3D model placement angle adjustment method and system, computer equipment and storage medium
By determining the pre-tuned posture of the 3D model and the image recognition network adjustment, the problem of low efficiency of 3D model placement angle adjustment is solved, automatic and standardized placement angle adjustment is realized, and the efficiency and quality of 3D printing is improved.
Patent Information
- Application Number
- CN202411375286.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-29
AI Technical Summary
In the prior art, the 3D model placement angle adjustment efficiency is low, the manual adjustment accuracy is low, and the individualization difference is large, resulting in poor 3D printing efficiency and quality.
By determining the rotational attitude of the bounding box that occupies the smallest height in three-dimensional space as the pre-adjustment attitude, and using the image recognition network to adjust the model to the unified attitude, adjust the model attitude according to the desired angle, and realize automated and standardized placement angle adjustment.
The efficiency and accuracy of 3D model placement angle adjustment is improved, automated and standardized placement angle adjustment is realized, and the efficiency and quality of 3D printing is improved.
Smart Images

Figure CN118991041A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of 3D printing technology, and specifically to a 3D model placement angle adjustment method, a 3D model placement angle adjustment system, a computer device, a computer-readable storage medium, and a computer program product. Background Art
[0002] 3D printing is a rapid prototyping technology. According to the data to be printed, the 3D printing equipment uses powdered metal, plastic, or resin and other curable materials to construct the 3D model by printing layer by layer. For some 3D models (such as RPD (Removable Partial Dentures) related models), the 3D model needs to be adjusted to a suitable placement angle before 3D printing for subsequent placement.
[0003] In the prior art, an operator generally manually adjusts the placement angle of each 3D model so as to subsequently add support to the 3D model or make further placement before printing. This operation is very inefficient, and the manual adjustment has low accuracy and large individual differences.
[0004] In view of this, how to automatically adjust the placement angle of the 3D model to improve the efficiency of 3D printing is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention
[0005] In view of the shortcomings of the above-mentioned related technologies, the purpose of the present application is to provide a 3D model placement angle adjustment method, a 3D model placement angle adjustment system, a computer device, a computer-readable storage medium and a computer program product, so as to overcome the technical problem of low efficiency of manually adjusting the 3D model placement angle in the above-mentioned related technologies.
[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect disclosed in the present application discloses a method for adjusting the placement angle of a 3D model, comprising the following steps: determining a bounding box of a minimum height occupied by at least one 3D model in a three-dimensional space, so as to determine the rotational posture of the 3D model corresponding to the bounding box occupying the minimum height as the pre-adjusted posture of the 3D model; inputting the projection view of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the orientation information of the pre-adjusted posture of each 3D model identified; and selecting the corresponding 3D model for unified posture adjustment according to the expected angle included in the acquired expected adjustment information.
[0007] The second aspect of the present application discloses a 3D model placement angle adjustment system, comprising: a pre-adjustment module, used to determine the bounding box of at least one 3D model with a minimum height in three-dimensional space, so as to determine the rotational posture of the 3D model corresponding to the bounding box occupying the minimum height as the pre-adjusted posture of the 3D model; a unified posture adjustment module, used to input the projection view of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the orientation information of the pre-adjusted posture of each 3D model identified; an angle adjustment module, used to select the corresponding 3D model for unified posture adjustment according to the expected angle included in the acquired expected adjustment information.
[0008] The third aspect of the present application discloses a computer device, including: a storage device for storing at least one program, and a processing device connected to the storage device, for calling the at least one program from the storage device and implementing the 3D model placement angle adjustment method as described in any embodiment of the first aspect of the present application when executing it.
[0009] In a fourth aspect, the present application discloses a computer-readable storage medium storing at least one program, which, when called and executed by a processor of a computer, implements the 3D model placement angle adjustment method as described in any embodiment of the first aspect of the present application.
[0010] The fifth aspect of the present application discloses a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the 3D model placement angle adjustment method as described in any embodiment of the first aspect of the present application.
[0011] In summary, the 3D model placement angle adjustment method, 3D model placement angle adjustment system, computer equipment, computer-readable storage medium and computer program product disclosed in the present application can first be adjusted to a unified posture according to the orientation information of the pre-adjusted posture of the 3D model, and under the unified posture, the corresponding 3D model can be selected for posture adjustment according to the expected angle included in the expected adjustment information, thereby realizing the adjustment of the 3D model placement angle automatically and in a standardized manner.
[0012] Those skilled in the art can easily perceive other aspects and advantages of the present application from the detailed description below. In the detailed description below, only exemplary embodiments of the present application are shown and described. As will be appreciated by those skilled in the art, the content of the present application enables those skilled in the art to modify the disclosed specific embodiments without departing from the spirit and scope of the invention to which the present application relates. Accordingly, the description in the drawings and specification of the present application is merely exemplary and not restrictive. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] The specific features of the invention involved in this application are shown in the attached claims. The features and advantages of the invention involved in this application can be better understood by referring to the exemplary embodiments and drawings described in detail below. The drawings are briefly described as follows:
[0014] Figure 1 Shown is a schematic diagram of a three-dimensional space in one embodiment of the present application.
[0015] Figure 2 Shown is a schematic diagram of various types of RPD models in one embodiment of the present application.
[0016] Figure 3 Shown is a schematic diagram of a 3D model in a prone position in one embodiment of the present application.
[0017] Figure 4 Shown is a schematic flow chart of a method for adjusting the 3D model placement angle in one embodiment of the present application.
[0018] Figure 5 It is a flowchart of step S110 in one embodiment of the present application.
[0019] Figure 6 It is a schematic diagram showing how to determine the height occupied by a bounding box in a three-dimensional space in one embodiment of the present application.
[0020] Figure 7 It is a process schematic diagram of step S110 in another embodiment of the present application.
[0021] Figure 8 Shown is a schematic diagram of each 3D model in a pre-adjusted posture in one embodiment of the present application.
[0022] Fig. 9 Shown is a schematic diagram of the process of training an image recognition network in one embodiment of the present application.
[0023] Fig.10 It is a flowchart of step S120 in one embodiment of the present application.
[0024] Fig.11 In one embodiment, the present application will Figure 8 The third 3D model shown is a schematic diagram of the process of adjusting to a prone posture.
[0025] Fig.12 In another embodiment, the present application will Figure 8 The third 3D model shown is a schematic diagram of the process of adjusting to a prone posture.
[0026] Fig.13 Shown is a schematic diagram of each 3D model adjusted to a unified posture in one embodiment of the present application.
[0027] Fig.14 Shown is a schematic diagram of an adjustment information input interface in one embodiment of the present application.
[0028] Fig.15 It is a flowchart of step S130 in one embodiment of the present application.
[0029] Fig.16 Shown is a schematic diagram of a 3D model of the maxillary-anteroposterior palatal rod type after uniform posture adjustment in one embodiment of the present application.
[0030] Fig.17 Shown is a module block diagram of a 3D model placement angle adjustment system in one embodiment of the present application.
