CN113436350A - Three-dimensional model generation method and system - Google Patents

Three-dimensional model generation method and system Download PDF

Info

Publication number
CN113436350A
CN113436350A CN202110765376.1A CN202110765376A CN113436350A CN 113436350 A CN113436350 A CN 113436350A CN 202110765376 A CN202110765376 A CN 202110765376A CN 113436350 A CN113436350 A CN 113436350A
Authority
CN
China
Prior art keywords
dimensional
target object
dimensional data
model
dimensional model
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
Application number
CN202110765376.1A
Other languages
Chinese (zh)
Inventor
林钦
周晖
周波
胡锦晖
龚飞
叶伟
张�浩
刘凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Onew Technology Co ltd
Original Assignee
Wuhan Onew Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Onew Technology Co ltd filed Critical Wuhan Onew Technology Co ltd
Priority to CN202110765376.1A priority Critical patent/CN113436350A/en
Publication of CN113436350A publication Critical patent/CN113436350A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00Manipulating 3D models or images for computer graphics
    • G06T19/20Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/10Geometric CAD
    • G06F30/15Vehicle, aircraft or watercraft design
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00Details relating to CAD techniques
    • G06F2111/20Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00Indexing scheme for image data processing or generation, in general
    • G06T2200/04Indexing scheme for image data processing or generation, in general involving 3D image data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20Indexing scheme for editing of 3D models
    • G06T2219/2021Shape modification

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Architecture (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The invention provides a three-dimensional model generation method and a system, comprising the following steps: s1, constructing a cloud model library of standard components; s2, acquiring three-dimensional data of the target object in a certain posture, and screening; s3, matching the three-dimensional data of the target object meeting the preset conditions in a certain posture with a cloud model library of a standard component; s4, acquiring three-dimensional data of the target object in the next pose, and splicing and/or completing the three-dimensional model of the target object according to the three-dimensional data of the target object in the pose and the three-dimensional data of the target object in the previous pose; and S5, screening the three-dimensional data of the completed target object according to the preset conditions. According to the method and the device, the target object can be rapidly and three-dimensionally modeled based on the standard component cloud model library, so that the three-dimensional modeling speed is greatly improved, the three-dimensional model is ensured to be consistent with the object, the modeling period is further reduced, and the application range of the method and the device is expanded.

