Three-dimensional-model generation method and apparatus, and device and storage medium

Abstract

The present disclosure relates to a three-dimensional-model generation method and apparatus, and a device and a storage medium. The method comprises: acquiring three-dimensional point cloud data of a target object; acquiring reconstruction parameters for point cloud feature regions in the three-dimensional point cloud data; and performing multi-resolution grid reconstruction on the three-dimensional point cloud data on the basis of the reconstruction parameters for the point cloud feature regions, so as to generate a multi-resolution three-dimensional model of the target object.

Description

Three-dimensional model generation method, device, equipment and storage medium

[0001] Cross-reference

[0002] This disclosure claims priority to Chinese patent application number 202311766480.8, filed with the Patent Office of China on December 21, 2023, entitled “Three-dimensional model generation method, device, equipment and storage medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the technical field of three-dimensional model generation, and in particular to a three-dimensional model generation method, apparatus, device, and storage medium. Background Art

[0004] For three-dimensional models obtained by three-dimensional scanning, it is usually necessary to obtain multi-resolution three-dimensional models with different degrees of refinement. The multi-resolution three-dimensional model is mainly used to highlight the high-resolution area (i.e., the area of ​​interest) and simplify the low-resolution area (i.e., the area of ​​non-interest). It can not only simplify the model data and reduce the time spent on post-processing operations, but also ensure the accuracy of the post-processing results and meet the user's needs for model details.

[0005] For example, in digital oral restoration design applications, it is usually necessary to obtain multi-resolution three-dimensional models with different degrees of refinement. The multi-resolution three-dimensional model is mainly used to simplify the model data, highlight high-resolution areas (such as teeth) and simplify low-resolution areas (such as gums), so that when users perform tooth restoration or oral design and other processing operations based on the multi-resolution three-dimensional model, the time spent on post-processing operations can be reduced and the accuracy of the post-processing results can be guaranteed.

[0006] In related technologies, the region of interest is typically reconstructed into a fine mesh, while the non-region of interest is reconstructed into a coarse mesh. The fine and coarse meshes are then aligned and stitched together to generate a multi-resolution 3D model. However, this approach requires at least two reconstruction operations, which is cumbersome and resource-intensive. Furthermore, the stitched boundaries between the two meshes can easily produce triangular meshes that hinder computation, leading to stitching errors in the multi-resolution 3D model. Summary of the Invention

[0007] In order to solve the above technical problems, the present disclosure provides a three-dimensional model generation method, device, equipment and storage medium.

[0008] In a first aspect, an embodiment of the present disclosure provides a method for generating a three-dimensional model, the method comprising:

[0009] Obtain three-dimensional point cloud data of the target object;

[0010] Obtain reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data;

[0011] Based on the reconstruction parameters of each point cloud feature area, multi-resolution mesh reconstruction is performed on the three-dimensional point cloud data to generate a multi-resolution three-dimensional model of the target object.

[0012] In a second aspect, an embodiment of the present disclosure provides a three-dimensional model generation device, the device comprising:

[0013] A first acquisition module is configured to acquire three-dimensional point cloud data of a target object;

[0014] A second determination module is configured to obtain reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data;

[0015] The generation module is set to perform multi-resolution mesh reconstruction on the three-dimensional point cloud data based on the reconstruction parameters of each point cloud feature area, and generate a multi-resolution three-dimensional model of the target object.

[0016] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the device comprising:

[0017] one or more processors;

[0018] a storage device configured to store one or more programs,

[0019] When one or more programs are executed by one or more processors, the one or more processors implement the three-dimensional model generation method provided by the first aspect.

[0020] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the three-dimensional model generation method provided in the first aspect.

[0021] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art:

[0022] The disclosed embodiments provide a 3D model generation method, apparatus, device, and storage medium that obtains 3D point cloud data of a target object; obtains reconstruction parameters for each point cloud feature region within the 3D point cloud data; and, based on the reconstruction parameters for each point cloud feature region, performs multi-resolution mesh reconstruction on the 3D point cloud data to generate a multi-resolution 3D model of the target object. This allows for a single meshing process based on the reconstruction parameters for each point cloud feature region within the 3D point cloud data to produce 3D models with different resolutions, simplifying operations and reducing resource consumption, thereby improving the efficiency of generating multi-resolution 3D models. Furthermore, the meshing process is eliminated, thereby reducing errors in the multi-resolution 3D models. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0024] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] FIG1 is a schematic diagram of a flow chart of a three-dimensional model generation method provided by an embodiment of the present disclosure;

[0026] FIG2 is a schematic diagram of a flow chart of another three-dimensional model generation method provided by an embodiment of the present disclosure;

[0027] FIG3 is a schematic structural diagram of a three-dimensional model generating device provided by an embodiment of the present disclosure;

[0028] FIG4 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0031] It should be noted that multi-resolution 3D models are obtained by reconstructing the mesh of 3D point cloud data using 3D reconstruction technology. However, the large amount of 3D point cloud data is not conducive to the rapid generation of multi-resolution 3D models.

