Method and apparatus for acquiring three-dimensional model, and device and storage medium

Abstract

A method for acquiring a three-dimensional model. The method comprises: acquiring an initial three-dimensional model and a plurality of original single-frame textures of a target object, wherein the initial three-dimensional model is generated on the basis of a plurality of target single-frame point clouds, and each target single-frame point cloud is determined after point cloud data to be deleted is removed from an original single-frame point cloud; removing, from the plurality of original single-frame textures, texture data corresponding to said point cloud data, so as to obtain a plurality of target single-frame textures; and rendering the plurality of target single-frame textures on the initial three-dimensional model, so as to obtain a target three-dimensional model of the target object.

Description

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

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on September 28, 2023, with application number 202311280633.8, and invention name “Method, device, equipment and storage medium for obtaining three-dimensional models”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the technical field of three-dimensional model generation, and in particular to a method, apparatus, device, and storage medium for acquiring a three-dimensional model. Background Art

[0003] When faced with needs such as oral restoration, the texture data of target objects such as teeth, prepared teeth, and gums are generally rendered onto a three-dimensional model determined based on point cloud data. This makes it easier to obtain the rendered model of the target object and allows users to analyze the rendered model to solve problems such as oral restoration.

[0004] In many cases, the point cloud data of the target object often contains lip data and impurity data waiting to be deleted. In this case, it is necessary to remove this data from the point cloud data and determine the 3D model based on the point cloud data without the data to be deleted. However, the texture data corresponding to the data to be deleted will still be retained. If the texture that retains the data to be deleted is directly rendered onto the 3D model without the data to be deleted, the rendering result of the 3D model will not match the user's expectations, thus affecting the user's ability to accurately analyze the rendering results.

[0005] Summary of the Invention

[0006] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and storage medium for obtaining a three-dimensional model.

[0007] In a first aspect, the present disclosure provides a method for obtaining a three-dimensional model, the method comprising:

[0008] Acquire an initial three-dimensional model of a target object and multiple original single-frame textures, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point clouds are determined by removing point cloud data to be deleted from the original single-frame point clouds;

[0009] Removing texture data corresponding to the to-be-deleted point cloud data from the multiple original single-frame textures to obtain multiple target single-frame textures;

[0010] The multiple target single-frame textures are rendered onto the initial three-dimensional model to obtain a target three-dimensional model of the target object.

[0011] In a second aspect, the present disclosure provides a device for acquiring a three-dimensional model, the device comprising:

[0012] an acquisition module, configured to acquire a plurality of original single-frame point clouds of the target object and determine a to-be-deleted area of ​​the target object;

[0013] a determination module configured to remove the to-be-deleted point cloud data from the original single-frame point cloud based on the to-be-deleted area to obtain the target single-frame point cloud;

[0014] The rendering module is configured to perform grid fusion on the target single-frame point cloud to obtain the initial three-dimensional model.

[0015] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the device comprising:

[0016] a processor, a memory, and executable instructions stored in the memory;

[0017] The processor reads the executable instructions from the memory and implements the method provided in the first aspect when executing the executable instructions.

[0018] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the method provided in the first aspect when the computer program is executed by a processor.

[0019] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art:

[0020] The disclosed embodiments provide a method, apparatus, device, and storage medium for acquiring a three-dimensional model, which acquires an initial three-dimensional model and multiple original single-frame textures of a target object, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point cloud is determined after removing the point cloud data to be deleted from the original single-frame point cloud; removes the texture data corresponding to the point cloud data to be deleted from the multiple original single-frame textures to obtain multiple target single-frame textures; and renders the multiple target single-frame textures onto the initial three-dimensional model to obtain a target three-dimensional model of the target object. Thus, based on the data to be deleted removed from the original single-frame point cloud, the corresponding texture can be removed from the texture data, and the texture data after the corresponding texture is removed can be rendered onto the initial three-dimensional model, thereby rendering a rendering result that meets the user's expectations, making it convenient for the user to accurately analyze the rendering result to obtain accurate information such as accurate dental restoration recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] 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.

