CN104952075A - Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method - Google Patents
Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method Download PDFInfo
- Publication number
- CN104952075A CN104952075A CN201510334502.2A CN201510334502A CN104952075A CN 104952075 A CN104952075 A CN 104952075A CN 201510334502 A CN201510334502 A CN 201510334502A CN 104952075 A CN104952075 A CN 104952075A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- model
- image
- texture
- matrix
- 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
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Generation (AREA)
Abstract
The invention discloses a laser scanning three-dimensional model-oriented multi-image automatic texture mapping method which comprises the following steps: acquiring a three-dimensional point cloud model of a three-dimensional scene by a laser scanner, forming a corresponding triangular grid model, calculating the three-dimensional point cloud model of the three-dimensional scene and corresponding camera parameters by a multi-image three-dimensional reconstruction system, calculating a rotating matrix, a translation matrix and a zooming matrix between the triangular grid model and the three-dimensional point cloud model, and adjusting the triangular grid model to be overlapped with a multi-image three-dimensional reconstructed model so as to carry out automatic texture mapping on the adjusted triangular grid mode according to the camera parameters to obtain corresponding texture images. According to the multi-image automatic texture mapping method disclosed by the invention, the phenomenon that the conventional three-dimensional model mapping effect is poor is greatly improved, so that the whole texture mapping process is completed fully automatically, and the result quality is higher.
Description
Technical field
The present invention relates to computer vision field, particularly relate to and map based on the three-dimensional reconstruction system of many images and the automatically texture of laser scanning model, be specifically related to a kind of many images automatic texture mapping method towards laser scanning three-dimensional model.
Background technology
The three-dimensional reconstruction system based on many images conventional at present utilizes the matching relationship between image feature vector to reach the world coordinate system coordinate of the Intrinsic Matrix solving camera in three-dimensional scenic, outer parameter matrix and three-dimensional point.
The method of another kind of conventional acquisition scene three-dimensional data is that laser scanning obtains three-dimensional model.In order to obtain the details that scene is enriched as far as possible, need to use face colouring to substitute the Point Coloring mode of existing three-dimensional model, namely on triangle grid model, the pixel of each tri patch takes from a triangular texture region on texture image.Due to the geometry pin-point accuracy of laser scanning three-dimensional model, the camera parameter error that many 3-dimensional reconstructions method obtains is very little, combining laser scanning three-dimensional model and the three-dimensional scenic that obtains based on many 3-dimensional reconstructions can describe (parameter of each camera) and calculate the abundant triangle grid model of grain details.
Flow process based on the three-dimensional reconstruction system of many images extracts the proper vector of often opening image, proper vector between image is mated, using the input of the matching result of proper vector as three-dimensional reconstruction, often opened the dense three-dimensional point cloud of camera parameter corresponding to image and three-dimensional scenic, and eliminate the distortion of often opening image and to be eliminated the image after distortion.
The input data that many images automatically texture maps to be needed have triangle grid model, the parameter of each camera and the image of correspondence.
In recent years, and then texture carries out based on many 3-dimensional reconstructions always, because the three-dimensional model error on geometry obtained based on many 3-dimensional reconstructions is larger, the texture result finally obtained is not ideal, laser scanning three-dimensional model is introduced the mapping of many image textures final result details can be made abundanter.
Summary of the invention
For the deficiencies in the prior art, the invention provides a kind of many images automatic texture mapping method towards laser scanning three-dimensional model.
Towards many images automatic texture mapping method of laser scanning three-dimensional model, comprising:
Step 1, use laser scanner obtain the three-dimensional point cloud model of three-dimensional scenic, and form corresponding triangle grid model;
Step 2, obtain several images that are multi-direction, multi-angle of described three-dimensional scenic, and solve and often opened camera Intrinsic Matrix corresponding to image, Camera extrinsic matrix number, and the dense three-dimensional point cloud of described three-dimensional scenic;
The number of the photo obtained is at least 20.Usual use slr camera carries out taking pictures of multi-direction, multi-angle to scene and finds a view to obtain the image of multi-direction, multi-angle accordingly.
