CN107680074A - The method and apparatus of geometrical reconstruction object - Google Patents
The method and apparatus of geometrical reconstruction object Download PDFInfo
- Publication number
- CN107680074A CN107680074A CN201610625552.0A CN201610625552A CN107680074A CN 107680074 A CN107680074 A CN 107680074A CN 201610625552 A CN201610625552 A CN 201610625552A CN 107680074 A CN107680074 A CN 107680074A
- Authority
- CN
- China
- Prior art keywords
- color
- estimated
- camera
- camera posture
- corresponding color
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of method and apparatus of geometrical reconstruction object.This method includes：According to depth map and corresponding color diagram, camera posture is estimated；Based on estimated camera posture, according to depth map, voxel blocks signed distance function TSDF values in acquisition three dimensions；And according to the TSDF values obtained, object described in geometrical reconstruction；Wherein, according to depth map and corresponding color diagram, camera posture is estimated by solving optimization problem；Wherein, in the optimization problem, cost function is relevant with following factors：Pass through the quadratic sum of three-dimensional point in the camera coordinates space of the present frame after the camera pose adjustment to be estimated and the distance of the corresponding three-dimensional points in the above global coordinate space of all frames and pass through after the camera pose adjustment to be estimated color on present frame corresponding color figure of three-dimensional point in the above global coordinate space of all frames and the above quadratic sum of the distance metric of the corresponding color in the global coordinate space of all frames.
Description
Technical field
This invention relates generally to image processing field.Specifically, being capable of geometrical reconstruction object the present invention relates to one kind
Method and apparatus.
Background technology
Nowadays, digitized three dimensional object has been widely used for the various fields of people's daily life, for example strengthens
Reality, digital museum, 3 D-printing etc..Occur the portable depth camera such as Kinect in recent years, can be easily
From different position and direction sampling depth images and coloured image.With the popularization of this kind equipment, people can be more easily
Build digitized three dimensional object.
The digitized process of three dimensional object is roughly divided into two steps：Geometrical reconstruction and color mapping.It is in general, three-dimensional
The geological information of object is obtained based on depth image, and key point therein is to estimate the camera posture of each amplitude deepness image；
And the color of three-dimensional point is then according to the projection relation between threedimensional model and two dimensional image, according to respective pixel in coloured image
Color determines.In traditional method, what above-mentioned two step was typically carried out respectively, only pass through camera posture phase therebetween
Mutual correlation.For geometrical reconstruction, the camera posture of each amplitude deepness image is estimated based on the geometric match between three-dimensional point cloud.
And mapped for color, the camera posture of each width coloured image can obtain in the following manner.Simplest method directly will
The camera posture of coloured image is set to the camera posture with the immediate depth image of its acquisition time.Due to corresponding depth map
The acquisition time of picture and coloured image is very close, and during gathered data very slowly, therefore the movement of depth camera is typically
This method is rational for principle.But the camera posture estimated based on depth information be not it is very accurate, in
It is that fuzzy phenomenon generally occurs in the color mapping result that this method obtains.In order to improve the performance of color mapping, some
The camera posture that method attempts to estimate geometrical reconstruction is modified.The typical thought of one of which is to define one by colour
Optimization problem of the camera posture of image as variable to be solved, using the solution mode of iteration, and estimates geometrical reconstruction
Initial value of the camera posture gone out as solution procedure.More preferable color mapping effect can be obtained using revised camera posture
Fruit, but had differences between the camera posture of corresponding depth image and coloured image, this can hinder follow-up processing procedure.
The content of the invention
The brief overview on the present invention is given below, to provide on the basic of certain aspects of the invention
Understand.It should be appreciated that this general introduction is not the exhaustive general introduction on the present invention.It is not intended to determine the pass of the present invention
Key or pith, nor is it intended to limit the scope of the present invention.Its purpose only provides some concepts in simplified form,
In this, as the preamble in greater detail discussed later.
The purpose of the present invention is to propose to a kind of method and apparatus of geometrical reconstruction object, above mentioned problem can solve the problem that.