Description

Three-dimensional model generation method and system
Technical Field
The invention relates to the technical field of computers, in particular to a three-dimensional model generation method and a three-dimensional model generation system.
Background
The three-dimensional model has wide application prospects in the fields of medical treatment, buildings, electronic games, construction of virtual scenes based on VR (virtual reality)/AR (augmented reality) technology and the like. At present, an object three-dimensional model is obtained by scanning a depth image of a real object, and then processing the depth image by a three-dimensional modeling tool to construct the three-dimensional model of the real object.
However, the above method has the following disadvantages: 1. a single real object needs to be scanned, then three-dimensional modeling is carried out, and the modeling period is long; 2. if the real object cannot be scanned in all directions, the three-dimensional model obtained through final modeling has large deviation with the real object, and the expected effect cannot be obtained when the three-dimensional model is applied to a specific field.
Disclosure of Invention
The invention aims to provide a three-dimensional model generation method and a three-dimensional model generation system, which can complete rapid three-dimensional modeling of a target object based on a standard cloud model library, thereby greatly improving the three-dimensional modeling rate, ensuring that the three-dimensional model conforms to the object, further reducing the modeling period and expanding the application range of the three-dimensional model.
In one aspect, the present invention provides a method for generating a three-dimensional model, which includes the following steps:
s1, acquiring a three-dimensional model of the standard component, and constructing a cloud model library of the standard component according to the three-dimensional model of the standard component;
s2, acquiring three-dimensional data of the target object in a certain pose, screening the three-dimensional data according to preset conditions, entering the next step if the three-dimensional data of the target object in the pose meets the preset conditions, acquiring the three-dimensional data of the target object in the other pose again if the three-dimensional data does not meet the preset conditions, screening the acquired three-dimensional data again according to the preset conditions until the three-dimensional data of the target object in the certain pose meets the preset conditions, and entering the next step;
s3, matching the three-dimensional data of the target object meeting the preset conditions in a certain posture with a cloud model library of a standard component; if the three-dimensional data of the target object is not matched with the three-dimensional model data of any standard part in the cloud model library of the standard part, entering the next step;
s4, acquiring three-dimensional data of the target object in the next pose, and splicing and/or completing the three-dimensional model of the target object according to the three-dimensional data of the target object in the pose and the three-dimensional data of the target object in the previous pose to acquire the three-dimensional data of the target object after being completed;
and S5, screening the three-dimensional data of the completed target object according to the preset conditions.
Preferably, in step S1, the method for obtaining the three-dimensional model of the standard component includes: and carrying out three-dimensional scanning on the standard component to obtain three-dimensional image information of the standard component, and then constructing a three-dimensional model by adopting a three-dimensional modeling tool, or directly calling the three-dimensional model of the standard component from an existing database.
Preferably, in step S2, the three-dimensional data includes: one or more items of surface texture, color, acquisition point, depth, variety, spatial position three-dimensional data and the like of the target object.
Preferably, in step S4, the process of "splicing and/or complementing the three-dimensional data of the target object in the pose and the three-dimensional data of the target object in the previous pose" includes:
acquiring a three-dimensional model of the target object under the current pose according to the three-dimensional data of the target object under the current pose, dividing the three-dimensional model into a plurality of cells, acquiring a three-dimensional model of the target object under the previous pose according to the three-dimensional data of the target object under the previous pose, and dividing the three-dimensional model into a plurality of cells;
comparing the cell of the three-dimensional model of the target real object in the current pose with the cell of the three-dimensional model of the target real object in the previous pose to obtain the difference between the two groups of three-dimensional models, and determining the area corresponding to the difference on the three-dimensional model of the target real object in the current pose and the area corresponding to the difference on the three-dimensional model of the target real object in the previous pose;
respectively acquiring the characteristics of each cell and the curvature between adjacent blocks in the area corresponding to the difference on the three-dimensional model of the target object in the current pose, respectively acquiring the characteristics of each cell and the curvature between adjacent blocks in the area corresponding to the difference on the three-dimensional model of the target object in the previous pose, and splicing and/or complementing the two groups of three-dimensional models according to the characteristics of the cells and the curvature between the adjacent blocks in the area corresponding to the difference of the two groups of three-dimensional models to obtain the three-dimensional model of the finished target object, wherein the corresponding three-dimensional data is the three-dimensional data of the finished target object.
Preferably, the differences include: one or more of the color, depth, intensity, etc. of the cells.
Preferably, step S5 further includes: and if the three-dimensional data of the completed target object meet the preset conditions, outputting a three-dimensional model of the completed target object, and uploading the three-dimensional model of the completed target object to a cloud model library of a standard component.
Preferably, the standard elements comprise various standard workpieces used in the construction/manufacturing field.
Preferably, the standard component comprises an automobile part.
There is also provided a three-dimensional modeling system for implementing the three-dimensional model generation method, including:
the cloud model library is used for storing a three-dimensional model of the standard part;
the three-dimensional data acquisition unit is used for acquiring three-dimensional data of the target real object at different poses;