[0032] To quickly generate multi-resolution 3D models, 3D point cloud data is usually simplified while retaining the features of interest, and the simplified 3D point cloud data is then reconstructed into a mesh. The simplification process of 3D point cloud data involves a trade-off: the more the 3D point cloud data is simplified, the faster the multi-resolution 3D model can be reconstructed, but the fewer features can be retained; the less the 3D point cloud data is simplified, the slower the multi-resolution 3D model can be reconstructed, but the more features can be retained. Therefore, how to improve the efficiency of generating multi-resolution 3D models while retaining enough important features is a technical problem that urgently needs to be solved.

[0033] In addition to using the above-mentioned split-mold method to generate multi-resolution three-dimensional models, related technologies also use non-split-mold technology to obtain multi-resolution three-dimensional models. The specific method of the non-split-mold technology is to first use a lower resolution to quickly generate a coarse mesh model, then identify important feature areas from the coarse mesh model, and then generate high-resolution feature areas and low-resolution feature areas, and finally stitch the two feature areas into a complete multi-resolution three-dimensional model. However, this process requires at least two reconstruction operations, which is cumbersome and resource-intensive. In addition, a triangular mesh that hinders calculation is easily generated at the boundary where the two meshes are stitched, resulting in stitching errors in the multi-resolution three-dimensional model.

[0034] In order to improve the efficiency of generating multi-resolution three-dimensional models and reduce resource consumption, embodiments of the present disclosure provide a three-dimensional model generation method, apparatus, device, and storage medium.

[0035] The following describes the 3D model generation method provided by embodiments of the present disclosure in conjunction with Figures 1 and 2. In some embodiments of the present disclosure, the 3D model generation method can be performed by an electronic device. The electronic device can include a device with communication capabilities, such as a tablet computer, desktop computer, or laptop computer; a device simulated by a virtual machine or simulator; or a 3D scanning device that integrates the functions of the aforementioned devices.

[0036] FIG1 shows a schematic flow chart of a three-dimensional model generation method provided by an embodiment of the present disclosure.

[0037] As shown in FIG1 , the three-dimensional model generating method may include the following steps.

[0038] S110: Acquire three-dimensional point cloud data of the target object.

[0039] In some embodiments of the present disclosure, during the real-time scanning stage of the target object, the target object is scanned in real time to obtain three-dimensional point cloud data.

[0040] The target object may be an oral cavity, including but not limited to teeth, gums, prepared teeth, and a scanning rod, etc. The target object may also be a face, a part, etc.

[0041] Specifically, during the real-time scanning stage, the 3D scanner is controlled to scan the target object, and the scanning head of the 3D scanner is controlled to be within a working distance from the surface of the target object (for example, the working distance of an intraoral 3D scanner is generally 3-5 mm) to obtain a scanned image of the target object, which is then transmitted to the electronic device of the 3D scanner for three-dimensional reconstruction of the scanned image to obtain 3D point cloud data of the target object.

[0042] The scanned image is an image containing local features of the target object.

[0043] S120: Obtain reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data.

[0044] After the scanning phase is completed, the reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data are determined, so that a multi-resolution three-dimensional model can be reconstructed at one time based on the reconstruction parameters of each point cloud feature area.

[0045] The point cloud feature region refers to the local feature region in the 3D point cloud data. Different point cloud feature regions correspond to different point cloud feature region types.

[0046] The reconstruction parameters are parameters that instruct the electronic device to reconstruct the mesh of each point cloud feature area in the three-dimensional point cloud data. Optionally, the reconstruction parameters include but are not limited to resolution parameters or depth levels. The resolution parameter refers to the resolution or resolution level. A resolution level can correspond to one or more depth levels.

[0047] A multi-resolution 3D model refers to a mesh model with at least two regions having different resolutions. When a 3D scanner scans multiple feature-type regions of an object, it can reconstruct a multi-resolution mesh model corresponding to the feature-type regions with different resolution requirements. However, when a 3D scanner only scans a feature-type region of an object with a single resolution requirement, it can only reconstruct a single-resolution mesh model.

[0048] S130 , based on the reconstruction parameters of each point cloud feature area, reconstruct the three-dimensional point cloud data into a multi-resolution grid to generate a multi-resolution three-dimensional model of the target object.

[0049] In some embodiments of the present disclosure, after the scanning stage is completed, the three-dimensional point cloud data is meshed once based on the reconstruction parameters of each point cloud feature area to implement the process of performing multi-resolution mesh reconstruction and obtain a multi-resolution three-dimensional model of the target object.