To achieve these goals, according to an aspect of the invention, there is provided a kind of method of geometrical reconstruction object, is somebody's turn to do
Method includes：According to depth map and corresponding color diagram, camera posture is estimated；Based on estimated camera posture, according to depth
Scheme, voxel blocks signed distance function TSDF values in acquisition three dimensions；And according to the TSDF values obtained, geometrical reconstruction
The object；Wherein, according to depth map and corresponding color diagram, camera posture is estimated by solving optimization problem；Wherein, exist
In the optimization problem, cost function is relevant with following factors：Pass through the present frame after the camera pose adjustment to be estimated
Camera coordinates space in three-dimensional point and the distance of the corresponding three-dimensional points in the above global coordinate space of all frames square
With and pass through three-dimensional point before after the camera pose adjustment to be estimated in the global coordinate space of all frames current
Color and the quadratic sum of the distance metric of the corresponding color in the above global coordinate space of all frames on frame corresponding color figure.
According to another aspect of the present invention, there is provided a kind of equipment of geometrical reconstruction object, the equipment include：Camera appearance
State estimation unit, is configured as：According to depth map and corresponding color diagram, camera posture is estimated；TSDF values obtain device, by with
It is set to：Based on estimated camera posture, according to depth map, voxel blocks signed distance function TSDF in acquisition three dimensions
Value；And geometrical reconstruction device, it is configured as：According to the TSDF values obtained, object described in geometrical reconstruction；Wherein, camera appearance
State estimation unit is further configured to：, according to depth map and corresponding color diagram, estimate camera by solving optimization problem
Posture；Wherein, in the optimization problem, cost function is relevant with following factors：Pass through the camera posture to be estimated to adjust
Three-dimensional point in the camera coordinates space of present frame after whole and the corresponding three-dimensional points in the above global coordinate space of all frames
Distance quadratic sum and pass through before after the camera pose adjustment to be estimated in the global coordinate space of all frames
The distance of color of the three-dimensional point on present frame corresponding color figure and the corresponding color in the above global coordinate space of all frames
The quadratic sum of measurement.
In addition, according to another aspect of the present invention, additionally provide a kind of storage medium.The storage medium can including machine
The program code of reading, when performing described program code on message processing device, described program code causes at described information
Equipment is managed to perform according to the above method of the invention.
In addition, in accordance with a further aspect of the present invention, additionally provide a kind of program product.Described program product can including machine
The instruction of execution, when performing the instruction on message processing device, the instruction causes described information processing equipment to perform
According to the above method of the present invention.
Brief description of the drawings
With reference to the explanation of embodiments of the invention, can be more readily understood that below in conjunction with the accompanying drawings the present invention more than and
Other objects, features and advantages.Part in accompanying drawing is intended merely to show the principle of the present invention.In the accompanying drawings, identical or class
As technical characteristic or part will be represented using same or similar reference.In accompanying drawing：
Fig. 1 shows the flow chart of the method for geometrical reconstruction object according to an embodiment of the invention.
Fig. 2 shows the block diagram of the equipment of geometrical reconstruction object according to an embodiment of the invention.
Fig. 3 shows the schematic frame available for the computer for implementing method and apparatus according to an embodiment of the invention
Figure.
Embodiment
The one exemplary embodiment of the present invention is described in detail hereinafter in connection with accompanying drawing.Rise for clarity and conciseness
See, do not describe all features of actual embodiment in the description.It should be understood, however, that developing any this reality
It must be made during embodiment much specific to the decision of embodiment, to realize the objectives of developer,
For example, meet those restrictive conditions related to system and business, and these restrictive conditions may be with embodiment
It is different and change.In addition, it will also be appreciated that although development is likely to be extremely complex and time-consuming, to benefiting
For those skilled in the art of present disclosure, this development is only routine task.
Herein, it is also necessary to which explanation is a bit, in order to avoid having obscured the present invention because of unnecessary details, in the accompanying drawings
It illustrate only and according to the closely related apparatus structure of the solution of the present invention and/or processing step, and eliminate and the present invention
The little other details of relation.In addition, it may also be noted that described in the accompanying drawing of the present invention or a kind of embodiment
Element and the element that can be shown in one or more other accompanying drawings or embodiment of feature and feature be combined.
The flow of the method for geometrical reconstruction object according to an embodiment of the invention is described below with reference to Fig. 1.