the three-dimensional data screening unit is connected with the three-dimensional data acquisition unit and is used for screening the three-dimensional data of the target object according to preset conditions;
the model matching unit is connected with the three-dimensional data screening unit and used for matching the screened three-dimensional data of the target object meeting the preset conditions with the cloud model library of the standard part, and when the three-dimensional data of the target object is matched with the three-dimensional model data of one standard part in the cloud model library of the standard part, the three-dimensional model of the standard part is directly output and is used as the three-dimensional model of the target object;
and the model supplementing unit is connected with the three-dimensional data screening unit and the model matching unit and is used for splicing and/or supplementing the three-dimensional model of the target object according to the three-dimensional data of the target object which does not pass the screening so as to obtain the three-dimensional model of the target object after the completion, and screening the three-dimensional data of the target object after the completion according to the preset conditions.
Preferably, when the three-dimensional data of the completed target object meets the preset condition, the model matching unit outputs the three-dimensional model of the completed target object.
The invention has the following beneficial effects:
according to the method, the standard part cloud model base is established firstly, the standard part cloud model base is compared with the three-dimensional data of the target object, if the three-dimensional data of the target object is matched with the standard part cloud model base, the three-dimensional model of the standard part is directly output and serves as the three-dimensional model of the target object, if the three-dimensional data of the target object is not matched with the three-dimensional model base, the three-dimensional model of the target object is intelligently completed according to the three-dimensional data of the target object under different poses, therefore, the three-dimensional modeling speed is greatly improved, the acquired object three-dimensional model is uploaded to the standard part cloud model base in time for subsequent direct calling, the modeling period is further reduced, and the application range of the standard part cloud model base is expanded.
Drawings
FIG. 1 is a flow chart of a three-dimensional model generation method of the present invention;
FIG. 2 is a schematic diagram of the effect of stitching and/or completing a three-dimensional model according to the present invention;
FIG. 3 is a schematic diagram of a three-dimensional model generation system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be further described with reference to the accompanying drawings.
Example 1:
as shown in fig. 1, the three-dimensional model generation method provided in this embodiment includes the following steps:
s1, acquiring a three-dimensional model of the standard component, and constructing a cloud model library of the standard component according to the three-dimensional model of the standard component; the standard part comprises various standard workpieces used in the fields of construction, manufacturing and the like, such as automobile parts, components and the like, and the method for acquiring the three-dimensional model of the standard part comprises the following steps: three-dimensional scanning is carried out on the standard component to obtain three-dimensional image information of the standard component, and then a three-dimensional modeling tool is adopted to construct a three-dimensional model, or the three-dimensional model of the standard component is directly called from an existing database;
s2, acquiring three-dimensional data of the target object in a certain pose (namely an initial pose), screening the three-dimensional data according to preset conditions, entering the next step if the three-dimensional data of the target object in the pose meets the preset conditions, acquiring the three-dimensional data of the target object in the other pose if the three-dimensional data of the target object in the pose does not meet the preset conditions, screening the acquired three-dimensional data again according to the preset conditions, repeating the steps until the three-dimensional data of the target object in the certain pose meets the preset conditions, and entering the next step;
the target real object comprises various workpieces used in the fields of construction, manufacturing and the like, and the target real object can be scanned by tools such as a three-dimensional scanner and the like to obtain three-dimensional data of the target real object, and meanwhile, the three-dimensional data comprises: one or more items of surface texture, color, acquisition point, depth, variety, spatial position three-dimensional data and the like of the target object, wherein the preset conditions comprise: the depth reaches a preset value, the color and the texture are approximate, and the like;
s3, matching the three-dimensional data of the target object meeting the preset conditions in a certain posture with a cloud model library of a standard component;
if the three-dimensional data of the target object is matched with the three-dimensional model data of one standard part in the cloud model library of the standard part, directly outputting the three-dimensional model of the standard part, and taking the three-dimensional model as the three-dimensional model of the target object;
if the three-dimensional data of the target object is not matched with the three-dimensional model data of any standard part in the cloud model library of the standard part, the situation that the three-dimensional data of the target object is incomplete under the pose is shown, and the next step is carried out;
s4, acquiring three-dimensional data of the target object in the next pose, and splicing and/or completing the three-dimensional model of the target object according to the three-dimensional data of the target object in the pose and the three-dimensional data of the target object in the previous pose to acquire the three-dimensional data of the target object after being completed;
in this embodiment, as shown in fig. 2, the process of "splicing and/or completing the three-dimensional data of the target real object in the pose with the three-dimensional data of the target real object in the previous pose" includes:
acquiring a three-dimensional model of the target object under the current pose according to the three-dimensional data of the target object under the current pose, dividing the three-dimensional model into a plurality of cells 1, acquiring a three-dimensional model of the target object under the previous pose according to the three-dimensional data of the target object under the previous pose, and dividing the three-dimensional model into a plurality of cells 2;