Step 3, described triangle grid model is carried out coupling with described dense three-dimensional point cloud obtain the triangle grid model that aligns;
Step 4, according to all images, camera Intrinsic Matrix, Camera extrinsic matrix number and described alignment triangle grid model that each image is corresponding, adopt and obtain based on perspective projection modelling texture region that on described alignment triangle grid model, each tri patch is corresponding in each image and splicing obtains corresponding texture image.
The three-dimensional point cloud model of three-dimensional scenic of the present invention uses laser scanner scans scene to obtain, not that conventional many 3-dimensional reconstructions calculate, for the three-dimensional point cloud model using laser scanner scans to obtain, when process, then the color of removal three-dimensional point cloud model is carried out triangle gridding and is formed corresponding triangle grid model.
As preferably, described triangle grid model is PLY form.PLY compare other represent three-dimensional model file layout can more simply with element (three-dimensional vertices, texture coordinate, tri patch) list to store triangle grid model,
Technology maturation and be easy to realize, utilizes many 3-dimensional reconstructions method to solve and is often opened camera Intrinsic Matrix corresponding to image, Camera extrinsic matrix number, and dense three-dimensional point cloud in described step 2.
Overlapping most by mating these two models of dense three-dimensional point cloud making the three-dimensional model of laser scanning (i.e. triangle grid model) and many 3-dimensional reconstructions obtain, ensureing that the camera parameter that many 3-dimensional reconstructions obtain is effective under laser scanning three-dimensional model.As preferably, described step 3 is specific as follows:
Transposed matrix as described in calculating according to the geometric similarity (as geometric properties such as profiles) between described triangle grid model and described dense three-dimensional point cloud between triangle grid model and dense three-dimensional point cloud, described transposed matrix comprises rotation matrix, translation matrix, scaled matrix and distortion parameter;
Using described dense three-dimensional point cloud as benchmark, obtain according to the described transposed matrix adjustment direction of triangle grid model, position, size the triangle grid model that aligns.
When mating in the present invention, needs carry out under same world coordinate system.
In the present invention from during the final texture region of initial texture regional choice of all correspondences to ensure that the final texture region that all tri patchs are corresponding comes from same image as far as possible for principle.Namely selecting to cover maximum that of pixel in numerous selective image, corresponding to by selecting many adjacent triangular faces in geometry topology as far as possible the effect optimization same image can being guaranteed texture.
The corresponding texture region of each tri patch, when texture region corresponding for all tri patchs is spliced into texture image, splicing gap can be there is in the texture image obtained, for improving the quality of the texture image obtained, as preferably, the present invention also comprises and carries out aberration Weakening treatment to splicing the texture image obtained.
Finally obtaining texture image in the present invention can be OBJ, MTL, PNG tri-file layouts, namely towards the result that many images automatically texture of laser scanning three-dimensional model maps.
Compared with prior art, after the many images automatic texture mapping method towards laser scanning three-dimensional model of the present invention drastically increases the geometric accuracy of triangle grid model and texture, the details of model enriches degree, and easily realizes.
Embodiment
Below in conjunction with specific embodiment, the present invention is described in detail, and following examples will contribute to those skilled in the art and understand the present invention further, but not limit the present invention in any form.
Many images automatic texture mapping method towards laser scanning three-dimensional model of the present embodiment comprises:
Step 1, use laser scanner scans scene obtain three-dimensional point cloud model, obtain the triangle grid model of PLY form through process.
Step 2, use slr camera to carry out multi-direction, taking pictures of multi-angle to scene to find a view, and utilize many 3-dimensional reconstructions method to solve often to be opened the dense three-dimensional point cloud of camera Intrinsic Matrix corresponding to image, Camera extrinsic matrix number, scene.
The dense three-dimensional point cloud that step 3, coupling laser scanning three-dimensional model and many 3-dimensional reconstructions obtain, the dense three-dimensional point cloud obtained using many 3-dimensional reconstructions is as benchmark, rotation matrix, translation matrix, the scaled matrix between model is tried to achieve according to the geometric similarity (feature such as profile) at three-dimensional point cloud place, the dense three-dimensional point cloud that the direction of adjustment laser scanning three-dimensional model, position, size make laser scanning three-dimensional model and many 3-dimensional reconstructions obtain overlaps most, obtains the triangle grid model that aligns.