[0023] FIG1 is a schematic diagram of a tooth to be scanned including labial data provided by the prior art;

[0024] FIG2 is a rendered target 3D model including lip side data provided by the prior art;

[0025] FIG3 is a schematic diagram of a rendering result with an occlusion effect provided by the prior art;

[0026] FIG4 is a schematic diagram of a flow chart of a method for acquiring a three-dimensional model provided in an embodiment of the present disclosure;

[0027] FIG5 is a schematic diagram of an initial three-dimensional model provided by an embodiment of the present disclosure;

[0028] FIG6 is a schematic diagram of a target three-dimensional model provided by an embodiment of the present disclosure;

[0029] FIG7 is a schematic flow chart of another method for acquiring a three-dimensional model provided in an embodiment of the present disclosure;

[0030] FIG8 is a schematic structural diagram of a device for acquiring a three-dimensional model provided by an embodiment of the present disclosure;

[0031] FIG9 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] 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.

[0033] 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.

[0034] During the scanning process of the target object, the black and white camera on the 3D scanner is used to collect the point cloud data of the target object, and the texture data of the target object is collected by the texture camera. The point cloud data is then meshed and fused to generate an initial 3D model. The texture data is then rendered onto the initial 3D model to obtain a rendered target 3D model of the target object.

[0035] In one case, the point cloud data and texture data may include data to be deleted (for example, labial data of the gums of the target object). After mesh fusion of the point cloud data is performed to obtain an initial three-dimensional model, the data to be deleted can be removed from the initial three-dimensional model, but the data to be deleted is still retained in the texture data. The texture data retaining the data to be deleted is then rendered onto the initial three-dimensional model to obtain a rendered target three-dimensional model.

[0036] In another case, when the target object is scanned, the point cloud data and texture data do not include the deleted data. During the scanning process, the texture of the target object may change (for example, the user draws a tooth edge line on the target object). At this time, the point cloud data and texture data include the deleted data. After the point cloud data is meshed and fused to obtain the initial three-dimensional model, the data to be deleted can be removed from the initial three-dimensional model, and then all the collected texture data can be rendered onto the initial three-dimensional model to obtain a rendered three-dimensional model.

[0037] For ease of understanding, Figure 1 shows a schematic diagram of the teeth to be scanned including lip data, and Figure 2 shows a rendered target three-dimensional model including lip data. The curved box in Figure 1 is the user's upper lip. After scanning the teeth to be scanned in Figure 1, the point cloud data and texture data include data to be deleted (i.e., lip data). After meshing the point cloud data to obtain the initial three-dimensional model, the data to be deleted can be removed from the initial three-dimensional model, but the lip data is still retained in the texture data. The texture data that retains the lip data is then rendered onto the initial three-dimensional model from which the data to be deleted has been removed, resulting in the rendered target three-dimensional model shown in Figure 2, wherein the rectangular box in Figure 2 contains the lip data.

[0038] It can be seen that the existing solution is to render the texture that retains the data to be deleted onto the initial three-dimensional model from which the data to be deleted has been removed. This results in the rendering result of the target three-dimensional model not being consistent with the result expected by the user, thereby affecting the user's accurate analysis of the rendering result.

[0039] In related technologies, 3D scanners can also collect point cloud data and texture data of target objects at different viewing angles. However, the initial 3D model generated after mesh fusion of the point cloud data may have occlusion problems (for example, a local mesh area will occlude another part of the local mesh area at a specific imaging viewing angle). At the same time, the texture data includes all the textures of the local mesh area at a specific viewing angle of the user and part of the texture of the occluded local mesh area. At this time, after rendering the texture data onto the initial 3D model, the texture data at a specific viewing angle will be simultaneously rendered onto the occluded local mesh area. This rendering result is obviously not realistic, and therefore does not match the rendering result expected by the user.

[0040] To facilitate understanding, Figure 3 shows a schematic diagram of a rendering result with occlusion effects. The squares in Figure 3 represent texture data, which is rendered onto both the occluding and occluded teeth. As can be seen, different teeth correspond to the same rendering result, which could lead to incorrect analysis by the user. Therefore, this rendering result is consistent with the user's expectations.

[0041] In order to render a rendering result that meets user expectations, the embodiments of the present disclosure provide a method, apparatus, device, and storage medium for acquiring a three-dimensional model.