[0050] Among them, the multi-resolution three-dimensional model integrates the grid models corresponding to each point cloud feature area.

[0051] For example, the reconstruction parameter is explained as a resolution parameter. The point cloud feature areas of the three-dimensional point cloud data include a high curvature preparation area (area of ​​interest) A, a low curvature preparation area B, a high curvature non-prepared area C and a low curvature non-prepared area (area of ​​non-interest) D. The resolution parameter corresponding to the high curvature preparation area (area of ​​interest) A is a, the resolution parameter corresponding to the low curvature preparation area B is 2a, the resolution parameter corresponding to the high curvature non-prepared area C is 2a, and the resolution parameter corresponding to the low curvature non-prepared area (area of ​​non-interest) D is 4a. Based on these three resolution parameters, the three-dimensional point cloud data in these four point cloud feature areas are meshed and reconstructed to obtain mesh models corresponding to the four point cloud feature areas respectively, and the mesh models corresponding to the four point cloud feature areas respectively form a multi-resolution three-dimensional model of the target object. There are three resolution areas in the multi-resolution three-dimensional model.

[0052] The disclosed embodiments provide a 3D model generation method that obtains 3D point cloud data of a target object; obtains reconstruction parameters for each point cloud feature region in the 3D point cloud data; and, based on the reconstruction parameters of each point cloud feature region, performs multi-resolution mesh reconstruction on the 3D point cloud data to generate a multi-resolution 3D model of the target object. This method enables a single meshing process to generate 3D models with different resolutions based on the reconstruction parameters of each point cloud feature region in the 3D point cloud data, simplifying the operation and reducing resource consumption, thereby improving the efficiency of generating multi-resolution 3D models. Furthermore, the method eliminates the need for mesh stitching operations, thereby reducing errors in the multi-resolution 3D models.

[0053] In some embodiments of the present disclosure, a specific explanation is given of the process of obtaining reconstruction parameters of each point cloud feature area in three-dimensional point cloud data.

[0054] FIG2 shows a flow chart of another three-dimensional model generation method provided by an embodiment of the present disclosure.

[0055] As shown in FIG2 , the three-dimensional model generating method may include the following steps.

[0056] S210: Acquire three-dimensional point cloud data of the target object.

[0057] Among them, S210 is similar to S110 and will not be described in detail here.

[0058] S220: Determine region type description information of each point cloud feature region in the three-dimensional point cloud data.

[0059] The region type description information refers to type information describing the type of the region, and is used to characterize the type of the region. Optionally, the region type description information can be in any form, including but not limited to digital information, texture information, and time information.

[0060] Taking two bits as an example, the region type description information is used to describe the curvature and tooth preparation characteristics. Specifically, the region type description information corresponding to the high-curvature tooth preparation area (area of ​​interest) A is 11, the region type description information corresponding to the low-curvature tooth preparation area B is 01, the region type description information corresponding to the high-curvature non-prepared area C is 10, and the region type description information corresponding to the low-curvature non-prepared area (non-area of ​​interest) D is 00.

[0061] In some embodiments of the present disclosure, specific implementations of S220 include but are not limited to the following:

[0062] S2201, performing grid processing on the three-dimensional point cloud data to obtain a temporary grid model of the target object;

[0063] S2202: Determine each grid feature region from the temporary grid model, and determine region type description information associated with each grid feature region;

[0064] S2203. Map each grid feature area to the three-dimensional point cloud data according to the mapping relationship between the temporary grid model and the three-dimensional point cloud data to obtain each point cloud feature area in the three-dimensional point cloud data, and use the area type description information associated with each grid feature area as the area type description information of each point cloud feature area.

[0065] At S2201, the electronic device may grid the 3D point cloud data according to a preset point spacing to obtain a temporary mesh model of the target object. The preset point spacing refers to the fusion point spacing used to reconstruct the 3D point cloud data into the temporary mesh model. The preset point spacing can be relatively large to generate a coarse mesh model as the temporary mesh model. The large point spacing of the temporary mesh model allows for rapid generation of the temporary mesh model, facilitating rapid processing and analysis of the temporary mesh model.

[0066] In S2202, the method for determining each grid feature area includes: using a region recognition model to perform region recognition processing on the temporary grid model to determine each grid feature area in the grid model; and / or, in response to multiple region determination operations, identifying regions corresponding to multiple region determination operations from the temporary grid model as each grid feature area in the temporary grid model, and obtaining region type description information associated with each grid feature area.

[0067] The region recognition model can be trained based on multiple reference grid models and region annotation information of the reference grid models. The region determination operation can be understood as a region division operation acting on the temporary grid model.