[0031] Fig.18 Shown is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION
[0032] The following is a description of the embodiments of the present application by specific specific embodiments, and those familiar with the technology can easily understand the advantages of the present application and the technical effects that can be achieved by the content disclosed in this specification. In the following description, some embodiments can refer to the drawings pointed to. It should be understood that other embodiments without drawings can also be used, and specific steps, modules or units, electrical and operational changes can be made without departing from the spirit and scope of the present application. The detailed description below should not be considered restrictive, and the scope of the embodiments of the present application is limited only by the claims published by the present application. The terms used herein are only for describing specific embodiments and are not intended to limit the present application.
[0033] Although in some instances the terms first, second or third etc. are used to describe various elements or parameters in this article, these elements or parameters should not be limited by these terms. These terms are only used to distinguish one object or parameter from another object or parameter, and are not used to define the order, timing, priority or importance of multiple objects. For example, a first 3D model can be referred to as a second 3D model, and similarly, a second 3D model can be referred to as a first 3D model, without departing from the scope of the various described embodiments.
[0034] Furthermore, as used in this article, the singular forms "one", "an" and "the" are intended to also include plural forms, unless there is an indication to the contrary in the context. It should be further understood that the terms "comprising", "including" indicate the presence of the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the presence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. For example, the process, method, system, product or equipment comprising a series of steps or units need not be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment. In addition, the term "and / or" that may be used hereinafter, describes the association relationship of associated objects, indicating that three kinds of relationships may exist, for example, A and / or B, which can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / ", if not otherwise specified, generally represents that the associated objects before and after are a kind of "and / or" relationship. In addition, in the description of the embodiments of the present application, "multiple" refers to two or more than two.
[0035] Some nouns or terms used in each embodiment of the present application are explained below, and the nouns or terms are also used as a part of the content of the invention. It will be appreciated by those skilled in the art that, unless otherwise defined, all terms including technical terms and scientific terms used herein have the same meaning as the general understanding of the technicians in the field to which the present application belongs. It should also be understood that those terms such as those defined in general dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and unless specifically defined as herein, will not be interpreted with an idealized or overly formal meaning.
[0036] The three-dimensional space described in the embodiments of the present application is the space where the build volume is located. The build volume corresponds to the printing platform of the 3D printing device. The 3D model placed in the build volume can be manufactured in the printing platform. Among them, the three-dimensional space has a coordinate system. In the embodiments, a corner of the build volume can be used as the origin of the coordinate to form the coordinate system of the three-dimensional space. Please refer to Figure 1, which is a schematic diagram of a three-dimensional space in one embodiment of the present application. A build volume V is formed in the three-dimensional space R. In the figure, the lower left corner of the build volume V is used as the coordinate origin O, thereby forming a coordinate system XYZ in the three-dimensional space. The surface of the build volume V on the XOY plane corresponds to the printing surface of the printing platform. In the embodiment of the present application, the XOY plane is also referred to as the reference plane. In addition, in order to facilitate the description of the viewing direction of the projection view, six directions of up, down, front, back, left and right are defined in the three-dimensional space R. The view observed from the front as the viewing angle and facing the back is the front view, the view observed from the back as the viewing angle and facing the front is the back view, the view observed from the left as the viewing angle and facing the right is the left view, the view observed from the right as the viewing angle and facing the left is the right view, the view observed from the top as the viewing angle and facing the bottom is the top view, and the view observed from the back as the viewing angle and facing the front is the bottom view.
[0037] The 3D model described in the embodiments of the present application can use three-dimensional coordinate data to describe its position and shape in three-dimensional space. The three-dimensional coordinate data includes, for example, a starting position of the 3D model, and each offset position determined according to the relative position relationship between each position in the 3D model space and the starting position, or a positioning position determined according to each offset position and the starting position surface. Among them, the starting position, offset position and positioning position can all be exemplified as three-dimensional coordinate values described by means of a three-dimensional space coordinate system, etc. The 3D model can be pre-stored in a model library, and the 3D model can be imported into the three-dimensional space from the model library. In the embodiments of the present application, the posture of the 3D model when it is imported into the three-dimensional space is called the initial posture or default posture.
[0038] In some embodiments of the present application, the 3D model is configured as a model with an arched structure. In some examples, the 3D model includes a main body, or may further include an auxiliary part connected to the main body, and the auxiliary part is configured as an auxiliary part required for printing a 3D object, such as a base. In this example, the arched structure is located in the main body of the 3D model. The arched structure may also be referred to as a protruding structure or a convex structure. Depending on the viewing angle, the arched structure may also be regarded as a concave structure. Further, the 3D model may also include multiple arched structures.
[0039] In some embodiments, the 3D model can be configured as a dental model, and the dental model includes tooth guides, temporary crowns, dental bases, removable dentures, space maintainers, bridges, orthodontic accessories, orthodontic retainers, RPD (including component structures or all structures in RPD) and other related models. In the embodiment where the 3D model is configured as an RPD model, the RPD model is configured to include any one or more of the following types: maxillary-anterior palatal bar, maxillary-anteroposterior palatal bar, maxillary-mid palatal bar, maxillary-full mesh, small bracket, maxillary-full palatal plate, maxillary-dental full palatal plate, maxillary-half plate, mandibular-full mesh, mandibular-lingual bar, mandibular-dental lingual plate, and mandibular-other. Please refer to Figure 2 , which is a schematic diagram of various types of RPD models in one embodiment of the present application, as shown in the figure, Figure 2 (a) RPD model presented as maxillary-anterior palatal bar type, Figure 2 (b) RPD model presented as maxillary-anteroposterior palatal bar type, Figure 2 (c) RPD model presented as maxillary-mid-palatal bar type, Figure 2 (d) RPD model presented as maxillary-full network type, Figure 2 (e) RPD model presented as a small bracket type, Figure 2 (f) An RPD model of the maxillary-full palate plate type is presented, which has a sharp portion at the front end. Figure 2 (g) An RPD model of the maxillary-tooth full palate plate type is presented. This type of RPD model also has a sharp portion at the front end. Figure 2 (h) RPD model presented as maxillary-half plate type, Figure 2 (i) The RPD model presented as a mandibular-full-network type, Figure 2 (j) RPD model presented as mandibular-lingual bar type, Figure 2 (k) RPD model presented as mandibular-lingual plate type, Figure 2 (l) presents the RPD model of mandible-other types. It should be noted that Figure 2 The various types shown are for illustrative purposes only, and other classification methods may be used to classify the RPD model. The 3D model used in the embodiments of the present application may also be a model of other types, such as the various types exemplified in the above-mentioned dental model, and the present application does not impose any restrictions on this.
[0040] The prone posture of the 3D model described in some embodiments of the present application refers to a state in which the 3D model lies on the placement surface, with the plane where the reference plane is located or parallel to it (i.e., the XOY plane or a plane parallel to XOY) as the placement surface. Taking a 3D model configured as a model with an arched structure as an example, the state in which the 3D model lies on the placement surface refers to a state in which the arched structure of the 3D model lies flat on the placement surface in a manner away from the placement surface. In an example in which the 3D model has multiple arched structures, the arched structure with the largest degree of arching or the arched structure that most visually affects the form presented by the 3D model can be in a state in which the arched structure lies flat on the placement surface in a manner away from the placement surface. Of course, it can also be a state in which the largest number of arched structures lie flat on the placement surface in a manner away from the placement surface. Please refer to Figure 3 , which is a schematic diagram showing a 3D model in a prone position in one embodiment of the present application. As shown in the figure, the 3D model 30 has an arched structure 300, and the arched structure 300 forms a recess 301 corresponding to the arched structure 300. The arched structure 300 is facing away from the XOY plane, and the 3D model 30 is lying flat on the XOY plane. This posture of the 3D model is regarded as a prone posture.