[0042] The following describes the method for obtaining a three-dimensional model provided by an embodiment of the present disclosure in conjunction with Figures 4 to 7. In the embodiment of the present disclosure, the method for obtaining a three-dimensional model can be performed by an electronic device. The electronic device can include a device with communication capabilities, such as a tablet computer, a desktop computer, or a laptop computer, and can also include a device simulated by a virtual machine or simulator.

[0043] FIG4 shows a schematic flow chart of a method for acquiring a three-dimensional model provided in an embodiment of the present disclosure.

[0044] As shown in FIG4 , the method for obtaining the three-dimensional model may include the following steps.

[0045] S410. Acquire an initial three-dimensional model and multiple original single-frame textures of the target object, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point cloud is determined by removing point cloud data to be deleted from the original single-frame point cloud.

[0046] In this embodiment, before the user gives oral restoration suggestions, the user uses a handheld 3D scanner to scan multiple target objects in the oral cavity. During the scanning process, the black and white camera on the 3D scanner is used to collect multiple original single-frame point clouds of the multiple target objects, and the texture camera on the 3D scanner is used to collect multiple original single-frame textures of the multiple target objects, thereby obtaining point cloud data and texture data of each target object.

[0047] Furthermore, the 3D scanner transmits the collected multiple original single-frame textures and multiple original single-frame point clouds to the electronic device. When the gums of the target subject are covered by the lips, the multiple original single-frame textures and the multiple original single-frame textures contain deleted data (e.g., lip data). The electronic device can remove the to-be-deleted point clouds from the multiple original single-frame point clouds to obtain multiple target single-frame point clouds, and generate an initial 3D model based on the multiple target single-frame point clouds.

[0048] The target object may be a tooth, a prepared tooth or a gum in the oral cavity.

[0049] Among them, the original single-frame point cloud is point cloud data obtained by reconstructing the depth map collected by the 3D scanner.

[0050] Optionally, the point cloud data to be deleted includes but is not limited to data on the edge of the scanning head area, lip side data, impurity data, and point clouds corresponding to the data to be deleted.

[0051] In this embodiment, the methods for obtaining the initial three-dimensional model of the target object include but are not limited to the following methods:

[0052] Acquire multiple original single-frame point clouds of the target object and determine the area to be deleted of the target object; based on the area to be deleted, remove the point cloud data to be deleted from the original single-frame point cloud to obtain the target single-frame point cloud; perform grid fusion on the target single-frame point cloud to obtain an initial three-dimensional model.

[0053] In one case, a method for determining a to-be-deleted area of ​​a target object includes: performing region recognition processing on a plurality of original single-frame point clouds using a pre-trained recognition model to obtain the to-be-deleted area of ​​the target object.

[0054] In another embodiment, a method for determining a to-be-deleted region of a target object includes: determining the to-be-deleted region on the three-dimensional model in response to a region selection operation on the initial three-dimensional model.

[0055] Among them, the area to be deleted can be located in the pixel coordinate system, and the original single-frame point cloud is located in the world coordinate system. Then, based on the conversion relationship between the pixel coordinate system and the world coordinate system, the area to be deleted is mapped to multiple original single-frame point clouds, the point cloud deletion area in the original single-frame point cloud is determined, and the point cloud data to be deleted in the point cloud deletion area is removed from the multiple original single-frame point clouds to obtain multiple target single-frame point clouds.

[0056] The initial three-dimensional model can be understood as a mesh model, which is formed by mesh fusion of multiple target single-frame point clouds, and includes vertices and triangular facets.

[0057] In order to facilitate users to view the scanning results in real time, after obtaining multiple original single-frame point clouds of the target object, the following steps can also be included: sampling and processing the original single-frame point cloud according to a first sampling method to obtain first sampling data in the original single-frame point cloud; grid fusion is performed on the first sampling data to obtain a real-time reconstructed model, and the real-time reconstructed model is displayed.

[0058] Among them, the first sampling method includes but is not limited to random sampling method, fixed-point sampling method and fixed-distance sampling method.

