[go: up one dir, main page]

CN115272549B - Storage and rendering scheduling method and device for oversized digital scene - Google Patents

Storage and rendering scheduling method and device for oversized digital scene Download PDF

Info

Publication number
CN115272549B
CN115272549B CN202210919619.7A CN202210919619A CN115272549B CN 115272549 B CN115272549 B CN 115272549B CN 202210919619 A CN202210919619 A CN 202210919619A CN 115272549 B CN115272549 B CN 115272549B
Authority
CN
China
Prior art keywords
segmentation
scene
rendering
digital
component
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.)
Active
Application number
CN202210919619.7A
Other languages
Chinese (zh)
Other versions
CN115272549A (en
Inventor
曹均丽
巫梅樱枝
邓星
李汶影
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.)
Dongsen Digital Technology Chongqing Co ltd
Original Assignee
Dongsen Digital Technology Chongqing 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 Dongsen Digital Technology Chongqing Co ltd filed Critical Dongsen Digital Technology Chongqing Co ltd
Priority to CN202210919619.7A priority Critical patent/CN115272549B/en
Publication of CN115272549A publication Critical patent/CN115272549A/en
Application granted granted Critical
Publication of CN115272549B publication Critical patent/CN115272549B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/003D [Three Dimensional] image rendering
    • G06T15/005General purpose rendering architectures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20Finite element generation, e.g. wire-frame surface description, tesselation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Graphics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The application provides a storage and rendering scheduling method and device for oversized digital scenes, wherein the scheme classifies and stores the same gateway topology, repeatedly constructs an optimized storage mode stored by adopting a referential reference mode, saves storage space, accelerates loading speed, automatically generates a plurality of dimension grid envelopments for the digital scenes, and combines grid vertexes according to an optimized gradient by each envelopment to realize automatic vertex optimization according to the volume of the scene; meanwhile, models of different levels have grids with different precision, different segmentation sizes are adopted for different precision through normalized segmentation of the digital scene, so that distributed scheduling during subsequent rendering can be guaranteed, meanwhile, rendering is carried out in a view cone judging mode, transition is smoother, and rendering effect is better.