comparing the cell 1 of the three-dimensional model of the target real object in the current pose with the cell 2 of the three-dimensional model of the target real object in the previous pose to obtain the difference between the two groups of three-dimensional models, and determining the area corresponding to the difference on the three-dimensional model of the target real object in the current pose and the area corresponding to the difference on the three-dimensional model of the target real object in the previous pose; the differences include: one or more of the color, depth, intensity, etc. of the cells;
respectively acquiring the features of each cell 1 and the curvatures between adjacent blocks in the areas corresponding to the differences on the three-dimensional model of the target object at the current pose, respectively acquiring the features of each cell 2 and the curvatures between adjacent blocks in the areas corresponding to the differences on the three-dimensional model of the target object at the previous pose, splicing and/or complementing the two groups of three-dimensional models in a step-by-step recursive supplementation mode and the like according to the features of the cells and the curvatures between the adjacent blocks in the areas corresponding to the differences of the two groups of three-dimensional models (such as completing a part 3 and a part 4 in fig. 2), so as to acquire the three-dimensional model of the finished target object, wherein the corresponding three-dimensional data is the three-dimensional data of the finished target object;
s5, screening the three-dimensional data of the completed target object according to the preset conditions;
if the three-dimensional data of the completed target object meets the preset conditions, outputting a three-dimensional model of the completed target object, and uploading the three-dimensional model of the completed target object to a cloud model library of a standard part to supplement and update the cloud model library of the standard part, so that the three-dimensional data can be directly called subsequently;
and if the three-dimensional data of the completed target object does not meet the preset conditions, repeating the steps S2-S5.
Therefore, the three-dimensional model generation method of the embodiment can complete rapid three-dimensional modeling of the target object based on the standard cloud model library, that is, after comparison, if three-dimensional data of the target object is matched with the standard cloud model library, the three-dimensional model of the standard is directly output and serves as the three-dimensional model of the target object, and if the three-dimensional data of the target object is not matched with the three-dimensional model of the target object, the three-dimensional model of the target object is intelligently completed according to the three-dimensional data of the target object under different poses, so that the three-dimensional modeling speed is greatly increased, the three-dimensional model is ensured to be consistent with the object, the obtained object three-dimensional model is uploaded to the standard cloud model library in time for subsequent direct calling, the modeling period is further reduced, and the application range of the three-dimensional model is expanded.
Example 2:
the present embodiment provides a three-dimensional modeling system for implementing the three-dimensional model generation method described in embodiment 1, as shown in fig. 3, the three-dimensional modeling system includes:
a cloud model library 100 for storing three-dimensional models of standards;
a three-dimensional data acquisition unit 200 for acquiring three-dimensional data of the target real object at different poses;
the three-dimensional data screening unit 300 is connected with the three-dimensional data acquisition unit 200 and is used for screening the three-dimensional data of the target object according to preset conditions;
a model matching unit 400, connected to the three-dimensional data screening unit 300, for matching the screened three-dimensional data of the target object meeting the preset conditions with the cloud model library of the standard component, and when the three-dimensional data of the target object matches with the three-dimensional model data of one standard component in the cloud model library of the standard component, directly outputting the three-dimensional model of the standard component, and using the three-dimensional model as the three-dimensional model of the target object;
the model supplementing unit 500 is connected to the three-dimensional data screening unit 300 and the model matching unit 400, and is configured to splice and/or supplement the three-dimensional model of the target object according to the three-dimensional data of the target object that does not pass the screening to obtain a three-dimensional model of the target object after being completed, screen the three-dimensional data of the target object after being completed according to the preset condition, and when the three-dimensional data of the target object after being completed meets the preset condition, the model matching unit 400 outputs the three-dimensional model of the target object after being completed; preferably, the step of completing the splicing and/or completion is the same as the process of "splicing and/or completing the three-dimensional data of the target object in the pose with the three-dimensional data of the target object in the previous pose" in embodiment 1, and a burden is not required here.
In summary, the invention can complete the rapid three-dimensional modeling of the target object based on the standard cloud model library, that is, after comparison, if the three-dimensional data of the target object is matched with the standard cloud model library, the three-dimensional model of the standard is directly output and is used as the three-dimensional model of the target object, and if the three-dimensional data of the target object is not matched with the three-dimensional model of the target object, the three-dimensional model of the target object is intelligently completed according to the three-dimensional data of the target object at different poses, so that the three-dimensional modeling speed is greatly increased, the three-dimensional model is ensured to be consistent with the object, and the obtained object three-dimensional model is uploaded to the standard cloud model library in time for subsequent direct calling, thereby further reducing the modeling period and expanding the application range.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A three-dimensional model generation method is characterized by comprising the following steps:
s1, acquiring a three-dimensional model of the standard component, and constructing a cloud model library of the standard component according to the three-dimensional model of the standard component;
s2, acquiring three-dimensional data of the target object in a certain pose, screening the three-dimensional data according to preset conditions, entering the next step if the three-dimensional data of the target object in the pose meets the preset conditions, acquiring the three-dimensional data of the target object in the other pose again if the three-dimensional data does not meet the preset conditions, screening the acquired three-dimensional data again according to the preset conditions until the three-dimensional data of the target object in the certain pose meets the preset conditions, and entering the next step;