[0059] It is understandable that during the scanning process, grid fusion is performed based on the collected part of the original single-frame point cloud, which can quickly generate a real-time three-dimensional model, making it convenient for users to quickly determine whether there are unscanned teeth based on the real-time three-dimensional model and decide whether to continue scanning, thereby improving the user's scanning experience.

[0060] In order to facilitate the user to analyze the initial three-dimensional model, the target single-frame point cloud is mesh-fused to obtain the initial three-dimensional model, including but not limited to the following methods: sampling the target single-frame point cloud according to the second sampling method to obtain second sampling data in the target single-frame point cloud; mesh-fusion is performed on the second sampling data to obtain the initial three-dimensional model.

[0061] Among them, the second sampling method includes but is not limited to random sampling method, fixed-point sampling method and fixed-distance sampling method.

[0062] Figure 5 shows a schematic diagram of the initial 3D model. In one embodiment, since the initial 3D model is generated by sampling a single-frame point cloud of the target, the initial 3D model is generated quickly, allowing the user to accurately and quickly analyze the initial 3D model shown in Figure 5 to meet the user's scanning needs.

[0063] S420 , removing texture data corresponding to the point cloud data to be deleted from the multiple original single-frame textures to obtain multiple target single-frame textures.

[0064] In order to obtain rendering results that meet user expectations, after removing the point cloud data to be deleted from multiple original single-frame point clouds to obtain multiple target single-frame point clouds, it is also necessary to remove the corresponding texture data from the multiple original single-frame textures, so that the data on the edge of the scanning head area, the lip side data, the impurity data to be deleted can also be deleted in the texture data to obtain multiple target single-frame textures.

[0065] In this embodiment, the specific implementation method of S420 includes but is not limited to the following methods: mapping the point cloud data to be deleted from multiple original single-frame point clouds to multiple original single-frame textures, determining the texture data to be deleted in the multiple original single-frame textures; removing the texture data of the texture data to be deleted from the multiple original single-frame textures to obtain multiple target single-frame textures.

[0066] Specifically, the electronic device can determine a first mapping relationship between the original single-frame point cloud and the original single-frame texture according to the scanning timing of the target object, and then map the point cloud data to be deleted from multiple original single-frame point clouds to multiple original single-frame textures based on the first mapping relationship, determine the texture data to be deleted, so that the texture data to be deleted is determined in the multiple original single-frame textures, and the texture data to be deleted is removed from the multiple original single-frame textures, thereby retaining the texture data other than the lip side data, impurity data and the data to be deleted.

[0067] S430 , rendering multiple target single-frame textures onto the target single-frame point cloud of the initial three-dimensional model to obtain a target three-dimensional model of the target object.

[0068] The target three-dimensional model can also be understood as a mesh model, which is formed by fusion of multiple target single-frame point clouds after rendering multiple target single-frame textures, and includes vertices and triangles.

[0069] FIG6 shows a schematic diagram of a target three-dimensional model provided by an embodiment of the present disclosure. It is understandable that since the multiple target single-frame textures are texture data with lip side data, impurity data, and other data to be deleted removed, and the multiple target single-frame point clouds of the initial three-dimensional model are point cloud data with lip side data, impurity data, and other data to be deleted removed, rendering the multiple target single-frame textures onto the target single-frame point cloud of the initial three-dimensional model can produce the rendering result shown in FIG6 that meets the user's expectations, making it convenient for the user to accurately analyze the rendering result.

[0070] A method for acquiring a three-dimensional model according to an embodiment of the present disclosure acquires an initial three-dimensional model and multiple original single-frame textures of a target object, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point clouds are determined after removing the point cloud data to be deleted from the original single-frame point clouds; the texture data corresponding to the point cloud data to be deleted are removed from the multiple original single-frame textures to obtain multiple target single-frame textures; the multiple target single-frame textures are rendered onto a tooth three-dimensional model to obtain a target three-dimensional model of the target object. Thus, based on the data to be deleted removed from the original single-frame point cloud, the corresponding texture can be removed from the texture data, and the texture data after the corresponding texture is removed can be rendered onto the initial three-dimensional model, thereby rendering a rendering result that meets the user's expectations, making it convenient for the user to accurately analyze the rendering result to obtain accurate information such as tooth restoration suggestions.