[0068] In S2203, since there is a mapping relationship between the temporary grid model and the three-dimensional point cloud data, each grid feature area on the temporary grid model has a corresponding point cloud feature area in the three-dimensional point cloud data. When each grid feature area is mapped to the three-dimensional point cloud data, the area type description information associated with each grid feature area is also mapped to the corresponding point cloud feature area, thereby determining the area type description information of each point cloud feature area.

[0069] The mapping relationship can be understood as the changing relationship between the temporary mesh model and the three-dimensional point cloud data.

[0070] S230 : Determine reconstruction parameters of each point cloud feature region based on the region type description information of each point cloud feature region.

[0071] In some embodiments of the present disclosure, the specific implementation method of S230 includes but is not limited to the following method: obtaining the resolution parameter or depth level associated with the area type description information of each point cloud feature area as the target resolution parameter or target depth level of each point cloud feature area.

[0072] Specifically, the electronic device first obtains the preset area type description information and the associated resolution parameters or depth levels, and then searches and matches the preset area type description information based on the area type description information of each point cloud feature area, and obtains the resolution parameters or depth levels associated with the area type description information of each point cloud feature area as the target resolution parameters or target depth levels of each point cloud feature area.

[0073] The preset region type description information may be region type description information of a point cloud feature region serving as a reference.

[0074] In order to accurately construct the grid model of each point cloud feature area, the corresponding area type description information and the corresponding resolution parameter or depth level are preset for the area type of each point cloud feature area. In this way, the resolution parameter or depth level of each point cloud feature area can be determined by matching the area type description information of each point cloud feature area with the preset area type description information, and the associated resolution parameter or depth level can be identified from the area type description information of each point cloud feature area, that is, the target resolution parameter or target depth level of each point cloud feature area is obtained, that is, the reconstruction parameter of each point cloud feature area is obtained.

[0075] In other cases, the reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data are determined on the basis of the region type description information associated with each grid feature area determined by S2202, and can also be determined in the following way: obtaining the resolution parameter or depth level associated with the region type description information of each grid feature area as the target resolution parameter or target depth level of each grid feature area; based on the mapping relationship between the temporary grid model and the three-dimensional point cloud data, mapping each grid feature area to the three-dimensional point cloud data, determining each point cloud feature area in the three-dimensional point cloud data, and using the target resolution parameter or target depth level of each grid feature area as the target resolution parameter or target depth level of each point cloud feature area.

[0076] Specifically, obtaining the resolution parameter or depth level associated with the region type description information of each grid feature area includes: obtaining preset region type description information and the associated resolution parameter or depth level; searching and matching in the preset region type description information based on the region type description information of each grid feature area, and obtaining the resolution parameter or depth level associated with the region type description information of each grid feature area as the target resolution parameter or target depth level of each grid feature area.

[0077] The preset region type description information may be region type description information of a grid feature region serving as a reference.

[0078] In order to accurately construct the grid model of each point cloud feature area, the corresponding area type description information and the corresponding resolution parameter or depth level are preset for the area type of each grid feature area. In this way, the resolution parameter or depth level of each grid feature area can be determined by matching the area type description information of each grid feature area with the preset area type description information, and the associated resolution parameter or depth level is identified from the area type description information of each grid feature area, that is, the target resolution parameter or target depth level of each grid feature area is obtained, and then the each point cloud feature area in the three-dimensional point cloud data is determined through mapping, and the target resolution parameter or target depth level of each grid feature area should be used as the target resolution parameter or target depth level of each point cloud feature area, that is, the reconstruction parameter of each point cloud feature area is obtained.

[0079] In this way, after the scanning stage is completed, the target resolution parameters or target depth levels of each point cloud feature area can be quickly obtained without complex analysis on the three-dimensional point cloud data. The associated target resolution parameters or target depth levels can be automatically identified from the area type description information of the point cloud feature area as the reconstruction parameters of each point cloud feature area.

[0080] S240 , based on the reconstruction parameters of each point cloud feature area, perform multi-resolution mesh reconstruction on the three-dimensional point cloud data to generate a multi-resolution three-dimensional model of the target object.

[0081] In some embodiments of the present disclosure, specific implementation methods of S240 include but are not limited to the following methods: S2401. According to a preset point distance or a preset maximum depth level, the spatial field where the three-dimensional point cloud data is located is hierarchically divided into spatial grids to obtain spatial grids with multiple depth levels with different resolution parameters; S2402. Based on the target resolution parameters or target depth levels of each point cloud feature area, the spatial grids corresponding to the depth level or resolution parameter of each point cloud feature area in the spatial field are extracted to generate a multi-resolution three-dimensional model of the target object.