Overlapping most by mating these two models of dense three-dimensional point cloud obtained, ensureing that the camera parameter that many 3-dimensional reconstructions obtain is effective under laser scanning three-dimensional model.
The conversion of step 4, three-dimensional scenic expression way, extracts many images automatically texture and maps the most succinct three-dimensional scenic expression way (camera focus, rotation matrix, translation matrix, distortion parameter) that can identify to represent this three-dimensional scenic from the result that many 3-dimensional reconstructions method obtains.
Step 5, many images automatically texture maps, and tries to achieve texture region corresponding to each tri patch on alignment three-dimensional model and texture region corresponding for all tri patchs splicing is obtained corresponding texture image as mapping result according to the three-dimensional scenic expression way extracted in perspective projection model and step 4.
Corresponding texture region is obtained by the following method for each tri patch in the present embodiment:
Adopt and obtain this tri patch texture region corresponding in each image as initial texture region, then from initial texture regional choice final texture region of conduct of all correspondences based on perspective projection modelling.
From during the final texture region of initial texture regional choice of all correspondences to ensure that the final texture region that all tri patchs are corresponding comes from same image as far as possible for principle.
Geometry topology is selected as far as possible many adjacent triangular faces correspond to the effect optimization same image being guaranteed simultaneously texture.
Above-described embodiment has been described in detail technical scheme of the present invention and beneficial effect; be understood that and the foregoing is only most preferred embodiment of the present invention; be not limited to the present invention; all make in spirit of the present invention any amendment, supplement and equivalent to replace, all should be included within protection scope of the present invention.
Claims (7)
1., towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, comprising:
Step 1, use laser scanner obtain the three-dimensional point cloud model of three-dimensional scenic, and form corresponding triangle grid model;
Step 2, obtain several images that are multi-direction, multi-angle of described three-dimensional scenic, and solve and often opened camera Intrinsic Matrix corresponding to image, Camera extrinsic matrix number, and the dense three-dimensional point cloud of described three-dimensional scenic;
Step 3, described triangle grid model is carried out coupling with described dense three-dimensional point cloud obtain the triangle grid model that aligns;
Step 4, according to all images, camera Intrinsic Matrix, Camera extrinsic matrix number and described alignment triangle grid model that each image is corresponding, adopt and obtain based on perspective projection modelling texture region that on described alignment triangle grid model, each tri patch is corresponding in each image and splicing obtains corresponding texture image.
2., as claimed in claim 1 towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, described triangle grid model is PLY form.
3. as claimed in claim 1 towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, utilize many 3-dimensional reconstructions method to solve in described step 2 and often opened camera Intrinsic Matrix corresponding to image, Camera extrinsic matrix number, and dense three-dimensional point cloud.
4., as claimed in claim 1 towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, described step 3 is specific as follows:
Calculate the transposed matrix between described triangle grid model and dense three-dimensional point cloud according to the geometric similarity between described triangle grid model and described dense three-dimensional point cloud, described transposed matrix comprises rotation matrix, translation matrix and scaled matrix;
Using described dense three-dimensional point cloud as benchmark, obtain according to the described transposed matrix adjustment direction of triangle grid model, position, size the triangle grid model that aligns.
5. as claimed in claim 1 towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, in described step 4, obtain corresponding texture region by the following method for each tri patch:
(4-1) employing obtains this tri patch texture region corresponding in each image as initial texture region based on perspective projection modelling;
(4-2) from initial texture regional choice final texture region of conduct of all correspondences.
6. as claimed in claim 5 towards many images automatic texture mapping method of laser scanning three-dimensional model, it is characterized in that, from during the final texture region of initial texture regional choice of all correspondences to ensure that the final texture region that all tri patchs are corresponding comes from same image as far as possible for principle.