s3, matching the three-dimensional data of the target object meeting the preset conditions in a certain posture with a cloud model library of a standard component; if the three-dimensional data of the target object is not matched with the three-dimensional model data of any standard part in the cloud model library of the standard part, entering the next step;
s4, acquiring three-dimensional data of the target object in the next pose, and splicing and/or completing the three-dimensional model of the target object according to the three-dimensional data of the target object in the pose and the three-dimensional data of the target object in the previous pose to acquire the three-dimensional data of the target object after being completed;
and S5, screening the three-dimensional data of the completed target object according to the preset conditions.
2. The three-dimensional model generation method of claim 1, wherein in step S1, the method of obtaining the three-dimensional model of the standard part comprises: and carrying out three-dimensional scanning on the standard component to obtain three-dimensional image information of the standard component, and then constructing a three-dimensional model by adopting a three-dimensional modeling tool, or directly calling the three-dimensional model of the standard component from an existing database.
3. The three-dimensional model generation method according to claim 1, wherein in step S2, the three-dimensional data includes: one or more items of surface texture, color, acquisition point, depth, variety, spatial position three-dimensional data and the like of the target object.
4. The three-dimensional model generation method according to claim 1, wherein the process of "splicing and/or complementing the three-dimensional data of the target object in the pose with the three-dimensional data of the target object in the previous pose" in step S4 includes:
acquiring a three-dimensional model of the target object under the current pose according to the three-dimensional data of the target object under the current pose, dividing the three-dimensional model into a plurality of cells, acquiring a three-dimensional model of the target object under the previous pose according to the three-dimensional data of the target object under the previous pose, and dividing the three-dimensional model into a plurality of cells;
comparing the cell of the three-dimensional model of the target real object in the current pose with the cell of the three-dimensional model of the target real object in the previous pose to obtain the difference between the two groups of three-dimensional models, and determining the area corresponding to the difference on the three-dimensional model of the target real object in the current pose and the area corresponding to the difference on the three-dimensional model of the target real object in the previous pose;
respectively acquiring the characteristics of each cell and the curvature between adjacent blocks in the area corresponding to the difference on the three-dimensional model of the target object in the current pose, respectively acquiring the characteristics of each cell and the curvature between adjacent blocks in the area corresponding to the difference on the three-dimensional model of the target object in the previous pose, and splicing and/or complementing the two groups of three-dimensional models according to the characteristics of the cells and the curvature between the adjacent blocks in the area corresponding to the difference of the two groups of three-dimensional models to obtain the three-dimensional model of the finished target object, wherein the corresponding three-dimensional data is the three-dimensional data of the finished target object.
5. The three-dimensional model generation method of claim 4, wherein the difference comprises: one or more of the color, depth, intensity, etc. of the cells.
6. The three-dimensional model generation method of claim 1, wherein step S5 further comprises: and if the three-dimensional data of the completed target object meet the preset conditions, outputting a three-dimensional model of the completed target object, and uploading the three-dimensional model of the completed target object to a cloud model library of a standard component.
7. A three-dimensional model generation method according to claim 1, wherein said standard parts include various standard works used in the construction/manufacturing field.
8. The method of generating a three-dimensional model according to claim 7, wherein the standard component includes an automobile part.
9. A three-dimensional modeling system that implements the three-dimensional model generation method according to any one of claims 1 to 8, comprising:
the cloud model library is used for storing a three-dimensional model of the standard part;
the three-dimensional data acquisition unit is used for acquiring three-dimensional data of the target real object at different poses;
the three-dimensional data screening unit is connected with the three-dimensional data acquisition unit and is used for screening the three-dimensional data of the target object according to preset conditions;
the model matching unit is connected with the three-dimensional data screening unit and used for matching the screened three-dimensional data of the target object meeting the preset conditions with the cloud model library of the standard part, and when the three-dimensional data of the target object is matched with the three-dimensional model data of one standard part in the cloud model library of the standard part, the three-dimensional model of the standard part is directly output and is used as the three-dimensional model of the target object;
and the model supplementing unit is connected with the three-dimensional data screening unit and the model matching unit and is used for splicing and/or supplementing the three-dimensional model of the target object according to the three-dimensional data of the target object which does not pass the screening so as to obtain the three-dimensional model of the target object after the completion, and screening the three-dimensional data of the target object after the completion according to the preset conditions.
10. The system of claim 9, wherein the model matching unit outputs the three-dimensional model of the refined target object when the three-dimensional data of the refined target object meets the preset condition.
CN202110765376.1A 2021-07-07 2021-07-07 Three-dimensional model generation method and system Pending CN113436350A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110765376.1A CN113436350A (en) 2021-07-07 2021-07-07 Three-dimensional model generation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110765376.1A CN113436350A (en) 2021-07-07 2021-07-07 Three-dimensional model generation method and system