[0071] In another embodiment of the present disclosure, in order to solve the problem of occluding teeth and occluded teeth being rendered with the same texture data, the texture data can be rendered onto the initial three-dimensional model based on depth information, so that different local mesh areas are rendered with their respective corresponding texture data.

[0072] FIG7 shows a schematic flow chart of another method for acquiring a three-dimensional model provided in an embodiment of the present disclosure.

[0073] As shown in FIG7 , the method for obtaining the three-dimensional model may include the following steps.

[0074] S710. Acquire an initial three-dimensional model and multiple original single-frame textures of the target object, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point cloud is determined by removing point cloud data to be deleted from the original single-frame point cloud.

[0075] S720 : Remove texture data corresponding to the point cloud data to be deleted from the multiple original single-frame textures to obtain multiple target single-frame textures.

[0076] Among them, S710 to S720 are similar to S410 to S420 and are not described in detail here.

[0077] S730: Obtain a first depth map of the target single-frame point cloud at a corresponding imaging perspective.

[0078] In this embodiment, during the scanning phase of the target object, the target object can be scanned at multiple different imaging perspectives to obtain first depth maps at multiple different imaging perspectives. The first depth maps at multiple different imaging perspectives are then reconstructed to generate an original single-frame point cloud. The point cloud data to be deleted is then removed from the original single-frame point cloud to determine a target single-frame point cloud. Thus, the target single-frame point cloud can correspond to the first depth maps at multiple different imaging perspectives.

[0079] The first depth map under each imaging perspective may include depth information corresponding to the target single-frame point cloud.

[0080] S740: Determine a second mapping relationship between the target single-frame texture and the first depth map according to the first mapping relationship between the original single-frame point cloud and the original single-frame texture.

[0081] It is understandable that the target single-frame texture is determined by the original single-frame texture, the target single-frame point cloud is determined by the original single-frame point cloud, and the original single-frame point cloud and the original single-frame texture have a first mapping relationship, so the target single-frame point cloud and the target single-frame texture also have a first mapping relationship. Then, because the target single-frame point cloud corresponds to the first depth map under multiple different imaging perspectives, the second mapping relationship can be determined based on the first mapping relationship and the corresponding relationship between the target single-frame point cloud and the first depth map under multiple different imaging perspectives.

[0082] S750: Obtain a second depth map of the initial three-dimensional model at a corresponding imaging perspective.

[0083] In this embodiment, after the initial three-dimensional model is obtained, back-projection processing may be performed on the initial three-dimensional model at multiple viewing angles to obtain second depth maps at multiple different imaging viewing angles.

[0084] It is understood that the initial 3D model includes multiple local grid regions, each of which is associated with a target single-frame point cloud, and each target single-frame point cloud corresponds to a second depth map. Since the initial 3D model is in stereoscopic form, after back-projecting the initial 3D model from multiple different imaging perspectives, each imaging perspective corresponds to one or more second depth maps.

[0085] S760 : Render the target single-frame texture onto the initial three-dimensional model according to the first depth map and the second depth map under the same imaging perspective to obtain a target three-dimensional model of the target object.

[0086] In this embodiment, specific implementations of S760 include but are not limited to the following:

[0087] Target depth information equal to the first depth map is obtained from at least one second depth map; and a target single-frame texture is rendered to a target grid area corresponding to the target depth information to obtain a target three-dimensional model.

[0088] It can be understood that any imaging perspective corresponds to a first depth map, but any imaging perspective may correspond to one or more second depth maps. Therefore, when the first depth information in a first depth map is not equal to the second depth information in the second depth map, the local grid area corresponding to the second depth information is not the local grid area corresponding to the target single-frame texture. If rendering is performed directly, the texture data under the imaging perspective will be rendered to the local grid area where occlusion occurs, which will cause a rendering error.

[0089] In order to solve this problem, we first obtain target depth information equal to the first depth map from the second depth map under the same imaging perspective, so that the local grid area corresponding to the second depth information is the local grid area corresponding to the target single-frame texture, and the local grid area is used as the target grid area. Then, the target single-frame texture is rendered to the target grid area corresponding to the target depth information to obtain the target three-dimensional model, avoiding the problem that texture data under a certain imaging perspective is simultaneously rendered to the local grid area where occlusion occurs, thereby obtaining a target three-dimensional model that meets user expectations.