Fig. 1 shows the flow chart of the method for geometrical reconstruction object according to an embodiment of the invention.As shown in figure 1, root
Comprise the following steps according to the method for embodiments of the invention：According to depth map and corresponding color diagram, camera posture (step is estimated
S1)；Based on estimated camera posture, according to depth map, voxel blocks signed distance function TSDF in acquisition three dimensions
It is worth (step S2)；According to the TSDF values obtained, object (step S3) described in geometrical reconstruction；Wherein, by solving optimization problem
, according to depth map and corresponding color diagram, to estimate camera posture；Wherein, in the optimization problem, cost function is with
Row factor is relevant：Pass through three-dimensional point in the camera coordinates space of the present frame after the camera pose adjustment to be estimated with above
The camera posture to be estimated of the quadratic sum of the distance of corresponding three-dimensional points in the global coordinate space of all frames and passing through is adjusted
Color of the three-dimensional point on present frame corresponding color figure before after whole in the global coordinate space of all frames is with above owning
The quadratic sum of the distance metric of corresponding color in the global coordinate space of frame.
In step sl, according to depth map and corresponding color diagram, camera posture is estimated.
Inventive point is to utilize depth map and color diagram simultaneously, common to estimate camera posture with reference to both information.Due to
It is proposed that optimization problem in consider the constraint of geometric match and colour consistency simultaneously, the camera posture estimated is more
It is accurate to add, and then can obtain more gratifying digitized result.
Camera posture can be estimated according to depth map and corresponding color diagram by solving optimization problem.Can be by repeatedly
The Gauss-Newton method in generation solves the optimization problem.
In the optimization problem, cost function is relevant with following factors：Pass through the camera pose adjustment to be estimated
Three-dimensional point in the camera coordinates space of present frame afterwards and the corresponding three-dimensional points in the above global coordinate space of all frames
The quadratic sum of distance and pass through before after the camera pose adjustment to be estimated in the global coordinate space of all frames three
The distance degree of color and corresponding color in the above global coordinate space of all frames of the dimension point on present frame corresponding color figure
The quadratic sum of amount.
Specifically, for the first amplitude deepness image, the three-dimensional in camera coordinates system corresponding to each valid pixel is calculated
Point position and its normal direction.According to the pass between the camera coordinates system of the first given amplitude deepness image and world coordinate system
System, three-dimensional point position and its normal direction are converted into world coordinate system.According to the throwing between model and the first width coloured image
Shadow relation, calculate the color of each three-dimensional point.
Similar with existing typical three dimensional object digitization system, directed distance is blocked in the global geological information use of model
Function (Truncated Signed Distance Function, TSDF) characterizes, and user pays close attention to each voxel in space
TSDF values are defined as should in the voxel that three dimensions calculates is relative to the depth value and depth map of camera based on camera posture
Directed distance between the depth value of voxel correspondence position, calculate for convenience, the distance value is truncated to one and pre-defined
Section in and be normalized.
Before input kth (k=2,3 ...) amplitude deepness image and coloured image, the data obtained are：Three-dimensional space
Between in each voxel TSDF values, three in the world coordinate system calculated based on the location of pixels u in (k-1) amplitude deepness image
Dimension point positionWith its normal directionAnd the projection relation based on model and coloured image calculate three
Dimension point colorAfter inputting kth amplitude deepness image and coloured image, calculate camera corresponding to each valid pixel and sit
Three-dimensional point position V in mark systemkAnd its normal direction N (u)k(u).We are needed based on above- mentioned information estimation kth amplitude deepness image
With the camera posture of coloured image, i.e., between the camera coordinates system and world coordinate system of kth amplitude deepness image and coloured image
Transformation matrix Tg,k。
Invention defines a unified Optimization Framework, cost function therein is formed by two.First cost item
Geometric match between the model model corresponding with kth amplitude deepness image that (k-1) amplitude deepness image is built before describing is closed
System, is defined as：
Wherein Tg,kVk(u) position of the three-dimensional point in world coordinate system corresponding to kth amplitude deepness image is represented,
Represent Tg,kVk(u) corresponding points in the model of preceding (k-1) amplitude deepness image structure, the corresponding relation of the two is by same three
Location of pixels in location of pixels u and (k-1) amplitude deepness image of the dimension point in kth amplitude deepness imageDetermine.Summation symbol
Each single item in number arrives square of the distance of plane for point, therefore introduces normal directionCan be according to right during summation
The angle for answering the distance between three-dimensional point to be less than between given threshold value, the normal direction of corresponding three-dimensional points is less than given threshold value etc. about
Beam is limited sum term.