Description

Storage and rendering scheduling method and device for oversized digital scene
Technical Field
The application relates to the technical field of digital scene storage and rendering, in particular to a method and a device for storing and rendering scheduling of oversized digital scenes.
Background
Rendering in a computer drawing refers to the process of generating images from a model with software. A model is a description of a three-dimensional object in a well-defined language or data structure, which includes geometric, viewpoint, texture, and illumination information. And (3) the model in the three-dimensional scene is subjected to the set environment, lamplight, materials and rendering parameters. A process of two-dimensional projection into a digital image.
When the existing digital scene is rendered, the method has the following publication number: in the CN102467752a patent, since it is necessary to determine based on the camera position at the time of rendering, there is a case where the rendering transition is unnatural, resulting in poor rendering effect.
Disclosure of Invention
Aiming at the defects existing in the prior art, the application provides a method and a device for storing and rendering scheduling of an oversized digital scene,
the method solves the technical problems that in the prior art, when rendering is performed, judgment is needed based on the position of a camera, so that rendering transition is unnatural and rendering effect is poor.
A storage and rendering scheduling method of oversized digital scene includes: acquiring a component of a current digital scene, wherein a data structure of the component comprises a three-dimensional grid and additional information; screening the components by adopting a computer program, classifying and storing the components with the same grid topology, and storing the repeated components by adopting referential references; automatically generating a plurality of dimension grid envelopes for the digital scene using a computer program; merging grid vertexes of each enveloping body according to an optimized gradient, and carrying out normalized segmentation on the digital scene to obtain a plurality of scene segmentation file groups with different precision; and forming a view cone according to the view angle and the picture center block based on the segmentation file group for rendering.
In one embodiment, the component includes three-dimensional terrain data, building model data, and special construction model data.
In one embodiment, the additional information includes scene map information, normal direction, and grid classification.
In one embodiment, in the step of classifying and storing the members having the same mesh topology, the stored record information includes: component anchor point, component reference address, component extra information.
In one embodiment, the normalizing and splitting step is performed on the digital scene, including: and splitting the digitized scene with different precision by adopting different splitting sizes.
In one embodiment, based on the cut file group, the rendering step of forming a view cone according to the view angle and the picture center block includes: and (3) judging according to the cone formed by the visual angle and the central block of the picture, loading a high-precision cutting group in the central area, loading a secondary cutting group on the periphery, loading a primary cutting group again in a distance, and loading a rough cutting group on the background.
The device comprises a component acquisition module, a component storage module, a scene segmentation module and a scene rendering module, wherein: the component acquisition module is used for acquiring a component of the current digital scene, and the data structure of the component comprises a three-dimensional grid and additional information; the component storage module is used for screening the components by adopting a computer program, classifying and storing the components with the same grid topology, and storing the repeated components by adopting referential references; the scene segmentation module is used for automatically generating a plurality of dimension grid envelopes for the digital scene by adopting a computer program; merging grid vertexes of each enveloping body according to an optimized gradient, and carrying out normalized segmentation on the digital scene to obtain a plurality of scene segmentation file groups with different precision; the scene rendering module is used for forming a view cone according to the view angle and the picture center block based on the segmentation file group to render.
A computer device comprising a memory, a processor and a computer program stored in the memory and operable on the processor, wherein the processor executes the program to implement the steps of a method for predicting opening and closing deformation of a immersed tube tunnel pipe joint according to the above embodiments.
A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method of predicting open-close deformation of a immersed tube tunnel joint as described in the above embodiments.
According to the technical scheme, the beneficial technical effects of the application are as follows:
1. the same gateway topology is classified and stored, and an optimized storage mode of storing by adopting a referential reference mode is repeatedly constructed, so that the storage space is saved, and the loading speed is increased.
2. Automatically generating a plurality of dimension grid enveloping bodies for the digital scene, and combining grid vertexes according to an optimized gradient by each enveloping body to realize automatic vertex optimization according to the scene volume; meanwhile, as the models of different levels have grids with different precision, different segmentation sizes are adopted for different precision by carrying out normalized segmentation on the digital scene, so that the distributed scheduling in the subsequent rendering process can be ensured.
3. And the view cone judgment mode is adopted for rendering, so that the transition is smoother, and the rendering effect is better.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, elements or portions thereof are not necessarily drawn to scale.
FIG. 1 is a flow diagram of a method for storage and rendering scheduling of oversized digital scenes in one embodiment;
FIG. 2 is a block diagram of a storage and rendering scheduler for oversized digital scenes in one embodiment;
FIG. 3 is an internal block diagram of a computer device in one embodiment.
Detailed Description
Embodiments of the technical scheme of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and thus are merely examples, and are not intended to limit the scope of the present application.
It is noted that unless otherwise indicated, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs.
In one embodiment, as shown in fig. 1, there is provided a storage and rendering scheduling method of an oversized digital scene, including the steps of:
s110, acquiring a component of the current digital scene, wherein a data structure of the component comprises a three-dimensional grid and additional information.
In one embodiment, the components in step S110 include three-dimensional terrain data, building model data, and special construction model data.
In one embodiment, the additional information in step S110 includes scene map information, normal direction, and grid classification.