[0090] The present disclosure also provides a 3D model acquisition device for implementing the above-mentioned 3D model acquisition method, which is described below in conjunction with FIG8 . In the present disclosure, the 3D model acquisition device can be an electronic device. The electronic device can include a tablet computer, desktop computer, laptop computer, or other device with communication capabilities, or a device simulated by a virtual machine or simulator.

[0091] FIG8 shows a schematic structural diagram of a three-dimensional model acquisition device provided by an embodiment of the present disclosure.

[0092] As shown in FIG8 , the three-dimensional model acquisition device 800 may include:

[0093] An acquisition module 810 is configured to acquire an initial three-dimensional model of a target object and a plurality of original single-frame textures, wherein the initial three-dimensional model is generated based on a plurality of target single-frame point clouds, and the target single-frame point clouds are determined by removing point cloud data to be deleted from the original single-frame point clouds;

[0094] The determining module 820 is configured to remove the texture data corresponding to the to-be-deleted point cloud data from the plurality of original single-frame textures to obtain a plurality of target single-frame textures;

[0095] The rendering module 830 is configured to render the multiple target single-frame textures onto the target single-frame point cloud of the initial three-dimensional model to obtain a target three-dimensional model of the target object.

[0096] The disclosed embodiment provides a device for acquiring a three-dimensional model, which acquires an initial three-dimensional model and multiple original single-frame textures of a target object, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point clouds are determined after removing the point cloud data to be deleted from the original single-frame point clouds; the texture data corresponding to the point cloud data to be deleted are removed from the multiple original single-frame textures to obtain multiple target single-frame textures; the multiple target single-frame textures are rendered onto the initial three-dimensional model to obtain a target three-dimensional model of the target object. Thus, based on the data to be deleted removed from the original single-frame point cloud, the corresponding texture can be removed from the texture data, and the texture data after the corresponding texture is removed can be rendered onto the initial three-dimensional model, thereby rendering a rendering result that meets the user's expectations, making it convenient for the user to accurately analyze the rendering result to obtain accurate information such as accurate dental restoration recommendations.

[0097] In some embodiments of the present disclosure, the determination module 820 includes:

[0098] a mapping unit configured to map the to-be-deleted point cloud data from the plurality of original single-frame point cloud original single-frame textures to the plurality of original single-frame textures, and determine the to-be-deleted texture data in the plurality of original single-frame textures;

[0099] The first removing unit is configured to remove the texture data to be deleted from the multiple original single-frame textures to obtain the multiple target single-frame textures.

[0100] In some embodiments of the present disclosure, the mapping unit is specifically configured to:

[0101] Determining a first mapping relationship between the original single-frame point cloud and the original single-frame texture according to a scanning timing of the target object;

[0102] Based on the first mapping relationship, the point cloud data to be deleted is mapped from the multiple original single-frame point clouds to the multiple original single-frame textures to determine the texture data to be deleted.

[0103] In some embodiments of the present disclosure, the rendering module 830 includes:

[0104] A first acquisition unit is configured to acquire a first depth map of the target single-frame point cloud at a corresponding imaging perspective;

[0105] The first determining unit is configured to determine a second mapping relationship between the target single-frame texture and the first depth map according to a first mapping relationship between the original single-frame point cloud and the original single-frame texture.

[0106] A second acquiring unit is configured to acquire a second depth map of the initial three-dimensional model at a corresponding imaging perspective;

[0107] A rendering unit is configured to render the target single-frame texture onto the initial three-dimensional model according to the first depth map and the second depth map under the same imaging perspective to obtain a target three-dimensional model of the target object.

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

[0109] Acquire target depth information equal to that of the first depth map from the second depth map;

[0110] The target single-frame texture is rendered to a target grid area corresponding to the target depth information to obtain the target three-dimensional model.