[0041] In view of the fact that the existing technology described in the background technology is very inefficient in that the operator manually adjusts the placement angle of each 3D model, and the manual adjustment has low accuracy and large individual differences, the present application discloses a 3D model placement angle adjustment method, a 3D model placement angle adjustment system, a computer device, a computer-readable storage medium and a computer program product. According to the orientation information of the pre-adjusted posture of the 3D model, it can first be adjusted to a unified posture, and under the unified posture, the corresponding 3D model can be selected for posture adjustment according to the expected angle included in the expected adjustment information, thereby realizing the automatic and standardized adjustment of the 3D model placement angle.
[0042] The present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. The technical solutions in the embodiments of the present application are clearly and completely described. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments and technical effects obtained by ordinary technicians in this field without making creative work should belong to the scope of protection of this application. "An implementation method", "implementation method" or similar words mentioned in the whole text of this specification mean that the specific features, structures or characteristics described together with the implementation method are included in at least one implementation method of the present application. Therefore, in the whole text of this specification, the appearance of the phrases "in one implementation method", "in an implementation method" and similar words may (but not necessarily) relate to the same implementation method.
[0043] In some embodiments, the present application provides a 3D model placement angle adjustment method, which can be executed by a computer device configured with a 3D model placement angle adjustment system. The 3D model placement angle adjustment system is a software tool or software module that can process data, and it executes the 3D model placement angle adjustment method with the help of the operating environment provided by the hardware device and / or operating system in the computer device.
[0044] In one embodiment, the computer device can be configured as an electronic device, that is, the 3D model placement angle adjustment method is executed by the electronic device. For example, the electronic device includes desktop computers, laptops, tablet computers, smart TVs, smart phones, tablets, industrial computers and other devices. The electronic device can also be an electronic device composed of a host with multiple virtual machines and a human-computer interaction device corresponding to each virtual machine (such as a touch screen, keyboard and mouse).
[0045] In one embodiment, the computer device may be configured as a server, that is, the support generation method of the 3D model is executed by the server. The server may be arranged on one or more physical servers according to various factors such as function and load. In some examples, the server may be a server based on a cloud architecture, and the server refers to a cloud computing platform provided by a cloud computing provider, and the cloud computing platform can provide services such as IaaS (Infrastructure-as-a-Service), PaaS (Platform-as-a-Service), and SaaS (Software-as-a-Service). Among them, the cloud computing platform includes a public cloud (Public Cloud), a private cloud (Private Cloud), and a hybrid cloud (Hybrid Cloud). In some examples, the server may be composed of a distributed or centralized server cluster. For example, the server cluster is composed of at least one physical server. Multiple virtual servers are configured in each physical server, each virtual server runs at least one functional module in the system, and each virtual server communicates through a network.
[0046] See also Figure 4 , which is a flow chart of a 3D model placement angle adjustment method in one embodiment of the present application. As shown in the figure, the 3D model placement angle adjustment method includes step S110, step S120 and step S130. The following takes the 3D model placement angle adjustment method executed by a computer device as an example to illustrate various embodiments.
[0047] In step S110, the computer device determines a bounding box of a minimum height occupied by at least one 3D model in three-dimensional space, so as to determine the rotation posture of the 3D model corresponding to the bounding box occupying the minimum height as the preset posture of the 3D model. In this embodiment, the 3D model may be one or more (for example, two, three, four, or more). In an example with one 3D model, step S110 only needs to determine the preset posture of this one 3D model. In an example with multiple 3D models, step S110 will determine the preset posture of each 3D model respectively. The preset posture of each 3D model is determined based on the same method. The relevant embodiments of step S110 will be described later by taking one 3D model as an example.
[0048] See also Figure 5 , which is a flowchart of step S110 in one embodiment of the present application. As shown in the figure, step S110 further includes step S1101 and step S1102.
[0049] In step S1101, the computer device rotates at least one 3D model based on a preset rotation method to obtain the heights occupied by the bounding boxes of each 3D model in multiple rotation postures in the three-dimensional space. The object targeted by step S1101 is a 3D model as an example for explanation of the embodiment. In the example of multiple 3D models, the process of step S1101 for each 3D model is the same, and will not be repeated later.
[0050] The rotation posture refers to the posture corresponding to each rotation of the 3D model in a preset rotation mode. For example, the preset rotation mode may be a rotation mode pre-stored on a computer device, or may be a rotation mode selected or input by a user. In one embodiment, the preset rotation mode is to traverse all rotation directions and angles. In another embodiment, the preset rotation mode is configured as any one or more of the following: rotating once at each fixed angle based on the X-axis in the three-dimensional space, rotating once at each fixed angle based on the Y-axis in the three-dimensional space, and rotating once at each fixed angle based on the Z-axis in the three-dimensional space. Among them, taking the X-axis as the reference means taking the X-axis or an axis parallel to the X-axis as the rotation axis, taking the Y-axis as the reference means taking the Y-axis or an axis parallel to the Y-axis as the rotation axis, and taking the Z-axis as the reference means taking the Z-axis or an axis parallel to the Z-axis as the rotation axis. The fixed angles are, for example, 15°, 30°, 45°, and 90°. Correspondingly, the X, Y, and Z axes are rotated 24 times, 12 times, 6 times, 4 times, and 2 times, respectively. That is, the X, Y, and Z axes have 24, 12, 6, 4, and 2 rotation postures, respectively. It should be understood that the fixed angles set for each axis are not limited to being the same or different. The fixed angles set for each axis can be the same, completely different, or partially different. Preferably, the preset rotation mode is configured to rotate once every 90° based on the X axis in the three-dimensional space, once every 90° based on the Y axis in the three-dimensional space, and once every 90° based on the Z axis in the three-dimensional space. That is, the 3D model needs to rotate 4 times based on the X axis, 4 times based on the Y axis, and rotate based on the Z axis, with a total of 12 rotation postures.
[0051] Rotating the 3D model based on a preset rotation method can obtain multiple rotation postures of the 3D model, and the bounding box of the 3D model is determined in each rotation posture, so that the height occupied by the bounding box in the three-dimensional space can be further determined. The height occupied by the bounding box in the three-dimensional space refers to the height on the Z axis of the three-dimensional space occupied by the bounding box. The bounding box is the minimum bounding box that encloses the 3D model, which can be, for example, a bounding box in the form of AABB (Axis Aligned Bounding Box) or a bounding box in the form of OBB (Oriented Bounding Box).