[0082] In S2401, the preset point distance refers to the minimum point distance for hierarchical division of three-dimensional point cloud data, and the preset maximum depth level refers to the maximum depth level for hierarchical division of three-dimensional point cloud data. The side length of the spatial grid in the spatial grid is halved for each additional depth level, that is, the side length of the spatial grid in the spatial grid corresponding to different depth levels is an exponential multiple of 2. For example, if the spatial field where the three-dimensional point cloud data is located is divided into three depth levels, then the spatial field contains spatial grids of three depth levels, the side length of the spatial grid (i.e., voxel) in the spatial grid of the 0th depth level is 16, the side length of the spatial grid (i.e., voxel) in the spatial grid of the 1st depth level is 8, and the side length of the spatial grid (i.e., voxel) in the spatial grid of the 2nd depth level is 4. Naturally, the three spatial grids correspond to different resolution parameters.

[0083] The spatial field containing the three-dimensional point cloud data can be hierarchically divided into spatial grids using a preset spatial segmentation data structure. Optionally, the preset spatial segmentation data structure includes, but is not limited to, an octree spatial segmentation data structure, a quadtree spatial segmentation data structure, or other types of data structures.

[0084] In S2402, the spatial grid corresponding to the depth level or resolution parameter of each point cloud feature area in the spatial field can be understood as the spatial grid corresponding to the target depth level or target resolution parameter of each point cloud feature area. Since the spatial field where the three-dimensional point cloud data is located is hierarchically divided into spatial grids according to a preset point distance or a preset maximum depth level, each feature area of ​​the three-dimensional point cloud data has a spatial grid corresponding to a depth level or a resolution parameter, and since each point cloud feature area in the three-dimensional point cloud data is associated with a target resolution parameter or a target depth level, the spatial grid corresponding to each point cloud feature area at the target depth level or the target resolution parameter can be extracted based on the target resolution parameter or the target depth level of each point cloud feature area, so as to realize a one-time multi-resolution grid reconstruction and generate a multi-resolution three-dimensional model of the target object.

[0085] Specifically, the target resolution parameter or target depth level of each point cloud feature area can be the side length of its corresponding spatial grid. Based on the side length of the spatial grid corresponding to each point cloud feature area, multi-resolution grid reconstruction is performed at one time to generate a multi-resolution three-dimensional model of the target object.

[0086] Exemplarily, the point cloud feature areas of the three-dimensional point cloud data include a high curvature prepared area (area of ​​interest) A, a low curvature prepared area B, a high curvature non-prepared area C, and a low curvature non-prepared area (area of ​​non-interest) D. The target resolution parameter corresponding to the high curvature prepared area (area of ​​interest) A is a, the target resolution parameter corresponding to the low curvature prepared area B is 2a, the target resolution parameter corresponding to the high curvature non-prepared area C is 2a, and the target resolution parameter corresponding to the low curvature non-prepared area (area of ​​non-interest) D is 4a. Based on these four target resolution parameters, the spatial grids of the four point cloud feature areas corresponding to the target depth level or target resolution parameter in the spatial field are extracted to generate a multi-resolution three-dimensional model of the target object.

[0087] In this way, based on a preset point distance or a preset maximum depth level, the three-dimensional point cloud data can be simulated into a spatial field for spatial grid division, and based on the target resolution parameters or target depth levels of each point cloud feature area obtained, the spatial grid corresponding to the target depth level or target resolution parameter of each point cloud feature area in the spatial field is extracted to achieve a one-time reconstruction of a multi-resolution three-dimensional model of the target object, thereby improving the generation efficiency and accuracy of the multi-resolution model.

[0088] The present disclosure also provides a multi-resolution 3D model generation device for implementing the above-mentioned 3D model generation method, which is described below in conjunction with FIG3 . In some embodiments of the present disclosure, the multi-resolution 3D model generation device may be an electronic device. The electronic device may include a tablet computer, desktop computer, laptop computer, or other device with communication capabilities, or a device simulated by a virtual machine or simulator.

[0089] FIG3 shows a schematic structural diagram of a multi-resolution three-dimensional model generation device provided by an embodiment of the present disclosure.

[0090] As shown in FIG3 , a multi-resolution 3D model generating apparatus 300 may include:

[0091] A first acquisition module 310 is configured to acquire three-dimensional point cloud data of a target object;

[0092] The second acquisition module 320 is configured to obtain reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data;

[0093] The generation module 330 is configured to perform multi-resolution mesh reconstruction on the three-dimensional point cloud data based on the reconstruction parameters of each point cloud feature area to generate a multi-resolution three-dimensional model of the target object.

