| CN109816784B (en) | Method and system for three-dimensional reconstruction of human body and medium | |
| CN111652123B (en) | Image processing and image synthesizing method, device and storage medium | |
| CN112242004B (en) | AR scene virtual engraving method and system based on illumination rendering | |
| KR101759188B1 (en) | the automatic 3D modeliing method using 2D facial image | |
| CN104599317A (en) | Mobile terminal and method for achieving 3D (three-dimensional) scanning modeling function | |
| CN107578435A (en) | A kind of picture depth Forecasting Methodology and device | |
| CN108062788A (en) | A kind of three-dimensional rebuilding method, device, equipment and medium | |
| CN107330980A (en) | A kind of virtual furnishings arrangement system based on no marks thing | |
| CN111127642A (en) | Human face three-dimensional reconstruction method | |
| CN113223137B (en) | Generation method and device of perspective projection human face point cloud image and electronic equipment | |
| CN108010122A (en) | A kind of human 3d model rebuilds the method and system with measurement | |
| CN111742352B (en) | Method for modeling three-dimensional object and electronic equipment | |
| KR100623666B1 (en) | Method for manufacturing three-dimensional geographic information system digital image drawing using digital photommetry and non prism total station | |
| CN116310188B (en) | Virtual city generation method and storage medium based on instance segmentation and building reconstruction |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181101 Address after: 518000 B street, Taurus Plaza, Taoyuan Road, Nanshan District Nantou street, Shenzhen, Guangdong 2402 Applicant after: Shenzhen feather Trace Technology Co., Ltd. Address before: 518000 B 2402, Taurus Plaza, Taoyuan Road, Nanshan, Shenzhen, Guangdong Applicant before: Ming Li Applicant before: Guo Rui |
|
| TA01 | Transfer of patent application right |