Specifically, first, a current digital model member including three-dimensional terrain data, building model data, special construction model data, and the like is obtained. The data structure of the component includes a three-dimensional grid and additional information, where the additional information includes scene map information of the grid surface, normal direction, grid classification, and the like.
S120, adopting a computer program to screen the components, classifying and storing the components with the same grid topology, and adopting referential references to store the repeated components.
In one embodiment, in the step of classifying and storing the members having the same mesh topology, the stored record information includes: component anchor point, component reference address, component extra information.
Specifically, a computer program is adopted to screen all digital components, and components with the same network topology are classified, wherein the same grid topology is the component with the same property and category. The component is recorded, and the recorded information is a component positioning point, a component reference address and component additional information, wherein the component additional information generally refers to component attributes in a Building Information Model (BIM). Such as concrete marks, reinforcement content and the like in the upper components of the bridge, and the repeated components are stored in a referential reference mode so as to save data space. The same gateway topology is classified, and an optimized storage mode stored in a referential reference mode is repeatedly constructed, so that not only is the storage space saved, but also the loading speed is increased.
S130, adopting a computer program, automatically generating a plurality of dimension grid envelopes for the digital scene.
Specifically, a computer program is adopted to automatically generate a plurality of dimension grid envelopes for a digital scene, wherein the digital scene is a three-dimensional digital scene and comprises three-dimensional terrain data, building model data, special construction model data and the like.
And S140, merging grid vertexes of each enveloping body according to the optimized gradient, and carrying out normalized segmentation on the digital scene to obtain a plurality of scene segmentation file groups with different accuracies.
In one embodiment, the normalizing segmentation of the digital scene in step S140 includes: and slicing the digitized scene with different precision by adopting different slicing sizes.
Specifically, each enveloping body carries out grid vertex combination according to the optimized gradient, then carries out normalized segmentation on the digital scene, adopts different segmentation sizes for different precision, and finally forms a plurality of scene segmentation file groups with different precision. Automatically generating a plurality of dimension grid enveloping bodies for the digital scene, and combining grid vertexes according to an optimized gradient by each enveloping body to realize automatic vertex optimization according to the scene volume; meanwhile, as the models of different levels have grids with different precision, different segmentation sizes are adopted for different precision by carrying out normalized segmentation on the digital scene, so that the distributed scheduling in the subsequent rendering process can be ensured.
S150, forming a view cone according to the view angle and the picture center block based on the segmentation file group for rendering.
In one embodiment, step S150 includes: and (3) judging according to the cone formed by the visual angle and the central block of the picture, loading a high-precision cutting group in the central area, loading a secondary cutting group on the periphery, loading a primary cutting group again in a distance, and loading a rough cutting group on the background.
Specifically, when the GPU is rendered (GPU, graphics processor), a cone is formed according to the visual angle and the central block of the picture to judge, a high-precision cutting group is loaded in the central area, a secondary cutting group is loaded on the periphery, a primary cutting group is loaded at a distance, and a rough cutting group is loaded on the background. The secondary and secondary stages herein mean that the accuracy is sequentially reduced to form a transition, but the transition is smoother and the rendering effect is better compared with other patents in which the transition is rendered by adopting a view cone judgment mode according to the judgment of the position of the camera without the visual sense of large change. This step may go through the same processing mode multiple times, so that description and rendering of infinite terrain may be achieved.
In one embodiment, a storage and rendering scheduling device for oversized digital scenes is provided, which includes a component acquisition module 210, a component storage module 220, a scene segmentation module 230, and a scene rendering module 240, wherein:
the component obtaining module 210 is configured to obtain a component of the current digital scene, where a data structure of the component includes a three-dimensional grid and additional information;
the component storage module 220 is configured to screen components using a computer program, classify and store components having the same mesh topology, and store duplicate components using reference;
the scene segmentation module 230 is configured to automatically generate a plurality of dimension grid envelopes for the digital scene using a computer program; merging grid vertexes of each enveloping body according to the optimized gradient, and carrying out normalized segmentation on the digital scene to obtain a plurality of scene segmentation file groups with different accuracies;
the scene rendering module 240 is configured to form a view cone according to the view angle and the center block of the screen based on the segmentation file group for rendering.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing configuration templates and can also be used for storing target webpage data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method for storing and rendering scheduling of oversized digital scenes.
It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, there is also provided a storage medium storing a computer program comprising program instructions that when executed by a computer, cause the computer to perform a method as described in the previous embodiments, the computer being part of a storage and rendering scheduler for an oversized digital scene as mentioned above.
It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed across a network of computing devices, or they may alternatively be implemented in program code executable by computing devices, such that they may be stored on a computer storage medium (ROM/RAM, magnetic or optical disk) for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than what is shown or described herein, or they may be individually manufactured as individual integrated circuit modules, or a plurality of modules or steps in them may be manufactured as a single integrated circuit module. Therefore, the present application is not limited to any specific combination of hardware and software.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application, and are intended to be included within the scope of the appended claims and description.