Second cost item is used for the color and each point of the three-dimensional point in the model that (k-1) amplitude deepness image is built before describing
Uniformity in kth width coloured image between the color of subpoint, is defined as：
WhereinThree-dimensional point in the model that (k-1) amplitude deepness image is built before expression is in kth width depth
Position in the camera coordinates system of image and coloured image, H (p) represent the two-dimensional points for projecting to three-dimensional point in image, Fk(u)
Represent that kth width coloured image middle position is set to the color value of u pixel.Summation can be projected in kth width coloured image to all
The three-dimensional point of active position is carried out, can also be further according to the depth of projected position in the depth value and depth image calculated
The constraint that value can not differ too big is limited sum term.
Above-mentioned two cost item is carried out linear combination by us using suitable coefficient lambda, and final cost function is defined as：
E=E1+λE2
Wherein λ could be arranged to a fixed value, and a variable value can also be arranged to according to the fog-level of coloured image, color
Color image is fuzzyyer, and λ value is smaller.
In step s 2, based on estimated camera posture, according to depth map, voxel has blocked in acquisition three dimensions
To distance function TSDF values.
After the camera posture of kth amplitude deepness image and coloured image is estimated, you can update the TSDF values of each voxel, enter
And obtain the three-dimensional point position in world coordinate systemWith its normal directionThe color of each three-dimensional pointRoot
According to it, the pixel color of projected position is weighted and averagely tried to achieve in visible coloured image under preceding k camera posture, wherein
Weights can be simply set to 1, can also be according between the fog-level of image, the projecting direction of three-dimensional point and its normal direction
The factor such as angle determine.
In step s3, according to the TSDF values obtained, object described in geometrical reconstruction.
After all depth images and Color Image Processing, the final TSDF values of each voxel can be obtained, based on existing
Such as marching cube (marching cubes) algorithm, it can easily obtain the surface of three dimensional object model.
Furthermore it is possible to based on estimated camera posture, for each three-dimensional point meter of the object after geometrical reconstruction
Color is calculated, to carry out color mapping.
In one embodiment, the color value to two-dimensional projection's point significant in retrievable all colours figure is passed through
Weighted average updates the color of three-dimensional point.
It should be noted that all correspond to coloured image if not all depth images, then in the absence of corresponding
The depth image of coloured image, only carry out camera Attitude estimation according to geometric match.
The equipment that geometrical reconstruction object according to an embodiment of the invention is described next, with reference to Fig. 2.
Fig. 2 shows the block diagram of the equipment of geometrical reconstruction object according to an embodiment of the invention.Such as Fig. 2 institutes
Show, included according to the equipment 200 of the geometrical reconstruction object of the present invention：Camera attitude estimating device 21, is configured as：According to depth
Figure and corresponding color diagram, estimate camera posture；TSDF values obtain device 22, are configured as：Based on estimated camera posture,
According to depth map, voxel blocks signed distance function TSDF values in acquisition three dimensions；And geometrical reconstruction device 23, by with
It is set to：According to the TSDF values obtained, object described in geometrical reconstruction；Wherein, camera attitude estimating device 21 is further configured
For：, according to depth map and corresponding color diagram, estimate camera posture by solving optimization problem；Wherein, in the optimization
In problem, cost function is relevant with following factors：Pass through the camera coordinates of the present frame after the camera pose adjustment to be estimated
The quadratic sum of three-dimensional point in space and the distance of the corresponding three-dimensional points in the above global coordinate space of all frames and pass through
Three-dimensional point before after the camera pose adjustment to be estimated in the global coordinate space of all frames is in present frame corresponding color
Color and the quadratic sum of the distance metric of the corresponding color in the above global coordinate space of all frames on figure.
In one embodiment, the equipment 200 of geometrical reconstruction object also includes color mapping device, is configured as：It is based on
Estimated camera posture, color is calculated for each three-dimensional point of the object after geometrical reconstruction, to carry out color mapping.