[0052] See also Figure 6 , which is a schematic diagram showing the height occupied by a bounding box in a three-dimensional space in one embodiment of the present application, and the bounding box in the form of AABB under two rotation postures of the 3D model is used as an example for explanation, wherein Figure 6(a) is the rotation posture after the first 90° rotation based on the Y axis. The bounding box 301 of the 3D model in this rotation posture can be determined. Further, the height occupied by the bounding box 301 on the Z axis of the three-dimensional space can be determined as H1. Figure 6 (b) is the rotation posture after the second 90° rotation based on the Y axis. The bounding box 303 of the 3D model in this rotation posture can be determined, and the height occupied by the bounding box 303 on the Z axis of the three-dimensional space can be further determined as H2.
[0053] It should be understood that Figure 6 Only two rotation postures are used as an example to illustrate how to obtain the height of the bounding box. In the actual step S1101, the height occupied by the bounding box in each rotation posture in the three-dimensional space is determined. Taking the preset rotation method as rotating once every 90° based on the Y axis in the three-dimensional space and rotating once every 90° based on the Z axis in the three-dimensional space as an example, that is, the 3D model has 12 rotation postures, and step S1101 can respectively determine the heights occupied by the bounding boxes in the three-dimensional space under these 12 rotation postures.
[0054] Please continue reading Figure 5 In step S1102, the computer device selects the rotation posture corresponding to the minimum value of the height occupied by each 3D model as the preset posture, so as to adjust each 3D model to the preset posture.
[0055] According to step S1101, the heights occupied by the bounding boxes of each 3D model in multiple rotational postures in the three-dimensional space can be determined. Further, in step S1102, for each 3D model, the minimum value can be determined from the heights of the bounding boxes in multiple rotational postures, and the rotational posture of the 3D model corresponding to the bounding box of the minimum value is used as the pre-adjusted posture, so that the 3D model can be adjusted to the pre-adjusted posture. In other words, the height occupied by the bounding box of the 3D model in the pre-adjusted posture in the three-dimensional space is the minimum, thereby ensuring that the 3D model can be in the three-dimensional space with a lower posture.
[0056] In another embodiment, step S110 includes the step of determining the bounding box of the at least one 3D model based on a minimization bounding box algorithm, and the step of determining the rotational posture of the 3D model corresponding to the minimum height of the bounding box aligned with the height direction of the three-dimensional space as the pre-adjusted posture.
[0057] See also Figure 7 , which is a schematic diagram of the process of step S110 in another embodiment of the application. In this embodiment, Figure 7As shown in (a), the bounding box of the 3D model 30 determined based on the minimum bounding box algorithm is the bounding box 304 in the OBB form of the 3D model 30 determined by the minimum bounding box algorithm, and the minimum height H3 of the bounding box 304 is the shortest side among all sides of the bounding box 304. Further, the minimum height H3 of the bounding box 304 is expressed as follows in the height direction (i.e., the Z direction) of the three-dimensional space: Figure 7 As shown in (b) (the bounding box 304 at this time is the bounding box occupying the minimum height in the three-dimensional space), the corresponding rotation posture of the 3D model 30 can be determined as the pre-adjusted posture, so that the 3D model 30 can be adjusted to this state.
[0058] It should be noted that if Figure 5 and Figure 6 The implementation of step S110 shown in FIG. Figure 7 The implementation methods of step S110 shown are only two examples. The present application does not limit the method for determining the bounding box of the minimum height occupied by the 3D model in the three-dimensional space. Other determination methods are also within the protection scope of the present application.
[0059] See also Figure 8 , which is a schematic diagram of each 3D model in a pre-adjusted posture in one embodiment of the present application. The figure takes three 3D models as an example to illustrate the possible pre-adjusted postures. As shown in the figure, in the execution of step S110, the pre-adjusted postures presented by the first 3D model 31, the second model 32, and the third model 33 are not uniform.
[0060] Given that Figure 8 As shown, further, in step S120, the computer device executes inputting the projection view of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the orientation information of the pre-adjusted posture of each 3D model identified.
[0061] In one embodiment, the image recognition network can be obtained after training with training sample images, so that after the projection view is input into the image recognition network, the image recognition network can output the recognition information of the 3D model. In view of this, in one embodiment, the 3D model placement angle adjustment method also includes the step of training the image recognition network, which is completed before step S110, and the trained image recognition network can be directly used in step S120.
[0062] See also Fig. 9, which is a flow chart of training an image recognition network in one embodiment of the present application. As shown in the figure, the step of training the image recognition network further includes step S1001 and step S1002. In step S1001, the computer device executes the step of acquiring a training sample image. The training sample image includes an image of a 3D model in a uniform posture and multiple orientations and / or multiple offset angles.
[0063] In one embodiment, the training sample images may be images of the 3D model in various postures as samples obtained by software, for example, the training sample images are obtained through OpenGL. The training sample images include the images in the uniform posture described in step S120, and may also include images of the 3D model in multiple orientations, and may also include images at multiple offset angles based on the uniform posture. In one embodiment, the training sample images include an initial label as expected data for step S1002, and the initial label is used to represent the orientation information of the 3D model, for example, it may include any information in the orientation information and offset angle information of the 3D model. Furthermore, the initial label may also include category information for indicating the category to which the 3D model belongs.
[0064] In one embodiment, in the process of acquiring images of the 3D model in various postures, the posture of the 3D model can be adjusted by manual operation or software operation. For example, a forward-facing image of the 3D model in a uniform posture is acquired, and the posture of the 3D model is adjusted at a fixed angle (e.g., 10 degrees) while keeping the viewing angle unchanged, so that 35 images at different offset angles in the forward direction can be continuously acquired. While continuing to keep the viewing angle unchanged, the 3D model is flipped based on the uniform posture of the 3D model to acquire an image in the reverse direction, and then the posture of the 3D model is adjusted at a fixed angle (e.g., 10 degrees) to continue to acquire 35 images at different offset angles in the reverse direction. In the above manner, images of hundreds or more 3D models as samples can be acquired, so that a training sample model can be obtained.
[0065] The following is a specific example to illustrate the process of obtaining training sample images. For example, there are 12 types of 3D models as samples, and the number of each type of 3D models is, for example, 500. The following operations are performed for each 3D model: the 3D model is placed in a uniform posture and its projection view is obtained, the viewing angle is kept unchanged, the 3D model is rotated clockwise (or counterclockwise) by 10 degrees each time until it rotates one circle, and the projection view of the 3D model is obtained in each rotation posture; further, the 3D model is flipped 180 degrees in a uniform posture and its projection view is obtained, the viewing angle is kept unchanged, the 3D model is rotated clockwise (or counterclockwise) until it rotates one circle, and the projection view of the 3D model is obtained in each rotation posture. Similarly, this operation is performed on all 3D models, and 72 images can be obtained for each 3D model, and 72×500 training sample images can be obtained.
[0066] In step S1002, the computer device performs inputting the training sample images into a supervised recursive network for training to obtain an image recognition network. In one embodiment, the training sample images obtained in step S210 are input into a supervised recursive network for deep learning training to obtain an image recognition network, wherein inputting the training sample images into a supervised recursive network for training means that when training the recursive neural network, the training data of the initial labels included in the training sample images are used to supervise the learning process of the model. This means that the model will be trained based on the image and its corresponding initial label to learn how to predict or generate the correct label from the input image.