7. as the many images automatic texture mapping method towards laser scanning three-dimensional model in claim 1 ~ 6 as described in any one, it is characterized in that, also comprise and carry out aberration Weakening treatment to splicing the texture image obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510334502.2A CN104952075A (en) | 2015-06-16 | 2015-06-16 | Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510334502.2A CN104952075A (en) | 2015-06-16 | 2015-06-16 | Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104952075A true CN104952075A (en) | 2015-09-30 |
Family
ID=54166703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510334502.2A Pending CN104952075A (en) | 2015-06-16 | 2015-06-16 | Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104952075A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097433A (en) * | 2016-05-30 | 2016-11-09 | 广州汉阈数据处理技术有限公司 | Object industry and the stacking method of Image model and system |
| CN107123163A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | A kind of plant three-dimensional reconstruction system based on various visual angles stereoscopic vision |
| CN107464285A (en) * | 2017-06-26 | 2017-12-12 | 北京长城华冠汽车科技股份有限公司 | The Meshing Method and device of a kind of threedimensional model |
| CN107507274A (en) * | 2017-08-30 | 2017-12-22 | 北京图航科技有限公司 | A kind of quick restoring method of public security criminal-scene three-dimensional live based on cloud computing |
| CN107552965A (en) * | 2017-09-28 | 2018-01-09 | 惠州市洛玛科技有限公司 | Accurate marking device and its marking method |
| CN107918926A (en) * | 2017-11-22 | 2018-04-17 | 徐李添 | A kind of digital image magnification method based on quadrangle and triangle surface |
| CN108010123A (en) * | 2017-11-23 | 2018-05-08 | 东南大学 | A kind of three-dimensional point cloud acquisition methods for retaining topology information |
| CN108280870A (en) * | 2018-01-24 | 2018-07-13 | 郑州云海信息技术有限公司 | A kind of point cloud model texture mapping method and system |
| CN108537879A (en) * | 2018-03-29 | 2018-09-14 | 东华智业（北京）科技发展有限公司 | Reconstructing three-dimensional model system and method |
| WO2018176440A1 (en) * | 2017-04-01 | 2018-10-04 | 深圳市速腾聚创科技有限公司 | Method for fusing point cloud and planar image, intelligent device and non-volatile computer-readable storage medium |
| CN109389665A (en) * | 2018-08-24 | 2019-02-26 | 先临三维科技股份有限公司 | Texture acquirement method, apparatus, equipment and the storage medium of threedimensional model |
| CN109410302A (en) * | 2018-09-30 | 2019-03-01 | 先临三维科技股份有限公司 | Texture mapping method, device, computer equipment and storage medium |
| CN109934905A (en) * | 2019-01-16 | 2019-06-25 | 中德（珠海）人工智能研究院有限公司 | It is a kind of for generating the system and its generation method of threedimensional model |
| CN111242990A (en) * | 2020-01-06 | 2020-06-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | 360-degree three-dimensional reconstruction optimization method based on continuous phase dense matching |
| CN111612920A (en) * | 2020-06-28 | 2020-09-01 | 广州欧科信息技术股份有限公司 | Method and equipment for generating point cloud three-dimensional space image |
| CN112053425A (en) * | 2020-09-29 | 2020-12-08 | 广州极飞科技有限公司 | Multispectral image processing method and device and electronic equipment |
| CN112348939A (en) * | 2020-11-18 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Texture optimization method and device for three-dimensional reconstruction |
| CN113432548A (en) * | 2021-06-04 | 2021-09-24 | 中兵勘察设计研究院有限公司 | Three-dimensional scanning and photogrammetry integrated control device and control method |
| CN114147969A (en) * | 2021-11-16 | 2022-03-08 | 深圳市创必得科技有限公司 | Model preprocessing annular texture blanking method, device, equipment and storage medium |
| CN115546379A (en) * | 2022-11-29 | 2022-12-30 | 思看科技(杭州)股份有限公司 | Data processing method and device and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6816629B2 (en) * | 2001-09-07 | 2004-11-09 | Realty Mapping Llc | Method and system for 3-D content creation |