In one embodiment, the color value to two-dimensional projection's point significant in retrievable all colours figure is passed through
Weighted average updates the color of three-dimensional point.
In one embodiment, the optimization problem is solved by the Gauss-Newton method of iteration.
Due to the place in each device and unit included in the equipment 200 of the geometrical reconstruction object according to the present invention
Reason is similar with the processing in each step included in the method for geometrical reconstruction object described above respectively, therefore for letter
For the sake of clean, the detailed description of these devices and unit is omitted herein.
In addition, still need here, it is noted that each component devices, unit can be by softwares, firmware, hard in the said equipment
Part or the mode of its combination are configured.Specific means workable for configuration or mode are well known to those skilled in the art,
This is repeated no more.In the case where being realized by software or firmware, from storage medium or network to specialized hardware structure
Computer (such as all-purpose computer 300 shown in Fig. 3) installation forms the program of the software, and the computer is being provided with various journeys
During sequence, various functions etc. are able to carry out.
Fig. 3 shows the schematic frame available for the computer for implementing method and apparatus according to an embodiment of the invention
Figure.
In figure 3, CPU (CPU) 301 is according to the program stored in read-only storage (ROM) 302 or from depositing
The program that storage part 308 is loaded into random access memory (RAM) 303 performs various processing.In RAM 303, always according to need
Store the data required when CPU 301 performs various processing etc..CPU 301, ROM 302 and RAM 303 are via bus
304 are connected to each other.Input/output interface 305 is also connected to bus 304.
Components described below is connected to input/output interface 305：Importation 306 (including keyboard, mouse etc.), output section
Points 307 (including displays, such as cathode-ray tube (CRT), liquid crystal display (LCD) etc., and loudspeaker etc.), storage part
308 (including hard disks etc.), communications portion 309 (including NIC such as LAN card, modem etc.).Communications portion 309
Communication process is performed via network such as internet.As needed, driver 310 can be connected to input/output interface 305.
Detachable media 311 such as disk, CD, magneto-optic disk, semiconductor memory etc. can be installed in driver as needed
On 310 so that the computer program read out is installed in storage part 308 as needed.
It is such as removable from network such as internet or storage medium in the case where realizing above-mentioned series of processes by software
Unload the program that the installation of medium 311 forms software.
It will be understood by those of skill in the art that this storage medium be not limited to wherein having program stored therein shown in Fig. 3,
Separately distribute with equipment to provide a user the detachable media 311 of program.The example of detachable media 311 includes disk
(including floppy disk (registration mark)), CD (including compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk
(including mini-disk (MD) (registration mark)) and semiconductor memory.Or storage medium can be ROM 302, storage part
Hard disk included in 308 etc., wherein computer program stored, and user is distributed to together with the equipment comprising them.
The present invention also proposes a kind of program product for the instruction code for being stored with machine-readable.The instruction code is by machine
When device reads and performed, above-mentioned method according to an embodiment of the invention can perform.
Correspondingly, the storage medium of the program product for carrying the above-mentioned instruction code for being stored with machine-readable is also wrapped
Include in disclosure of the invention.The storage medium includes but is not limited to floppy disk, CD, magneto-optic disk, storage card, memory stick etc.
Deng.
In the feature in the description of the specific embodiment of the invention, describing and/or showing for a kind of embodiment above
It can be used in a manner of same or similar in one or more other embodiments, with the feature in other embodiment
It is combined, or substitute the feature in other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, key element, step or component when being used herein, but simultaneously
It is not excluded for the presence or additional of one or more further features, key element, step or component.
In addition, the method for the present invention be not limited to specifications described in time sequencing perform, can also according to it
His time sequencing, concurrently or independently perform.Therefore, the execution sequence of the method described in this specification is not to this hair
Bright technical scope is construed as limiting.
Although being had been disclosed above by the description of the specific embodiment to the present invention to the present invention, should
The understanding, above-mentioned all embodiments and example are illustrative, and not restrictive.Those skilled in the art can be in institute
Various modifications, improvement or equivalent of the design to the present invention in attached spirit and scope by the claims.These modification, improve or
Person's equivalent should also be as being to be considered as included in protection scope of the present invention.