[0094] The disclosed embodiments provide a multi-resolution 3D model generation device that obtains 3D point cloud data of a target object; obtains reconstruction parameters for each point cloud feature region within the 3D point cloud data; and, based on the reconstruction parameters for each point cloud feature region, performs multi-resolution mesh reconstruction on the 3D point cloud data to generate a multi-resolution 3D model of the target object. This allows for a single meshing process based on the reconstruction parameters for each point cloud feature region within the 3D point cloud data to generate 3D models with different resolutions, simplifying operations and reducing resource consumption, thereby improving the efficiency of generating multi-resolution 3D models. Furthermore, the device eliminates the need for mesh stitching operations, thereby reducing errors in the multi-resolution 3D model.

[0095] In some embodiments of the present disclosure, the second acquisition module 320 includes:

[0096] A first determining unit is configured to determine region type description information of each point cloud feature region in the three-dimensional point cloud data;

[0097] The second determining unit is configured to determine the reconstruction parameters of each point cloud feature region based on the region type description information of each point cloud feature region.

[0098] In some embodiments of the present disclosure, the first determining unit is specifically configured to:

[0099] Perform grid processing on the three-dimensional point cloud data to obtain a temporary grid model of the target object;

[0100] Determine each grid feature area from the temporary grid model, and determine the area type description information associated with each grid feature area;

[0101] According to the mapping relationship between the temporary grid model and the three-dimensional point cloud data, each grid feature area is mapped to the three-dimensional point cloud data to obtain each point cloud feature area in the three-dimensional point cloud data, and the area type description information associated with each grid feature area is used as the area type description information of each point cloud feature area.

[0102] In some embodiments of the present disclosure, the first determining unit is further specifically configured to:

[0103] Using the region recognition model, performing region recognition processing on the temporary grid model to determine each grid feature region in the temporary grid model; and / or,

[0104] In response to the multiple region determination operations, regions corresponding to the multiple region determination operations are identified from the temporary grid model as respective grid feature regions in the temporary grid model.

[0105] In some embodiments of the present disclosure, the second acquisition module 320 includes:

[0106] A first acquiring unit is configured to acquire a resolution parameter or a depth level associated with the region type description information of each grid feature region as a target resolution parameter or a target depth level of each grid feature region;

[0107] The mapping unit is configured to map each grid feature area to the three-dimensional point cloud data based on a mapping relationship between the temporary grid model and the three-dimensional point cloud data, determine each point cloud feature area in the three-dimensional point cloud data, and use the target resolution parameter or target depth level of each grid feature area as the target resolution parameter or target depth level of each point cloud feature area.

[0108] In some embodiments of the present disclosure, the first acquiring unit is specifically configured to:

[0109] Get the preset region type description information and the associated resolution parameters or depth levels;

[0110] Based on the region type description information of each grid feature region, a search and match is performed in the preset region type description information to obtain the resolution parameter or depth level associated with the region type description information of each grid feature region as the target resolution parameter or target depth level of each grid feature region.

[0111] In some embodiments of the present disclosure, the second determining unit is specifically configured to:

[0112] The resolution parameter or depth level associated with the region type description information of each point cloud feature region is obtained as the target resolution parameter or target depth level of each point cloud feature region.

[0113] In some embodiments of the present disclosure, the second determining unit is further specifically configured to:

[0114] Get the preset region type description information and the associated resolution parameters or depth levels;

[0115] Based on the region type description information of each point cloud feature area, a search and match is performed in the preset region type description information to obtain the resolution parameter or depth level associated with the region type description information of each point cloud feature area as the target resolution parameter or target depth level of each point cloud feature area.

[0116] In some embodiments of the present disclosure, the generation module 330 includes:

[0117] A hierarchical division unit is configured to hierarchically divide the spatial field where the three-dimensional point cloud data is located into spatial grids according to a preset point distance or a preset maximum depth level, thereby obtaining spatial grid grids of multiple depth levels with different resolution parameters;

[0118] The generation unit is configured to extract a spatial grid corresponding to the depth level or resolution parameter of each point cloud feature area in the spatial field based on the target resolution parameter or target depth level of each point cloud feature area, and generate a multi-resolution three-dimensional model of the target object.

[0119] In some embodiments of the present disclosure, the first acquisition module 310 is specifically configured to:

[0120] In the real-time scanning stage, the three-dimensional scanner is controlled to scan the target object and obtain a scanned image of the target object;

[0121] The scanned image is reconstructed in three dimensions to obtain the three-dimensional point cloud data of the target object.

[0122] It should be noted that the multi-resolution three-dimensional model generation device 300 shown in Figure 3 can execute the various steps in the method embodiments shown in Figures 1 to 2, and realize the various processes and effects in the method embodiments shown in Figures 1 to 2, which will not be elaborated here.

[0123] FIG4 shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0124] As shown in FIG4 , the electronic device may include a processor 401 and a memory 402 storing computer program instructions.

[0125] Specifically, the processor 401 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present disclosure.