[0067] Thus, through step S1001 and step S1002, an image recognition network can be obtained, and the image recognition network can be used to identify the orientation information of the 3D model, or further identify the category of the 3D model. Step S120 uses the image recognition network to perform image recognition.
[0068] See also Fig.10 , which is a flow chart of step S120 in one embodiment of the present application, as shown in the figure, step S120 includes step S1201, step S1202 and step S1203. In step S1201, the computer device executes to obtain the projection view of each 3D model in the pre-adjusted posture.
[0069] The projection view can be configured as a top view, a bottom view, a left view, a right view, a front view, or a rear view, wherein the projection view is a view based on the perspective of three-dimensional space. Figure 1 The various views are defined in the description of the illustrated embodiment. In some examples, the projection views of various 3D models can be obtained through software or gadgets. For example, the top view of the 3D model can be obtained through OpenGL. In the subsequent embodiments, the projection view will be configured as a top view as an example for explanation. Under the guidance of this application, those skilled in the art can also select several other viewpoints, which will not be described in detail in this application.
[0070] In step S1202, the computer device inputs the projection view into the image recognition network to output recognition information of each 3D model, wherein the recognition information at least includes the orientation information of the pre-adjusted posture.
[0071] The orientation information includes orientation information and offset angle information. The orientation information and the offset angle information are orientations and offset angles based on a unified posture. In one embodiment, the orientation information includes a positive orientation and a negative orientation. The positive orientation is an orientation consistent with the unified posture, and the negative orientation is an orientation opposite to the unified posture. For example, the unified posture is a prone posture. The positive orientation is that the notch corresponding to the arched structure of the 3D model is facing downward (including the situation of facing downward directly and facing downward at a certain deflection angle), for example Figure 8 The orientations of the first 3D model 31 and the second 3D model 32 are both in the positive orientation, and the negative orientation is that the notch corresponding to the arched structure of the 3D model faces upward (including the situation of facing upward directly and facing upward at a certain deflection angle), for example Figure 8 The orientation of the third 3D model 33 is the reverse orientation. In one embodiment, the offset angle includes a deflection direction and an offset angle, wherein the deflection angle is a deflection angle with reference to the reference plane of the unified posture, and the deflection direction includes counterclockwise and clockwise. Taking the unified posture as the prone posture as an example, the offset angle is a deflection angle with reference to the plane where XOY is located or parallel to, and the offset angle is Figure 8 As shown as an example, the offset angle information of the first 3D model 31 includes a deflection angle of 0, the offset angle information of the second 3D model 32 includes a counterclockwise deflection and a deflection angle of β2, and the offset angle information of the third 3D model 33 includes a clockwise deflection and a deflection angle of β3.
[0072] In one embodiment, the image recognition network can output recognition information of each 3D model including the position information of the pre-adjusted posture according to the input projection view. The input projection image is the projection view of each 3D model in the pre-adjusted posture obtained in step S1201, so that the image recognition network can output the position information of each 3D model in the pre-adjusted posture. Figure 8 As shown in the top view of the first 3D model 31, the top view of the second 3D model 32, and the top view of the third 3D model 33, the image recognition network can output the orientation information of the first 3D model 31 as a positive direction and a deflection angle of 0, output the orientation information of the second 3D model 31 as a positive direction, counterclockwise deflection, and a deflection angle of β2, and output the orientation information of the third 3D model 33 as a reverse direction, clockwise deflection, and a deflection angle of β3.
[0073] In another embodiment, the image recognition network can also output identification information including category information for each 3D model according to the input projection view. The category information is used to indicate the category to which the 3D model belongs, which can be, for example, an application field category, such as dentistry, industry, orthopedics, etc., or a subdivided category under the same field, such as various examples of dental models given above, such as tooth guides, temporary crowns, removable dentures, etc., or a more subdivided category, such as any one or more of the 12 types of RPD models given above, and the present application does not limit the specific categories.
[0074] like Fig.10 As shown, in step S1203, the computer device adjusts each 3D model from the pre-adjusted posture to a unified posture according to the orientation information of the pre-adjusted posture.
[0075] In one embodiment, as described in the embodiment of step S1202, the orientation information of the pre-adjusted posture includes orientation information and offset angle information. For the orientation information and offset angle information, please refer to the description in the above embodiment, which will not be repeated here.
[0076] In one embodiment, step S1203 includes, when the 3D model is determined to be in a forward orientation according to the orientation information, reversely rotating the 3D model according to the offset angle information so that the 3D model is in a uniform posture. The uniform posture is a prone posture, and the 3D model is Figure 8 Taking the second 3D model 32 as an example, Figure 8 The second 3D model 32 in the image is in a pre-adjusted posture, and the orientation information of the second 3D model 32 is forward, counterclockwise, and the deflection angle is β2. Therefore, the second 3D model 32 can be determined to be in a forward orientation according to the orientation information, and then the second 3D model 32 can be rotated clockwise by an angle a1 to make the second 3D model in a prone posture.
[0077] In one embodiment, step S1203 includes determining a rotation angle that makes the 3D model present a uniform posture according to the offset angle information when the 3D model is determined to be in a reverse orientation according to the orientation information. Figure 8 Taking the third 3D model 33 as an example, Figure 8 The third 3D model 33 in the figure is in a pre-adjusted posture, and the orientation information of the third 3D model 33 is reverse orientation, clockwise deflection, and the deflection angle is β3. Fig.11 , which is shown as follows in one embodiment of the present application: Figure 8The schematic diagram of the process of adjusting the third 3D model to a prone posture is shown. First, the third 3D model 33 can be determined to be in the reverse orientation based on the orientation information. Then, based on the offset angle information (i.e., clockwise deflection, the deflection angle is β3), it can be determined that the rotation angle that makes the third 3D model 33 in the prone posture is 180°-β3 clockwise, so that the third 3D model 33 can be adjusted to the prone posture based on this angle.
[0078] In one embodiment, step S1203 includes flipping the 3D model to make it in a forward orientation when the 3D model is determined to be in a reverse orientation according to the orientation information, and rotating the 3D model to make it in a uniform posture according to the offset angle information. The uniform posture is a prone posture, and the 3D model is Figure 8 Taking the third 3D model 33 as an example, Figure 8 The third 3D model 33 in the figure is in a pre-adjusted posture, and the orientation information of the third 3D model 33 is reverse orientation, clockwise deflection, and the deflection angle is β3. Fig.12 , shown as the present application in another embodiment Figure 8 The schematic diagram of the process of adjusting the third 3D model to a prone posture is shown. First, the third 3D model 33 can be determined to be in the reverse orientation based on the orientation information. Then, the third 3D model 33 can be first flipped 180° based on the X-axis to adjust it to the forward orientation, and then rotated β3 clockwise according to the offset angle information, so that the third 3D model 33 can be adjusted to a prone posture.
[0079] In some embodiments, when adjusting the 3D model to a uniform posture in step S1203, the 3D model may also be adjusted to the plane where the reference plane is located (i.e., the plane where XOY is located). Adjusting the 3D model to the plane where the reference plane is located means that the bottom surface of its bounding box is located on the plane where the reference plane is located. It should be noted that this process is to place the 3D model on the same plane, and it is not necessarily performed when adjusting to a uniform posture. In other embodiments, it may also be performed in the subsequent step S130, or it may be performed in the 3D model placement after the placement angle is adjusted. This application does not limit this.