Claims (7)

1. A method for storing and rendering a super-large digital scene, comprising:
acquiring a component of a current digital scene, wherein a data structure of the component comprises a three-dimensional grid and additional information;
screening the components by adopting a computer program, classifying and storing the components with the same grid topology, and storing the repeated components by adopting referential references;
automatically generating a plurality of dimension grid envelopes for the digital scene using a computer program;
merging grid vertexes of each enveloping body according to an optimized gradient, carrying out normalized segmentation on the digital scenes, and specifically segmenting the digital scenes with different precision by adopting different segmentation sizes to obtain a plurality of scene segmentation file groups with different precision;
based on the segmentation file group, forming a view cone according to the view angle and a picture center block for rendering, specifically judging according to the view angle and the picture center block for forming a cone, loading a high-precision segmentation group in a center area, loading a secondary segmentation group on the periphery, loading a secondary segmentation group at a distance, loading a primary segmentation group again, and loading a rough segmentation group on the background.
2. The method of claim 1, wherein the component comprises three-dimensional terrain data, building model data, and special construction model data.
3. The method of claim 1, wherein the additional information includes scene map information, normal direction, and grid classification.
4. The method according to claim 1, wherein in the step of classifying and storing members having the same mesh topology, the stored record information includes: component anchor point, component reference address, component extra information.
5. The device for storing and rendering and scheduling the oversized digital scene is characterized by comprising a component acquisition module, a component storage module, a scene segmentation module and a scene rendering module, wherein:
the component acquisition module is used for acquiring a component of the current digital scene, and the data structure of the component comprises a three-dimensional grid and additional information;
the component storage module is used for screening the components by adopting a computer program, classifying and storing the components with the same grid topology, and storing the repeated components by adopting referential references;
the scene segmentation module is used for automatically generating a plurality of dimension grid envelopes for the digital scene by adopting a computer program; merging grid vertexes of each enveloping body according to an optimized gradient, carrying out normalized segmentation on the digital scenes, and specifically segmenting the digital scenes with different precision by adopting different segmentation sizes to obtain a plurality of scene segmentation file groups with different precision;
the scene rendering module is used for forming a view cone according to the view angle and a picture center block based on the segmentation file group to render, particularly judging according to the view angle and the picture center block forming cone, loading a high-precision segmentation group in a center region, loading a secondary segmentation group on the periphery, loading a secondary segmentation group at a distance, and loading a rough segmentation group on the background.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 4 when the computer program is executed.
7. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 4.
CN202210919619.7A 2022-08-02 2022-08-02 Storage and rendering scheduling method and device for oversized digital scene Active CN115272549B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210919619.7A CN115272549B (en) 2022-08-02 2022-08-02 Storage and rendering scheduling method and device for oversized digital scene

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210919619.7A CN115272549B (en) 2022-08-02 2022-08-02 Storage and rendering scheduling method and device for oversized digital scene

Publications (2)

Publication Number Publication Date
CN115272549A CN115272549A (en) 2022-11-01
CN115272549B true CN115272549B (en) 2023-12-15

Family

ID=83747983

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210919619.7A Active CN115272549B (en) 2022-08-02 2022-08-02 Storage and rendering scheduling method and device for oversized digital scene

Country Status (1)

Country Link
CN (1) CN115272549B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116524157B (en) * 2023-04-28 2024-05-14 神力视界(深圳)文化科技有限公司 Augmented reality synthesis method, device, electronic equipment and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001037220A1 (en) * 1999-11-18 2001-05-25 Info Assets, Inc. Rendering image data
KR20100136604A (en) * 2009-06-19 2010-12-29 (주)이지스 3D Terrain Image Real-Time Visualization System and Its Method
WO2012140361A1 (en) * 2011-04-12 2012-10-18 Real Fusio France Method and system for rendering a virtual scene in three dimensions
CN106599493A (en) * 2016-12-19 2017-04-26 重庆市勘测院 Visual implementation method of BIM model in three-dimensional large scene
CN109816763A (en) * 2018-12-24 2019-05-28 苏州蜗牛数字科技股份有限公司 A kind of method for rendering graph
CN110543716A (en) * 2019-08-29 2019-12-06 中国南方电网有限责任公司 three-dimensional overhead cable level power grid optimization method and device and computer equipment
CN110910505A (en) * 2019-11-29 2020-03-24 西安建筑科技大学 Accelerated rendering method of scene model
CN111932668A (en) * 2020-07-29 2020-11-13 武汉中地先进技术研究院有限公司 Three-dimensional visualization method, system, medium and electronic equipment for urban landscape model
CN112883240A (en) * 2021-03-10 2021-06-01 苏州思萃融合基建技术研究所有限公司 Data lightweight BIM (building information modeling) building model management method and system based on digital twin
KR102271064B1 (en) * 2020-04-17 2021-06-30 뉴레이어 주식회사 Floor separation method for 3D building model, system and computer readable medium recording the method
CN114494646A (en) * 2022-01-25 2022-05-13 上海秉匠信息科技有限公司 Scene rendering method and device and electronic equipment
CN114596423A (en) * 2022-02-16 2022-06-07 南方电网数字电网研究院有限公司 Model rendering method and device based on virtual scene gridding and computer equipment