| CN101551918A (en) * | 2009-04-28 | 2009-10-07 | 浙江大学 | Acquisition method of large scene based on line laser |
| US8040355B2 (en) * | 2007-07-23 | 2011-10-18 | Disney Enterprises, Inc. | Three-dimensional location-based texture transfers |
| CN103021017A (en) * | 2012-12-04 | 2013-04-03 | 上海交通大学 | Three-dimensional scene rebuilding method based on GPU acceleration |
| CN103430218A (en) * | 2011-03-21 | 2013-12-04 | 英特尔公司 | Method of augmented makeover with 3d face modeling and landmark alignment |
-
2015
- 2015-06-16 CN CN201510334502.2A patent/CN104952075A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6816629B2 (en) * | 2001-09-07 | 2004-11-09 | Realty Mapping Llc | Method and system for 3-D content creation |
| US8040355B2 (en) * | 2007-07-23 | 2011-10-18 | Disney Enterprises, Inc. | Three-dimensional location-based texture transfers |
| CN101551918A (en) * | 2009-04-28 | 2009-10-07 | 浙江大学 | Acquisition method of large scene based on line laser |
| CN103430218A (en) * | 2011-03-21 | 2013-12-04 | 英特尔公司 | Method of augmented makeover with 3d face modeling and landmark alignment |
| CN103021017A (en) * | 2012-12-04 | 2013-04-03 | 上海交通大学 | Three-dimensional scene rebuilding method based on GPU acceleration |
Non-Patent Citations (1)
| Title |
|---|
| 戴嘉境: "基于多幅图像的三维重建理论及算法研究", 《中国优秀硕士学位论文全文数据库.信息科技辑》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106097433A (en) * | 2016-05-30 | 2016-11-09 | 广州汉阈数据处理技术有限公司 | Object industry and the stacking method of Image model and system |
| WO2018176440A1 (en) * | 2017-04-01 | 2018-10-04 | 深圳市速腾聚创科技有限公司 | Method for fusing point cloud and planar image, intelligent device and non-volatile computer-readable storage medium |
| CN107123163A (en) * | 2017-04-25 | 2017-09-01 | 无锡中科智能农业发展有限责任公司 | A kind of plant three-dimensional reconstruction system based on various visual angles stereoscopic vision |
| CN107464285A (en) * | 2017-06-26 | 2017-12-12 | 北京长城华冠汽车科技股份有限公司 | The Meshing Method and device of a kind of threedimensional model |
| CN107507274A (en) * | 2017-08-30 | 2017-12-22 | 北京图航科技有限公司 | A kind of quick restoring method of public security criminal-scene three-dimensional live based on cloud computing |
| CN107552965A (en) * | 2017-09-28 | 2018-01-09 | 惠州市洛玛科技有限公司 | Accurate marking device and its marking method |
| CN107918926A (en) * | 2017-11-22 | 2018-04-17 | 徐李添 | A kind of digital image magnification method based on quadrangle and triangle surface |
| CN107918926B (en) * | 2017-11-22 | 2018-11-13 | 徐李添 | A kind of digital image magnification method based on quadrangle and triangle surface |
| CN108010123B (en) * | 2017-11-23 | 2021-02-09 | 东南大学 | Three-dimensional point cloud obtaining method capable of retaining topology information |
| CN108010123A (en) * | 2017-11-23 | 2018-05-08 | 东南大学 | A kind of three-dimensional point cloud acquisition methods for retaining topology information |
| CN108280870A (en) * | 2018-01-24 | 2018-07-13 | 郑州云海信息技术有限公司 | A kind of point cloud model texture mapping method and system |
| CN108537879A (en) * | 2018-03-29 | 2018-09-14 | 东华智业（北京）科技发展有限公司 | Reconstructing three-dimensional model system and method |
| CN109389665A (en) * | 2018-08-24 | 2019-02-26 | 先临三维科技股份有限公司 | Texture acquirement method, apparatus, equipment and the storage medium of threedimensional model |
| CN109410302A (en) * | 2018-09-30 | 2019-03-01 | 先临三维科技股份有限公司 | Texture mapping method, device, computer equipment and storage medium |
| CN109934905A (en) * | 2019-01-16 | 2019-06-25 | 中德（珠海）人工智能研究院有限公司 | It is a kind of for generating the system and its generation method of threedimensional model |
| CN111242990A (en) * | 2020-01-06 | 2020-06-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | 360-degree three-dimensional reconstruction optimization method based on continuous phase dense matching |