[0080] See also Fig.13 , which is a schematic diagram showing that each 3D model is adjusted to a uniform posture in one embodiment of the present application. In the figure, the uniform posture is taken as an example of a prone posture. After executing step S1203 for each 3D model, each 3D model is presented in a prone posture in the three-dimensional space R.
[0081] Furthermore, in step S130, the computer device selects a corresponding 3D model according to the expected angle included in the acquired expected adjustment information to adjust the uniform posture.
[0082] In one embodiment, the expected adjustment information includes an expected angle, or may further include an expected adjustment category. The expected angle refers to the angle expected to be adjusted with reference to the unified posture. In the example where the unified posture is a prone posture, the expected angle may be, for example, a lifting angle (or tilt angle) of the 3D model with reference to the XOY plane. The expected adjustment category refers to the category of the 3D model of the expected adjustment angle in the 3D model, and the expected adjustment category has a corresponding relationship with the expected angle.
[0083] In one embodiment, the expected adjustment information may be a parameter pre-set or pre-stored on a computer device, and the 3D model is automatically adjusted according to the expected adjustment information when executing step S130.
[0084] In one embodiment, the expected adjustment information may be customized, for example, the user may freely configure the expected adjustment information. In view of this, step S130 includes the step of obtaining the expected adjustment information according to an input interface submitted by a trigger operation. The trigger operation may be configured as an operation of a corresponding submission option operated by the user, under which the content in the input interface will be submitted synchronously. Furthermore, in this embodiment, an input interface may be further provided for the user to submit the expected adjustment information, see Fig.14 , which is a schematic diagram of an adjustment information input interface in an embodiment of the present application. The adjustment information input interface provides 12 types of RPD models listed in the aforementioned embodiment, and provides an input box after each type for the user to input the desired adjustment angle in the desired adjustment category. When the desired angle is not input, the desired angle of this type can be defaulted to 0°. The user submits the input interface by operating the "Apply" button in the adjustment information input interface, so that the computer device can obtain the desired adjustment information in the interface.
[0085] It should be noted here that Fig.14 The information provided by the input interface shown is only an example. In an example where the desired adjustment information only includes the desired angle, the category of the 3D model may not be configured in the input interface, but only the angle to be adjusted may be provided. This application does not limit the method for obtaining the desired adjustment information and the content included.
[0086] In the embodiment where the expected adjustment information includes the expected angle, step S130 directly adjusts the corresponding 3D models to a uniform posture according to the expected angle. For example, the corresponding 3D model may be the selected model or all 3D models in the three-dimensional space. When the expected angle is obtained, step S130 adjusts the corresponding 3D models from a uniform posture to the expected angle in batches. In the example where the uniform posture is a prone posture, step S130 may raise the corresponding 3D models from the prone posture to the expected angle in batches based on the XOY plane.
[0087] In an embodiment where the desired adjustment information includes a desired category and a corresponding desired angle, see Fig.15 , which is a flow chart of step S130 in one embodiment of the present application. As shown in the figure, step S130 includes step S1301 and step S1302. In step S1301, the computer device determines the expected adjustment category and the corresponding expected angle according to the acquired expected adjustment information. The expected adjustment information is configured as follows: Fig.14 The interface shown is obtained as an example. The computer device can obtain the desired adjustment information that the 3D model of the maxillary-anteroposterior palatal rod type is adjusted to the desired angle of 45°, and the other types of 3D models are not adjusted.
[0088] In step S1302, the computer device executes a step of selecting a 3D model corresponding to a desired adjustment category for unified posture adjustment according to category information of each 3D model identified by the image recognition network.
[0089] In an embodiment of step S120 as described above, the image recognition network can identify the category information of each 3D model according to the input projection view, that is, it can identify the category of each 3D model. Fig.13 Taking the 3D model shown in as an example, the image recognition network can recognize that 3D model 34a and 3D model 34b are maxillary-anterior palatal rod type models, 3D model 35a, 3D model 35b, 3D model 35c are maxillary-anteroposterior palatal rod types, 3D model 36a, 3D model 36b, 3D model 36c are maxillary-mid palatal rod types, and 3D model 37a, 3D model 376b, 3D model 37c are maxillary-full network types.
[0090] Further, step S1302 may adjust the 3D model of the desired adjustment category in the desired adjustment information from a uniform posture to a desired angle. Fig.14 The interface shown is an example of how to obtain the desired adjustment information, that is, the 3D model of the maxillary-anteroposterior palatal bar type is adjusted to the desired angle of 45°, and the other types of 3D models are not adjusted. Fig.16 , which is a schematic diagram showing a unified posture adjustment of the maxillary-anteroposterior palatal bar type 3D model in one embodiment of the present application. Step S1302 will raise the maxillary-anteroposterior palatal bar type 3D model 35a, 3D model 35b, and 3D model 35c from the prone posture based on the XOY plane by 45 degrees according to the desired adjustment category, and present it as Fig.16The morphology in the figure is changed, while the other types of 3D models, the 3D models 34a and 34b of the maxillary-anterior palatal bar type, the 3D models 36a, 36b, and 36c of the maxillary-mid-palatal bar type, and the 3D models 37a, 376b, and 37c of the maxillary-full mesh type remain as Fig.13 The posture presented in it remains unchanged.
[0091] In this way, through any of the embodiments of steps S110 to S130 above, the angle adjustment of the 3D model can be achieved in batches and in a standardized manner, and support can be added to the 3D model subsequently, and then it can be placed in the building volume for subsequent printing operations.
[0092] In some embodiments, the present application also provides a 3D model placement angle adjustment system, which can be deployed in a computer device, for example, as a software tool or software module that can process data, and executes a 3D model placement angle adjustment method with the help of the operating environment provided by the hardware device and / or operating system in the computer device.
[0093] In order to more prominently emphasize the independence of the operation of the functional units, many of the functional units described in this specification have been labeled as modules. For example, a module can be implemented as a hardware circuit, which includes a custom VLSI circuit, a gate array, or an off-the-shelf semiconductor (such as a logic chip, transistor, or other discrete component). A module can also be implemented in a programmable hardware device, such as a field programmable gate array, programmable array logic, a programmable logic device, or the like.
[0094] Among them, each module can also be implemented in software run by different types of processors. For example, a module of executable code can include one or more physical or logical blocks of computer instructions, which are organized as objects, programs or functions. However, the executable files of the modules do not have to be physically located together, but can include different commands stored in different locations, which, when logically connected together, include the modules and achieve the specified goals of the modules.
[0095] Of course, the module of executable code can be one or many instructions, and can even be distributed in several different code segments, distributed in different programs and distributed in multiple storage devices. Similarly, operation data can be identified and shown in the module, and the operation data can be embodied in any suitable form and organized in any suitable type of data structure. The operation data can be collected as a single data set, or can be distributed in different locations (including different storage devices), and can exist at least partially as electrical signals in a system or network. When a module or a portion of a module is implemented in software, the software portion is stored on one or more computer-readable media.