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2001037220A1 (en) * 1999-11-18 2001-05-25 Info Assets, Inc. Rendering image data
KR20100136604A (en) * 2009-06-19 2010-12-29 (주)이지스 3D Terrain Image Real-Time Visualization System and Its Method
WO2012140361A1 (en) * 2011-04-12 2012-10-18 Real Fusio France Method and system for rendering a virtual scene in three dimensions
CN106599493A (en) * 2016-12-19 2017-04-26 重庆市勘测院 Visual implementation method of BIM model in three-dimensional large scene
CN109816763A (en) * 2018-12-24 2019-05-28 苏州蜗牛数字科技股份有限公司 A kind of method for rendering graph
CN110543716A (en) * 2019-08-29 2019-12-06 中国南方电网有限责任公司 three-dimensional overhead cable level power grid optimization method and device and computer equipment
CN110910505A (en) * 2019-11-29 2020-03-24 西安建筑科技大学 Accelerated rendering method of scene model
KR102271064B1 (en) * 2020-04-17 2021-06-30 뉴레이어 주식회사 Floor separation method for 3D building model, system and computer readable medium recording the method
CN111932668A (en) * 2020-07-29 2020-11-13 武汉中地先进技术研究院有限公司 Three-dimensional visualization method, system, medium and electronic equipment for urban landscape model
CN112883240A (en) * 2021-03-10 2021-06-01 苏州思萃融合基建技术研究所有限公司 Data lightweight BIM (building information modeling) building model management method and system based on digital twin
CN114494646A (en) * 2022-01-25 2022-05-13 上海秉匠信息科技有限公司 Scene rendering method and device and electronic equipment
CN114596423A (en) * 2022-02-16 2022-06-07 南方电网数字电网研究院有限公司 Model rendering method and device based on virtual scene gridding and computer equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
一种面向大规模动态图形场景的渲染优化方法;占伟伟 等;《信息技术与信息化》(第08期);37-40 *

Also Published As

Publication number Publication date
CN115272549A (en) 2022-11-01

Similar Documents

Publication Publication Date Title
US20230186546A1 (en) 3-d graphics rendering with implicit geometry
US12014258B2 (en) Method and device for optimizing simulation data, and computer-readable storage medium
CN112734641A (en) Training method and device of target detection model, computer equipment and medium
CN111126359A (en) High-definition image small target detection method based on self-encoder and YOLO algorithm
CN106952338B (en) Three-dimensional reconstruction method and system based on deep learning and readable storage medium
US10521958B2 (en) Computer handling of object silhouettes
WO2020224428A1 (en) Method for implanting information into video, computer device and storage medium
CN113761999A (en) Target detection method and device, electronic equipment and storage medium
CN115272549B (en) Storage and rendering scheduling method and device for oversized digital scene
CN113554589A (en) Semiconductor chip gold wire segmentation method and system based on deep learning
CN114882272A (en) Fusion analysis method for aerial manufacturing full-angle projection image surface patch attributes
CN114119834A (en) Rendering method, rendering device, electronic equipment and readable storage medium
CN119006678A (en) Three-dimensional Gaussian sputtering optimization method for pose-free input
CN114998108B (en) Vector data optimization processing method and system
US20220051055A1 (en) Training data generation method and training data generation device
CN119107651A (en) Method, device, computer equipment and storage medium for identifying text on workpiece surface
CN119068123A (en) A method, system, device and storage medium for reconstructing real three-dimensional scene
US20240119119A1 (en) Systems and methods for generating synthetic images of a training database
CN113744280A (en) Image processing method, apparatus, device and medium
CN112013820A (en) Real-time target detection method and device for deployment of airborne platform of unmanned aerial vehicle
CN116579409A (en) Intelligent camera model pruning acceleration method and acceleration system based on re-parameterization
CN113327195B (en) Image processing, image processing model training and image mode recognition method and device
CN116342800A (en) Semantic three-dimensional reconstruction method and system for multi-mode pose optimization
CN116091365B (en) Triangular surface-based three-dimensional model notch repairing method, triangular surface-based three-dimensional model notch repairing device, triangular surface-based three-dimensional model notch repairing equipment and medium
CN119206006B (en) Three-dimensional model data processing method, device, equipment, medium and product

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
GR01 Patent grant
GR01 Patent grant