Publications (1)

Publication Number Publication Date
CN113436350A true CN113436350A (en) 2021-09-24

Family

ID=77759335

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110765376.1A Pending CN113436350A (en) 2021-07-07 2021-07-07 Three-dimensional model generation method and system

Country Status (1)

Country Link
CN (1) CN113436350A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113989456A (en) * 2021-12-23 2022-01-28 苏州工业园区测绘地理信息有限公司 Automatic construction method of rail transit station space three-dimensional model based on GIS data
WO2022142908A1 (en) * 2020-12-28 2022-07-07 中兴通讯股份有限公司 Three-dimensional model generation method, xr device and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140320491A1 (en) * 2013-04-26 2014-10-30 Tsinghua University Method And System For Three-Dimensionally Reconstructing Non-Rigid Body Based On Multi-Depth-Map
WO2015188684A1 (en) * 2014-06-12 2015-12-17 深圳奥比中光科技有限公司 Three-dimensional model reconstruction method and system
CN111739161A (en) * 2020-07-23 2020-10-02 之江实验室 Human body three-dimensional reconstruction method and device under shielding condition and electronic equipment
CN111750805A (en) * 2020-07-06 2020-10-09 山东大学 Three-dimensional measuring device and method based on binocular camera imaging and structured light technology
CN112802111A (en) * 2021-04-01 2021-05-14 中智行科技有限公司 Object model construction method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140320491A1 (en) * 2013-04-26 2014-10-30 Tsinghua University Method And System For Three-Dimensionally Reconstructing Non-Rigid Body Based On Multi-Depth-Map
WO2015188684A1 (en) * 2014-06-12 2015-12-17 深圳奥比中光科技有限公司 Three-dimensional model reconstruction method and system
CN111750805A (en) * 2020-07-06 2020-10-09 山东大学 Three-dimensional measuring device and method based on binocular camera imaging and structured light technology
CN111739161A (en) * 2020-07-23 2020-10-02 之江实验室 Human body three-dimensional reconstruction method and device under shielding condition and electronic equipment
CN112802111A (en) * 2021-04-01 2021-05-14 中智行科技有限公司 Object model construction method and device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022142908A1 (en) * 2020-12-28 2022-07-07 中兴通讯股份有限公司 Three-dimensional model generation method, xr device and storage medium
CN113989456A (en) * 2021-12-23 2022-01-28 苏州工业园区测绘地理信息有限公司 Automatic construction method of rail transit station space three-dimensional model based on GIS data

Similar Documents

Publication Publication Date Title
CN113436350A (en) Three-dimensional model generation method and system
CN110335345B (en) Curtain wall node rendering method and device, computer equipment and storage medium
CN109844818A (en) For establishing the method and associated system of the deformable 3d model of element
CN113538706B (en) Digital sand table-based house scene display method, device, equipment and storage medium
KR101397476B1 (en) Virtual cosmetic surgery method by 3d virtual cosmetic surgery device
CN113370217A (en) Method for recognizing and grabbing object posture based on deep learning for intelligent robot
Pacheco et al. Reconstruction of high resolution 3D objects from incomplete images and 3D information
JP2006107145A (en) Face shape modeling system and face shape modeling method
CN116476070B (en) Method for adjusting scanning measurement path of large-scale barrel part local characteristic robot
CN115661367B (en) Dynamic hybrid deformation modeling method and system based on photo collection
CN111179408A (en) Method and apparatus for three-dimensional modeling
CN113989680A (en) Automatic building three-dimensional scene construction method and system
CN113446940A (en) Point cloud scanning method, device and equipment
CN113066188A (en) Three-dimensional simulation method and equipment for outdoor construction operation
CN116740300B (en) Multi-mode-based prime body and texture fusion furniture model reconstruction method
CN112750193A (en) Power transmission equipment three-dimensional model modeling method, device, equipment and storage medium
CN112927368B (en) Human body clothes picture editing and video generating method based on three-dimensional parameter expression
CN113808252B (en) Three-dimensional model step-by-step reconstruction method based on interactive labels and macros
CN114119835B (en) Hard surface model processing method and device and electronic equipment
US11948252B2 (en) Three-dimensional mesh generator based on two-dimensional image
CN116071501A (en) Three-dimensional model generation and assembly method and system based on hand-drawn sketch
Fuxiong A Novel Virtual Reality (VR) based Intelligent Guiding System
Kasper et al. Semi automatic object modeling for a service robot
CN117592511A (en) NeRF model construction method, neRF model construction device, neRF model construction equipment and storage medium
Tang et al. Skeleton-guided generation of synthetic noisy point clouds from as-built BIM to improve indoor scene understanding

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