[0096] See also Fig.17 , which is a module block diagram of a 3D model placement angle adjustment system in one embodiment of the present application. As shown in the figure, the 3D model placement angle adjustment system 6 includes a pre-adjustment module 60, a unified posture adjustment module 61, and an angle adjustment module 62. Among them, the pre-adjustment module 60 is used to determine the height occupied by the bounding box of at least one 3D model in a plurality of rotational postures in a three-dimensional space, so as to determine the rotational posture corresponding to the minimum occupied height as the pre-adjusted posture of the 3D model. The unified posture adjustment module 61 is used to input the projection view of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the orientation information of the pre-adjusted posture of each 3D model identified. The angle adjustment module 62 is used to select the corresponding 3D model for unified posture adjustment according to the expected angle included in the acquired expected adjustment information.
[0097] In one embodiment, the pre-adjustment module 60, the unified posture adjustment module 61, and the angle adjustment module 62 respectively coordinate and execute the 3D model placement angle adjustment method disclosed in any of the aforementioned embodiments of the present application according to the functions described above. Figures 1 to 16 Any embodiments described in related manner will not be described in detail here.
[0098] The present application also provides a computer device. In an embodiment, the computer device is used to implement the 3D model placement angle adjustment method described in any of the above embodiments. In one embodiment, the computer device is a device capable of performing digital calculations, logical processing, and information processing on data, which can be a server, a laptop computer, a desktop computer, an edge device, etc. The embodiments of the present application do not make specific limitations, and the embodiments of the present application do not limit the number of processors and memories in the computing device.
[0099] See also Fig.18, which is a schematic diagram of the structure of a computer device in an embodiment of the present application, wherein the computer device 7 includes a storage device 70 and a processing device 71 connected to the storage device 70. Furthermore, the computer device also includes a communication interface 72.
[0100] In one embodiment, the storage device 70, the processing device 71, and the communication interface 72 communicate with each other via a bus. The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.18 The bus is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus may include a path for transmitting information between various components of the computing device (for example, storage devices, processing devices, communication interfaces).
[0101] In some embodiments, the storage device 70 is used to store at least one program, and the at least one program can be executed by the processing device 71 to coordinate the storage device 70 to implement the 3D model placement angle adjustment method described in any of the above embodiments. The memory may include a volatile memory (Volatile Memory), such as a random access memory (Random Access Memory, RAM). The memory may also include a non-volatile memory (Non-Volatile Memory), such as a read-only memory (Read-only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory, a programmable read-only memory (Programmable Read-Only Memory, PROM), an erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), an electrically erasable programmable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), a mechanical hard disk (Hard Disk Drive, HDD) or a solid state drive (Solid State Drive, SSD).
[0102] In some embodiments, the processing device 71 includes one or more processors. The processing device 71 can be operable to perform data read and write operations with the storage device 70. The processing device may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP) or a digital signal processor (DSP). For another example, it can also be an application-specific integrated circuit (ASIC), a discrete gate or transistor logic device, or a discrete hardware component, which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.
[0103] In some embodiments, the communication interface 72 includes at least one interface unit, each of which is used to output a visual interface, receive a human-computer interaction event generated according to the operation of a technician, etc. For example, the communication interface 72 includes but is not limited to: a serial interface such as an HDMI interface or a USB interface, or a parallel interface, etc. In one embodiment, the communication device 72 also includes a network communication unit, which is a device for data transmission using a wired or wireless network, examples of which include but are not limited to: an integrated circuit including a network card, a local area network module such as a WiFi module or a Bluetooth module, a wide area network module such as a mobile network, etc.
[0104] The present application also provides a computer-readable and writable storage medium storing at least one program, wherein the at least one program is executed and implements the 3D model placement angle adjustment method described in any of the above embodiments when called. Figures 1 to 16 Any embodiments described in related manner will not be described in detail here.
[0105] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device equipped with the storage medium to execute all or part of the steps of the methods described in the various embodiments of the present application.
[0106] Those of ordinary skill in the art can understand that all or part of the processes in the methods described in the above embodiments can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
[0107] In the embodiments provided in the present application, the computer readable and writable storage medium may include a read-only memory, a random access memory, an EEPROM, a CD-ROM or other optical disk storage device, a disk storage device or other magnetic storage device, a flash memory, a USB flash drive, a mobile hard disk, or any other medium that can be used to store a desired program code in the form of an instruction or data structure and can be accessed by a computer. In addition, any connection can be appropriately referred to as a computer-readable medium. For example, if the instruction is sent from a website, a server or other remote source using a coaxial cable, an optical fiber cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, optical fiber cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. However, it should be understood that computer readable and writable storage media and data storage media do not include connections, carriers, signals, or other temporary media, but are intended to be non-temporary, tangible storage media. Disk and disc, as used in this application, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.
[0108] The present application also provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement the 3D model placement angle adjustment method in any of the above-mentioned embodiments.
[0109] If the method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a computer device equipped with the storage medium to execute all or part of the steps of the method described in each embodiment of the present application.
[0110] In one or more exemplary aspects, the functions described in the computer program of the 3D model placement angle adjustment method described in the present application can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored or transmitted as one or more instructions or codes to a computer-readable medium. The steps of the method or algorithm disclosed in the present application can be embodied in a processor-executable software module, wherein the processor-executable software module can be located on a tangible, non-temporary computer-readable and writable storage medium. A tangible, non-temporary computer-readable and writable storage medium can be any available medium that a computer can access.
[0111] The flowchart and block diagram in the accompanying drawings described in the present application illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. Based on this, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be realized by a dedicated hardware-based system that performs a specified function or operation, or can be realized by a combination of dedicated hardware and computer instructions.
[0112] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0113] In summary, the 3D model placement angle adjustment method, 3D model placement angle adjustment system, computer device, computer readable storage medium and computer program product disclosed in the present application can first be adjusted to a unified posture according to the orientation information of the pre-adjusted posture of the 3D model, and the corresponding 3D model can be selected for posture adjustment according to the expected angle included in the expected adjustment information under the unified posture, so that the adjustment of the 3D model placement angle can be realized automatically and in a standardized manner. Furthermore, different adjustments can be made according to the category of the 3D model, taking into account both standardization and personalization.
[0114] The above embodiments are merely illustrative of the inventive essence of the present application and the beneficial effects obtained, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the principles and scope of the present application. Therefore, all equivalent modifications or changes achieved by a person with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.
Claims
1. A method for adjusting the placement angle of a 3D model, characterized in that: The following steps are involved: Determine a bounding box of at least one 3D model that occupies a minimum height in the three-dimensional space, and determine a rotation posture of the 3D model corresponding to the bounding box that occupies the minimum height as a pre-adjusted posture of the 3D model; Inputting the projection views of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the recognized position information of the pre-adjusted posture of each 3D model; According to the expected angle included in the acquired expected adjustment information, a corresponding 3D model is selected to adjust the uniform posture.
2. The 3D model placement angle adjustment method according to claim 1, characterized in that: The 3D model is configured as a model having an arched structure.
3. The 3D model placement angle adjustment method according to claim 1 or 2, characterized in that: The 3D model is configured as an RPD model.