[0111] In some embodiments of the present disclosure, the acquisition module 810 includes:

[0112] an acquisition unit, configured to acquire a plurality of original single-frame point clouds of the target object and determine a to-be-deleted area of ​​the target object;

[0113] A second determining unit is configured to remove the to-be-deleted point cloud data from the original single-frame point cloud based on the to-be-deleted area to obtain the target single-frame point cloud;

[0114] The grid fusion unit is configured to perform grid fusion on the target single-frame point cloud to obtain the initial three-dimensional model.

[0115] In some embodiments of the present disclosure, the acquisition module 810 further includes:

[0116] A first sampling unit is configured to perform sampling processing on the original single-frame point cloud according to a first sampling method to obtain first sampling data in the original single-frame point cloud;

[0117] The second fusion unit is configured to perform grid fusion on the first sampling data to obtain a real-time reconstruction model, and display the real-time reconstruction model.

[0118] In some embodiments of the present disclosure, the grid fusion unit is specifically configured to:

[0119] Sampling the target single-frame point cloud according to a second sampling method to obtain second sampling data in the target single-frame point cloud;

[0120] Grid fusion is performed on the second sampling data to obtain the initial three-dimensional model.

[0121] It should be noted that the three-dimensional model acquisition device 800 shown in Figure 8 can execute the various steps in the method embodiments shown in Figures 4 to 7, and realize the various processes and effects in the method embodiments shown in Figures 4 to 7, which will not be repeated here.

[0122] FIG9 shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

[0123] As shown in FIG9 , the electronic device may include a processor 901 and a memory 902 storing computer program instructions.

[0124] Specifically, the processor 901 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 application.

[0125] Memory 902 may include a large-capacity memory for storing information or instructions. By way of example, and not limitation, memory 902 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 902 may include removable or non-removable (or fixed) media. Where appropriate, memory 902 may be internal or external to the integrated gateway device. In certain embodiments, memory 902 is non-volatile solid-state memory. In certain embodiments, memory 902 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.

[0126] The processor 901 reads and executes the computer program instructions stored in the memory 902 to perform the steps of the method for obtaining a three-dimensional model provided in the embodiment of the present disclosure.

[0127] In one example, the electronic device may further include a transceiver 903 and a bus 904. As shown in FIG9 , the processor 901, the memory 902, and the transceiver 903 are connected via the bus 904 and communicate with each other.

[0128] Bus 904 includes hardware, software or both.For example, but not limitation, bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industrial Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (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 two or more of these combinations. Where appropriate, bus 904 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0129] 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 acquisition 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 three-dimensional model acquisition method mentioned above.

[0130] This embodiment provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions implement a method for obtaining a three-dimensional model. The method includes:

[0131] Acquire an initial three-dimensional model of a target object and multiple original single-frame textures, wherein the initial three-dimensional model is generated based on multiple target single-frame point clouds, and the target single-frame point clouds are determined by removing point cloud data to be deleted from the original single-frame point clouds;

[0132] Removing texture data corresponding to the to-be-deleted point cloud data from the multiple original single-frame textures to obtain multiple target single-frame textures;

[0133] The multiple target single-frame textures are rendered onto the initial three-dimensional model to obtain a target three-dimensional model of the target object.

[0134] Of course, the storage medium containing computer-executable instructions provided in the embodiment of the present disclosure is not limited to the above method operations, and can also execute related operations in the three-dimensional model acquisition method provided in any embodiment of the present disclosure.

[0135] 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 acquisition method provided in each embodiment of the present disclosure.

[0136] 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

[0137] In the three-dimensional model acquisition method provided in the present invention, based on the data to be deleted removed from the original single-frame point cloud, the corresponding texture is removed from the texture data, and the texture data after removing the corresponding texture is rendered onto the initial three-dimensional model, thereby rendering a rendering result that meets the user's expectations, making it convenient for the user to accurately analyze the rendering results to obtain accurate dental restoration suggestions and other information, and has strong industrial practicality.

Claims

1. A method for obtaining a three-dimensional model, wherein: include: Acquire an initial three-dimensional model and a plurality of original single-frame textures of a target object, wherein the initial three-dimensional model is generated based on a plurality of target single-frame point clouds, and the target single-frame point clouds are determined by removing point cloud data to be deleted from the original single-frame point clouds; Removing texture data corresponding to the to-be-deleted point cloud data from the multiple original single-frame textures to obtain multiple target single-frame textures; The multiple target single-frame textures are rendered onto the initial three-dimensional model to obtain a target three-dimensional model of the target object.