[0126] Memory 402 may include a large-capacity memory for storing information or instructions. By way of example, and not limitation, memory 402 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway device. In certain embodiments, memory 402 is non-volatile solid-state memory. In certain embodiments, memory 402 includes read-only memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0127] The processor 401 reads and executes the computer program instructions stored in the memory 402 to perform the steps of the three-dimensional model generation method provided in the embodiment of the present disclosure.

[0128] In one example, the electronic device may further include a transceiver 403 and a bus 404. As shown in FIG4 , the processor 401, the memory 402, and the transceiver 403 are connected via the bus 404 and communicate with each other.

[0129] Bus 404 includes hardware, software or both. For example, and not limitation, bus may include Accelerated Graphics Port (AGP) or other graphics bus, Extended Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industrial Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local Bus (VLB) bus or other suitable bus or a combination of two or more of these. Where appropriate, bus 404 may include one or more buses. Although the present disclosure describes and illustrates a specific bus, the present disclosure contemplates any suitable bus or interconnection.

[0130] The following is an embodiment of a computer-readable storage medium provided in an embodiment of the present disclosure. The computer-readable storage medium and the three-dimensional model generation method of the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the computer-readable storage medium, please refer to the embodiment of the above-mentioned three-dimensional model generation method.

[0131] The present disclosure provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are configured to perform a three-dimensional model generation method. The method includes:

[0132] Obtain three-dimensional point cloud data of the target object;

[0133] Obtain reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data;

[0134] Based on the reconstruction parameters of each point cloud feature area, multi-resolution mesh reconstruction is performed on the three-dimensional point cloud data to generate a multi-resolution three-dimensional model of the target object.

[0135] Of course, the storage medium containing computer-executable instructions provided by the embodiment of the present disclosure is not limited to the above method operations, and its computer-executable instructions can also execute related operations in the three-dimensional model generation method provided by any embodiment of the present disclosure.

[0136] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present disclosure can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer cloud platform (which can be a personal computer, server, or network cloud platform, etc.) to execute the three-dimensional model generation method provided by each embodiment of the present disclosure.

[0137] Note that the above are only preferred embodiments of the present disclosure and the technical principles employed. Those skilled in the art will understand that the present disclosure is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present disclosure. Therefore, although the present disclosure has been described in more detail through the above embodiments, the present disclosure is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present disclosure, and the scope of the present disclosure is determined by the scope of the appended claims. Industrial Applicability

[0138] The technical solutions provided by this disclosure can be applied to the field of 3D model generation technology. The 3D model generation method provided by the embodiments of this disclosure can obtain 3D point cloud data of a target object; obtain reconstruction parameters for each point cloud feature region in the 3D point cloud data; and, based on the reconstruction parameters of each point cloud feature region, perform multi-resolution mesh reconstruction on the 3D point cloud data to generate a multi-resolution 3D model of the target object. This allows for a one-time meshing process to produce 3D models with different resolutions based on the reconstruction parameters of each point cloud feature region in the 3D point cloud data, simplifying operational difficulty and reducing resource consumption, thereby improving the efficiency of generating multi-resolution 3D models. Furthermore, the method eliminates the need for mesh stitching operations, thereby reducing errors in the multi-resolution 3D models.

Claims

1. A three-dimensional model generation method, comprising: Obtain three-dimensional point cloud data of the target object; Obtaining reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data; Based on the reconstruction parameters of each point cloud feature area, the three-dimensional point cloud data is reconstructed into a multi-resolution grid to generate a multi-resolution three-dimensional model of the target object.

2. The method according to claim 1, wherein: The step of obtaining reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data includes: Determine region type description information of each point cloud feature region in the three-dimensional point cloud data; Based on the region type description information of each point cloud feature region, a reconstruction parameter of each point cloud feature region is determined.

3. The method according to claim 2, wherein: The determining of the region type description information of each point cloud feature region in the three-dimensional point cloud data includes: Performing grid processing on the three-dimensional point cloud data to obtain a temporary grid model of the target object; Determine each grid feature area from the temporary grid model, and determine the area type description information associated with each grid feature area; According to the mapping relationship between the temporary grid model and the three-dimensional point cloud data, each grid feature area is mapped to the three-dimensional point cloud data to obtain each point cloud feature area in the three-dimensional point cloud data, and the area type description information associated with each grid feature area is used as the area type description information of each point cloud feature area.

4. The method according to claim 3, wherein: The gridding process of the three-dimensional point cloud data to obtain a temporary grid model of the target object includes: The three-dimensional point cloud data is meshed according to a preset point distance to obtain a temporary mesh model of the target object, wherein the preset point distance is greater than a preset threshold.