4. The 3D model placement angle adjustment method according to claim 3, characterized in that: The RPD model is configured to include any one or more of the following types: maxillary-anterior palatal bar, maxillary-anteroposterior palatal bar, maxillary-mid palatal bar, maxillary-full mesh, small bracket, maxillary-full palatal plate, maxillary-dental full palatal plate, maxillary-half plate, mandibular-full mesh, mandibular-lingual bar, mandibular-dental lingual plate, and mandibular-other.
5. The 3D model placement angle adjustment method according to claim 1, characterized in that: The projection view is configured as a top view.
6. The 3D model placement angle adjustment method according to claim 1, characterized in that: The unified posture configuration is a prone posture.
7. The 3D model placement angle adjustment method according to claim 1, characterized in that: Determining a bounding box of at least one 3D model occupying a minimum height in a three-dimensional space, and determining the rotation posture of the 3D model corresponding to the bounding box occupying the minimum height as the preset posture of the 3D model includes the following steps: Rotate the at least one 3D model based on a preset rotation method to obtain the heights occupied by the bounding boxes of each 3D model in multiple rotation postures in the three-dimensional space; For each 3D model, a rotation posture corresponding to the minimum value of the height occupied therein is selected as the pre-adjusted posture, so as to adjust each 3D model to the pre-adjusted posture.
8. The 3D model placement angle adjustment method according to claim 7, characterized in that: The preset rotation mode is configured as any one or more of the following rotation modes: rotating once at each fixed angle based on the X-axis in the three-dimensional space, rotating once at each fixed angle based on the Y-axis in the three-dimensional space, and rotating once at each fixed angle based on the Z-axis in the three-dimensional space.
9. The 3D model placement angle adjustment method according to claim 1, characterized in that: Determining a bounding box of at least one 3D model occupying a minimum height in a three-dimensional space, and determining the rotation posture of the 3D model corresponding to the bounding box occupying the minimum height as the preset posture of the 3D model includes the following steps: Determining a bounding box of the at least one 3D model based on a minimization bounding box algorithm; The rotational posture of the 3D model corresponding to the minimum height of the bounding box being aligned with the height direction of the three-dimensional space is determined as the pre-adjusted posture.
10. The 3D model placement angle adjustment method according to claim 1, characterized in that: Inputting the projection views of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the recognized position information of the pre-adjusted posture of each 3D model includes the following steps: Acquire a projection view of each 3D model in the pre-adjusted posture; Inputting the projection view into the image recognition network to output identification information of each 3D model, wherein the identification information includes at least orientation information of the pre-adjusted posture; The 3D models are adjusted from the pre-adjusted posture to a unified posture according to the orientation information of the pre-adjusted posture.
11. The 3D model placement angle adjustment method according to claim 10, characterized in that: The orientation information of the pre-adjusted posture includes direction information and offset angle information. The step of adjusting each 3D model from the pre-adjusted posture to a unified posture according to the orientation information of the pre-adjusted posture includes: when the 3D model is determined to be in a forward orientation according to the orientation information, the 3D model is reversely rotated according to the offset angle information to make it present a unified posture.
12. The 3D model placement angle adjustment method according to claim 10, characterized in that: The orientation information of the pre-adjusted posture includes direction information and offset angle information. The step of adjusting each 3D model from the pre-adjusted posture to a unified posture according to the orientation information of the pre-adjusted posture includes: when the 3D model is determined to be in the reverse orientation according to the orientation information, a rotation angle that makes the 3D model present a unified posture is determined according to the offset angle information.
13. The 3D model placement angle adjustment method according to claim 10, characterized in that: The orientation information of the pre-adjusted posture includes direction information and offset angle information. The step of adjusting each 3D model from the pre-adjusted posture to a unified posture according to the orientation information of the pre-adjusted posture includes: flipping the 3D model to make it in a forward direction when it is determined according to the orientation information that the 3D model is in a reverse orientation, and rotating the 3D model in accordance with the offset angle information to make it in a unified posture.
14. The 3D model placement angle adjustment method according to claim 1, characterized in that: The steps of selecting a corresponding 3D model to adjust the uniform posture according to the expected angle included in the acquired expected adjustment information include: Determine the expected adjustment category and the corresponding expected angle according to the acquired expected adjustment information; According to the category information of each 3D model identified by the image recognition network, a 3D model corresponding to the desired adjustment category is selected to adjust the unified posture.
15. The 3D model placement angle adjustment method according to claim 1 or 14, characterized in that: The step of selecting a corresponding 3D model to adjust a uniform posture according to the expected angle included in the acquired expected adjustment information includes: the step of acquiring the expected adjustment information according to an input interface submitted by a trigger operation.
16. The 3D model placement angle adjustment method according to claim 15, characterized in that: The step of selecting the corresponding 3D model to adjust the uniform posture according to the expected angle included in the acquired expected adjustment information also includes: providing the input interface for the user to submit the expected adjustment information.
17. The 3D model placement angle adjustment method according to claim 1, characterized in that: Also included is the step of training the image recognition network.
18. The 3D model placement angle adjustment method according to claim 17, characterized in that: The step of training the image recognition network comprises: Acquire training sample images, where the training sample images include images of the 3D model in a unified posture and multiple orientations and / or multiple offset angles; The training sample images are input into a supervised recursive network for training to obtain the image recognition network.
19. A 3D model placement angle adjustment system, characterized in that: include: A pre-adjustment module, used to determine a bounding box of a minimum height occupied by at least one 3D model in a three-dimensional space, so as to determine a rotation posture of the 3D model corresponding to the bounding box occupying the minimum height as a pre-adjustment posture of the 3D model; A unified posture adjustment module, used for inputting the projection views of each 3D model in the pre-adjusted posture into an image recognition network to adjust each 3D model to a unified posture according to the recognized position information of the pre-adjusted posture of each 3D model; The angle adjustment module selects a corresponding 3D model to adjust the uniform posture according to the expected angle included in the acquired expected adjustment information.
20. A computer device, characterized in that: include: A storage device for storing at least one program; A processing device is connected to the storage device, and is used to call the at least one program from the storage device and implement the 3D model placement angle adjustment method as described in any one of claims 1 to 18 when executing it.
21. A computer-readable storage medium, characterized in that: At least one program is stored, and when the at least one program is called and executed by a processor of a computer, the 3D model placement angle adjustment method as described in any one of claims 1 to 18 is implemented.
22. A computer program product, characterized in that When the computer program product is run on a computer, the computer is enabled to execute the 3D model placement angle adjustment method as described in any one of claims 1 to 18.
Citation Information
Patent Citations
Target object attitude selection method, image scoring method and model training method
CN112907583A
Orthodontic model stacking and printing method and system
CN113442438A
Method, device and equipment for acquiring initial placement angle of additive manufacturing printing model
CN118643646A
Method and device for acquiring 3D information of object
US20200242331A1
Method and device for placing 3D model, storage medium and 3D printer
US20230226769A1
Cited By
Method and device for hole 3D printing and model construction method
CN119348141A
Three-dimensional model view generation method and device, storage medium and electronic equipment
CN119863600A
Method for determining placement posture of three-dimensional data model
CN120976914A