Claims (10)
1. a kind of method of geometrical reconstruction object, including：
According to depth map and corresponding color diagram, camera posture is estimated；
Based on estimated camera posture, according to depth map, voxel blocks signed distance function TSDF in acquisition three dimensions
Value；And
According to the TSDF values obtained, object described in geometrical reconstruction；
Wherein, according to depth map and corresponding color diagram, camera posture is estimated by solving optimization problem；
Wherein, in the optimization problem, cost function is relevant with following factors：Pass through the camera pose adjustment to be estimated
Three-dimensional point in the camera coordinates space of present frame afterwards and the corresponding three-dimensional points in the above global coordinate space of all frames
The quadratic sum of distance and pass through before after the camera pose adjustment to be estimated in the global coordinate space of all frames three
The distance degree of color and corresponding color in the above global coordinate space of all frames of the dimension point on present frame corresponding color figure
The quadratic sum of amount.
2. the method as described in claim 1, in addition to：
Based on estimated camera posture, color is calculated for each three-dimensional point of the object after geometrical reconstruction, to carry out
Color maps.
3. the method as described in claim 1, wherein by two-dimensional projection's point significant in retrievable all colours figure
The weighted average of color value update the color of three-dimensional point.
4. the method as described in claim 1, wherein in the case where some depth maps are without corresponding color diagram, using only depth
Degree figure estimates camera posture.
5. the method as described in claim 1, wherein solving the optimization problem by the Gauss-Newton method of iteration.
6. a kind of equipment of geometrical reconstruction object, including：
Camera attitude estimating device, is configured as：According to depth map and corresponding color diagram, camera posture is estimated；
TSDF values obtain device, are configured as：Based on estimated camera posture, according to depth map, body in three dimensions is obtained
Element blocks signed distance function TSDF values；And
Geometrical reconstruction device, is configured as：According to the TSDF values obtained, object described in geometrical reconstruction；
Wherein, camera attitude estimating device is further configured to：By solving optimization problem come according to depth map and corresponding
Color diagram, estimate camera posture；
Wherein, in the optimization problem, cost function is relevant with following factors：Pass through the camera pose adjustment to be estimated
Three-dimensional point in the camera coordinates space of present frame afterwards and the corresponding three-dimensional points in the above global coordinate space of all frames
The quadratic sum of distance and pass through before after the camera pose adjustment to be estimated in the global coordinate space of all frames three
The distance degree of color and corresponding color in the above global coordinate space of all frames of the dimension point on present frame corresponding color figure
The quadratic sum of amount.
7. equipment as claimed in claim 6, in addition to：
Color mapping device, is configured as：Based on estimated camera posture, for each of the object after geometrical reconstruction
Three-dimensional point calculates color, to carry out color mapping.
8. equipment as claimed in claim 6, wherein by two-dimensional projection's point significant in retrievable all colours figure
The weighted average of color value update the color of three-dimensional point.
9. equipment as claimed in claim 6, wherein in the case where some depth maps are without corresponding color diagram, using only depth
Degree figure estimates camera posture.