2. The method according to claim 1, wherein: The removing the texture data corresponding to the to-be-deleted point cloud data from the multiple original single-frame textures to obtain multiple target single-frame textures includes: Mapping the to-be-deleted point cloud data from the multiple original single-frame point clouds to the multiple original single-frame textures, and determining the to-be-deleted texture data in the multiple original single-frame textures; The texture data to be deleted is removed from the multiple original single-frame textures to obtain the multiple target single-frame textures.

3. The method according to claim 2, wherein: The step of mapping the point cloud data to be deleted from the multiple original single-frame point clouds to the multiple original single-frame textures and determining the texture data to be deleted in the multiple original single-frame textures includes: Determining a first mapping relationship between the original single-frame point cloud and the original single-frame texture according to a scanning timing of the target object; Based on the first mapping relationship, the point cloud data to be deleted is mapped from the multiple original single-frame point clouds to the multiple original single-frame textures to determine the texture data to be deleted.

4. The method according to claim 1, wherein: The step of rendering the plurality of target single-frame textures onto the initial three-dimensional model to obtain a target three-dimensional model of the target object comprises: Acquire a first depth map of the target single-frame point cloud at a corresponding imaging perspective; Determining a second mapping relationship between the target single-frame texture and the first depth map according to a first mapping relationship between the original single-frame point cloud and the original single-frame texture; Acquire a second depth map of the initial three-dimensional model at a corresponding imaging perspective; The target single-frame texture is rendered onto the initial three-dimensional model according to the first depth map and the second depth map under the same imaging perspective to obtain a target three-dimensional model of the target object.

5. The method according to claim 4, wherein: The step of rendering the target single-frame texture onto the initial three-dimensional model according to the first depth map and the second depth map under the same imaging perspective to obtain a target three-dimensional model of the target object includes: Acquire target depth information equal to that of the first depth map from the second depth map; The target single-frame texture is rendered to a target grid area corresponding to the target depth information to obtain the target three-dimensional model.

6. The method according to claim 1, wherein: The step of obtaining an initial three-dimensional model of the target object includes: Acquire multiple original single-frame point clouds of the target object, and determine the area to be deleted of the target object; Based on the area to be deleted, removing the point cloud data to be deleted from the original single-frame point cloud to obtain the target single-frame point cloud; The target single-frame point cloud is mesh-fused to obtain the initial three-dimensional model.

7. The method according to claim 6, wherein: After acquiring a plurality of original single-frame point clouds of the target object, the method further includes: According to a first sampling method, sampling processing is performed on the original single-frame point cloud to obtain first sampling data in the original single-frame point cloud; The first sampling data is mesh-fused to obtain a real-time reconstruction model, and the real-time reconstruction model is displayed.

8. The method according to claim 6, wherein: The step of performing grid fusion on the target single-frame point cloud to obtain the initial three-dimensional model includes: According to a second sampling method, sampling the target single-frame point cloud is performed to obtain second sampling data in the target single-frame point cloud; The second sampling data is subjected to grid fusion to obtain the initial three-dimensional model.

9. A device for acquiring a three-dimensional model, wherein: include: An acquisition module is configured to acquire an initial three-dimensional model and a plurality of original single-frame textures of a target object, wherein the initial three-dimensional model is generated based on a plurality of target single-frame point clouds, and the target single-frame point clouds are determined by removing point cloud data to be deleted from the original single-frame point clouds; A determination module is configured to remove the texture data corresponding to the to-be-deleted point cloud data from the multiple original single-frame textures to obtain multiple target single-frame textures; The rendering module is configured to render the multiple target single-frame textures onto the target single-frame point cloud of the initial three-dimensional model to obtain a target three-dimensional model of the target object.

10. An electronic device, wherein: include: A processor, a memory, and executable instructions stored in the memory; The processor reads the executable instructions from the memory, and implements the method described in any one of claims 1 to 8 when executing the executable instructions.

11. A computer-readable storage medium having a computer program stored thereon, 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 8.

Images