5. The method according to claim 3, wherein: Determining each grid feature area from the temporary grid model includes: Using a region recognition model, performing region recognition processing on the temporary grid model to determine each grid feature region in the temporary grid model; and / or, In response to a plurality of region determination operations, regions respectively corresponding to the plurality of region determination operations are identified from the temporary grid model as respective grid feature regions in the temporary grid model.

6. The method according to claim 3, wherein: The step of obtaining reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data includes: Acquire a resolution parameter or a depth level associated with the region type description information of each grid feature region as a target resolution parameter or a target depth level of each grid feature region; Based on the mapping relationship between the temporary grid model and the three-dimensional point cloud data, each grid feature area is mapped to the three-dimensional point cloud data, each point cloud feature area in the three-dimensional point cloud data is determined, and the target resolution parameter or target depth level of each grid feature area is used as the target resolution parameter or target depth level of each point cloud feature area.

7. The method according to claim 6, wherein: The obtaining of the resolution parameter or depth level associated with the region type description information of each grid feature region includes: Get the preset region type description information and the associated resolution parameters or depth levels; Based on the region type description information of each grid feature region, a search and match is performed in the preset region type description information to obtain the resolution parameter or depth level associated with the region type description information of each grid feature region as the target resolution parameter or target depth level of each grid feature region.

8. The method according to claim 2, wherein: The determining, based on the region type description information of each point cloud feature region, reconstruction parameters of each point cloud feature region includes: The resolution parameter or the depth level associated with the region type description information of each point cloud feature region is obtained as the target resolution parameter or the target depth level of each point cloud feature region.

9. The method according to claim 8, wherein: The obtaining of the resolution parameter or depth level associated with the region type description information of each point cloud feature region includes: Get the preset region type description information and the associated resolution parameters or depth levels; Based on the region type description information of each point cloud feature region, a search and match is performed in the preset region type description information to obtain the resolution parameter or depth level associated with the region type description information of each point cloud feature region as the target resolution parameter or target depth level of each point cloud feature region.

10. The method according to any one of claims 2 to 9, wherein: The type of the region type description information includes at least one of the following: digital information, texture information, and time information.

11. The method according to any one of claims 6 to 9, wherein: The step of reconstructing the three-dimensional point cloud data into a multi-resolution grid based on the reconstruction parameters of each point cloud feature area to generate a multi-resolution three-dimensional model of the target object includes: According to a preset point distance or a preset maximum depth level, the spatial field where the three-dimensional point cloud data is located is hierarchically divided into spatial grids to obtain spatial grids of multiple depth levels with different resolution parameters; Based on the target resolution parameters or target depth levels of the respective point cloud feature regions, spatial grids of the respective point cloud feature regions corresponding to the depth levels or resolution parameters in the spatial field are extracted to generate a multi-resolution three-dimensional model of the target object.

12. The method according to claim 11, wherein: The step of hierarchically dividing the spatial field where the three-dimensional point cloud data is located into spatial grids comprises: The spatial field where the three-dimensional point cloud data is located is hierarchically divided into spatial grids according to a preset spatial segmentation data structure, wherein the preset spatial segmentation data structure includes at least one of the following: an octree spatial segmentation data structure and a quadtree spatial segmentation data structure.

13. The method according to claim 11, wherein: The target resolution parameter or target depth level of each point cloud feature region is the side length of the spatial grid corresponding to each point cloud feature region in the spatial field.

14. The method according to claim 1, wherein: The step of obtaining the three-dimensional point cloud data of the target object includes: In the real-time scanning stage, the three-dimensional scanner is controlled to scan the target object to obtain a scanned image of the target object; The scanned image is three-dimensionally reconstructed to obtain three-dimensional point cloud data of the target object.

15. The method according to claim 14, wherein: The controlling the three-dimensional scanner to scan the target object and obtaining a scanned image of the target object comprises: The scanning head of the three-dimensional scanner is controlled to scan the target object within a preset working distance from the surface of the target object to obtain a scanned image of the target object, wherein the scanned image is an image including local features of the target object.

16. The method according to claim 15, wherein: The point cloud feature region is a local feature region in the three-dimensional point cloud data.

17. A multi-resolution three-dimensional model generation device, comprising: A first acquisition module is configured to acquire three-dimensional point cloud data of a target object; A second acquisition module is configured to acquire reconstruction parameters of each point cloud feature area in the three-dimensional point cloud data; The generation module is configured to perform multi-resolution mesh reconstruction on the three-dimensional point cloud data based on the reconstruction parameters of each point cloud feature area to generate a multi-resolution three-dimensional model of the target object.

18. An electronic device, comprising: processor; a memory configured to store executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the method according to any one of claims 1 to 16.

19. A computer-readable storage medium, wherein: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method according to any one of claims 1 to 16.

Images