10. equipment as claimed in claim 6, wherein solving the optimization problem by the Gauss-Newton method of iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610625552.0A CN107680074A (en) | 2016-08-02 | 2016-08-02 | The method and apparatus of geometrical reconstruction object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610625552.0A CN107680074A (en) | 2016-08-02 | 2016-08-02 | The method and apparatus of geometrical reconstruction object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107680074A true CN107680074A (en) | 2018-02-09 |
Family
ID=61133988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610625552.0A Pending CN107680074A (en) | 2016-08-02 | 2016-08-02 | The method and apparatus of geometrical reconstruction object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107680074A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322542A (en) * | 2018-03-28 | 2019-10-11 | 苹果公司 | Rebuild the view of real world 3D scene |
| CN115601506A (en) * | 2022-11-07 | 2023-01-13 | 上海人工智能创新中心（Cn） | Three-dimensional scene reconstruction method, electronic device and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101582165A (en) * | 2009-06-29 | 2009-11-18 | 浙江大学 | Camera array calibration algorithm based on gray level image and spatial depth data |
| US20140146057A1 (en) * | 2012-11-26 | 2014-05-29 | Electronics And Telecommunications Research Institute | Apparatus for 3d reconstruction based on multiple gpus and method thereof |
| CN105184861A (en) * | 2015-10-20 | 2015-12-23 | 南京大学 | Automatic human three-dimensional (3D) reconstruction system |
| CN105654492A (en) * | 2015-12-30 | 2016-06-08 | 哈尔滨工业大学 | Robust real-time three-dimensional (3D) reconstruction method based on consumer camera |
-
2016
- 2016-08-02 CN CN201610625552.0A patent/CN107680074A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101582165A (en) * | 2009-06-29 | 2009-11-18 | 浙江大学 | Camera array calibration algorithm based on gray level image and spatial depth data |
| US20140146057A1 (en) * | 2012-11-26 | 2014-05-29 | Electronics And Telecommunications Research Institute | Apparatus for 3d reconstruction based on multiple gpus and method thereof |
| CN105184861A (en) * | 2015-10-20 | 2015-12-23 | 南京大学 | Automatic human three-dimensional (3D) reconstruction system |
| CN105654492A (en) * | 2015-12-30 | 2016-06-08 | 哈尔滨工业大学 | Robust real-time three-dimensional (3D) reconstruction method based on consumer camera |
Non-Patent Citations (1)
| Title |
|---|
| 梅峰等: "基于RGB-D深度相机的室内场景重建", 《中国图象图形学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110322542A (en) * | 2018-03-28 | 2019-10-11 | 苹果公司 | Rebuild the view of real world 3D scene |
| CN110322542B (en) * | 2018-03-28 | 2023-10-27 | 苹果公司 | Reconstructing views of a real world 3D scene |
| CN115601506A (en) * | 2022-11-07 | 2023-01-13 | 上海人工智能创新中心（Cn） | Three-dimensional scene reconstruction method, electronic device and medium |
| CN115601506B (en) * | 2022-11-07 | 2024-05-28 | 上海人工智能创新中心 | Reconstruction method of three-dimensional scene, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3944200B1 (en) | Facial image generation method and apparatus, device and storage medium | |
| El-Hakim et al. | A multi-sensor approach to creating accurate virtual environments | |
| Radeva et al. | Deformable B-solids and implicit snakes for 3D localization and tracking of SPAMM MRI data | |
| CN109387204A (en) | The synchronous positioning of the mobile robot of dynamic environment and patterning process in faced chamber | |
| CN109754417A (en) | The System and method for of unsupervised learning geometry from image | |
| CN108898630A (en) | A kind of three-dimensional rebuilding method, device, equipment and storage medium | |
| CN106846467B (en) | Entity scene modeling method and system based on optimization of position of each camera | |
| US20170032560A1 (en) | Robust attribute transfer for character animation | |
| CN103559737A (en) | Object panorama modeling method | |
| MX2007014662A (en) | Large mesh deformation using the volumetric graph laplacian. | |
| CN103649998A (en) | Method for determining a parameter set designed for determining the pose of a camera and/or for determining a three-dimensional structure of the at least one real object | |
| CN107680073A (en) | The method and apparatus of geometrical reconstruction object | |
| CN111868738A (en) | Cross-equipment monitoring computer vision system | |
| CN111260765A (en) | Dynamic three-dimensional reconstruction method for microsurgery operative field | |
| CN107680074A (en) | The method and apparatus of geometrical reconstruction object | |
| CN113706431B (en) | Model optimization method and related device, electronic equipment and storage medium | |
| CN104183002A (en) | Three-dimensional model change method and device | |
| Krissian et al. | Fast sub-voxel re-initialization of the distance map for level set methods | |
| CN108986155A (en) | The depth estimation method and estimation of Depth equipment of multi-view image | |
| CN108961381A (en) | Method and apparatus for the 3-D geometric model coloring to object | |
| CN115375847B (en) | Material recovery method, three-dimensional model generation method and model training method | |
| Lu et al. | Surface reconstruction via cooperative evolutions | |
| CN109816726A (en) | A kind of visual odometry map updating method and system based on depth filter | |
| Fu et al. | Interior dense 3D reconstruction system with RGB-D camera for complex large scenes | |
| CN106548466B (en) | The method and apparatus of three-dimensional reconstruction object |
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 |
Application publication date: 20180209 |
|
| RJ01 | Rejection of invention patent application after publication |