| CN111242990B (en) * | 2020-01-06 | 2024-01-30 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | 360-degree three-dimensional reconstruction optimization method based on continuous phase dense matching |
| CN111612920A (en) * | 2020-06-28 | 2020-09-01 | 广州欧科信息技术股份有限公司 | Method and equipment for generating point cloud three-dimensional space image |
| CN111612920B (en) * | 2020-06-28 | 2023-05-05 | 广州欧科信息技术股份有限公司 | Method and equipment for generating point cloud three-dimensional space image |
| CN112053425B (en) * | 2020-09-29 | 2022-05-10 | 广州极飞科技股份有限公司 | Multispectral image processing method and device and electronic equipment |
| CN112053425A (en) * | 2020-09-29 | 2020-12-08 | 广州极飞科技有限公司 | Multispectral image processing method and device and electronic equipment |
| CN112348939A (en) * | 2020-11-18 | 2021-02-09 | 北京沃东天骏信息技术有限公司 | Texture optimization method and device for three-dimensional reconstruction |
| CN113432548A (en) * | 2021-06-04 | 2021-09-24 | 中兵勘察设计研究院有限公司 | Three-dimensional scanning and photogrammetry integrated control device and control method |
| CN114147969A (en) * | 2021-11-16 | 2022-03-08 | 深圳市创必得科技有限公司 | Model preprocessing annular texture blanking method, device, equipment and storage medium |
| CN114147969B (en) * | 2021-11-16 | 2024-04-16 | 深圳市创必得科技有限公司 | Model preprocessing annular texture blanking method, device, equipment and storage medium |
| CN115546379A (en) * | 2022-11-29 | 2022-12-30 | 思看科技(杭州)股份有限公司 | Data processing method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104952075A (en) | Laser scanning three-dimensional model-oriented multi-image automatic texture mapping method | |
| Zioulis et al. | Spherical view synthesis for self-supervised 360 depth estimation | |
| CN111047510B (en) | Large-field-angle image real-time splicing method based on calibration | |
| US20210004973A1 (en) | Image processing method, apparatus, and storage medium | |
| Ji et al. | Deep view morphing | |
| CN102592275B (en) | Virtual viewpoint rendering method | |
| CN103426163B (en) | System and method for rendering affected pixels | |
| CN101000461B (en) | Method for generating stereoscopic panorama by fish eye image | |
| CN110349251A (en) | A kind of three-dimensional rebuilding method and device based on binocular camera | |
| CN110349247B (en) | Indoor scene CAD three-dimensional reconstruction method based on semantic understanding | |
| CN107369204B (en) | Method for recovering basic three-dimensional structure of scene from single photo | |
| Germann et al. | Articulated billboards for video‐based rendering | |
| CN103810685A (en) | Super resolution processing method for depth image | |
| CN111047709B (en) | Binocular vision naked eye 3D image generation method | |
| CN103761765B (en) | Three-dimensional object model texture mapping method based on mapped boundaries optimization | |
| CN109118578A (en) | A kind of multiview three-dimensional reconstruction texture mapping method of stratification | |
| WO2008112802A2 (en) | System and method for 2-d to 3-d image conversion using mask to model, or model to mask, conversion | |
| CN105006021A (en) | Color mapping method and device suitable for rapid point cloud three-dimensional reconstruction | |
| CN106780573B (en) | A kind of method and system of panorama sketch characteristic matching precision optimizing | |
| CN109523622B (en) | Unstructured light field rendering method | |
| CN102982524B (en) | Splicing method for corn ear order images | |
| Poullis et al. | 3d reconstruction of urban areas | |
| Xu et al. | Layout-guided novel view synthesis from a single indoor panorama | |
| CN106028020B (en) | A kind of virtual perspective image cavity complementing method based on multi-direction prediction | |
| CN104751508B (en) | The full-automatic of new view is quickly generated and complementing method in the making of 3D three-dimensional films |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150930 |