Method, apparatus, electronic device and program product for optimizing a 3D oral model

Abstract

The present disclosure provides a method, device, electronic device and program product for optimizing a 3D oral model. The method comprises: determining one or more candidate 3D point sets in a 3D oral model based on the 3D oral model reconstructed by intraoral scanning, wherein each candidate 3D point set forms a 3D surface bridging between adjacent teeth. The method further comprises: identifying an error 3D point set in the one or more candidate 3D point sets based on two-dimensional (2D) images captured during the intraoral scanning, wherein the 3D surface formed by the error 3D point set is incorrectly connected to the adjacent teeth in the reconstructed 3D oral model. By utilizing the 2D images captured during the intraoral scanning, the present disclosure can effectively detect the incorrectly connected area in the 3D oral model, thereby achieving the optimization of the 3D oral model.

Description

Technical Field

[0001] Embodiments of this disclosure relate to three-dimensional reconstruction technology, and more specifically to methods, apparatus, electronic devices, and computer program products for optimizing three-dimensional (3D) oral models. Background Technology

[0002] Oral scanning refers to the process of digitally acquiring 3D models of the internal structures of the oral cavity (including teeth, gums, and surrounding tissues) using specialized optical technology. During an intraoral scan, professionals use a handheld device equipped with a camera and sensors (i.e., an intraoral scanner) to capture multiple images of the oral cavity from different angles. These images are transmitted to a computer workstation, where they are quickly stitched together using 3D reconstruction algorithms to generate a 3D model of the patient's teeth and soft tissues.

[0003] In a patient's natural teeth, adjacent teeth are typically arranged closely together with small gaps between them. In this situation, limited by the resolution and scanning accuracy of 3D reconstruction algorithms, the point cloud data corresponding to adjacent teeth in the gap region is prone to overlap or loss. This leads to the erroneous reconstruction of close sections between adjacent teeth as continuous structures during the reconstruction process, resulting in a connection phenomenon (also known as "adhesion") in the reconstructed 3D model in the interdental gap region. Addressing this adhesion in the interdental gap region and further optimizing the 3D oral model to improve its accuracy presents a challenge for relevant technical personnel. Summary of the Invention

[0004] According to a first aspect of this disclosure, a method for optimizing a three-dimensional (3D) oral cavity model is provided. The method includes: determining one or more candidate 3D point sets located in interdental regions of the 3D oral cavity model based on a 3D oral cavity model reconstructed via an intraoral scan, wherein each candidate 3D point set forms a 3D surface that spans between adjacent teeth; and identifying erroneous 3D point sets within the one or more candidate 3D point sets based on two-dimensional (2D) images acquired during the intraoral scan, wherein the 3D surfaces formed by the erroneous 3D point sets incorrectly connect adjacent teeth in the reconstructed 3D oral cavity model.

[0005] According to a second aspect of this disclosure, an apparatus for optimizing a 3D oral cavity model is provided, the apparatus comprising: a gap region determination unit configured to determine one or more candidate 3D point sets located in gap regions of the 3D oral cavity model based on a 3D oral cavity model reconstructed by an intraoral scan, wherein each candidate 3D point set forms a 3D surface that spans between adjacent teeth; and an error connection identification unit configured to identify erroneous 3D point sets in the one or more candidate 3D point sets based on two-dimensional (2D) images acquired during an intraoral scan, wherein the 3D surfaces formed by the erroneous 3D point sets erroneously connect adjacent teeth in the reconstructed 3D oral cavity model.

[0006] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes: a processing unit; and a memory coupled to the processing unit and containing instructions stored thereon, the instructions causing the device to perform the method according to a first aspect of this disclosure when executed by the processing unit.

[0007] According to a fourth aspect of this disclosure, a computer program product is provided, which is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method described according to a first aspect of this disclosure.

[0008] According to a fifth aspect of this disclosure, a computer-readable storage medium is provided, the computer-readable storage medium including computer-executable instructions that, when executed by a device, cause the device to perform the method according to a first aspect of this disclosure.

[0009] The summary section is provided to present the chosen concepts in a simplified form, which will be further described in the detailed description below. The summary section is not intended to identify key or principal features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. Attached Figure Description

[0010] Figure 1 A schematic flowchart of a method for optimizing a 3D oral cavity model according to some embodiments of the present disclosure is shown.

[0011] Figure 2 A schematic flowchart illustrating the process of detecting interdental regions according to some embodiments of the present disclosure is shown.

[0012] Figure 3 A schematic diagram of two exemplary connection types is shown.

[0013] Figure 4 A schematic flowchart illustrating the process of identifying misconnected interdental regions according to some embodiments of the present disclosure is shown.

[0014] Figure 5 An exemplary 2D image and its corresponding binarized image for identifying faulty connections are shown.

[0015] Figure 6 Exemplary repair results for two types of faulty connections are shown.

[0016] Figure 7 A schematic block diagram of an apparatus for optimizing a 3D oral cavity model that can implement some embodiments of the present disclosure is shown.

[0017] Figure 8 A block diagram of an electronic device capable of implementing some embodiments of the present disclosure is shown.

[0018] In these accompanying figures, the same or similar reference symbols are used to indicate the same or similar elements. The figures are for illustrative purposes only, and the sizes of the elements are not necessarily drawn to scale. Detailed Implementation

[0019] This disclosure will now be discussed with reference to several example implementations. It should be understood that these implementations are discussed only to enable those skilled in the art to better understand and thus implement this disclosure, and not to imply any limitation on the scope of this disclosure.

[0020] As used herein, the term "comprising" and its variations are to be interpreted as open-ended terms meaning "including but not limited to". The term "based on" is to be interpreted as "at least partially based on". The terms "an implementation" and "an implementation" are to be interpreted as "at least one implementation". The term "another implementation" is to be interpreted as "at least one other implementation". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0021] In the 3D oral cavity modeling process, an intraoral scanner is used to scan the patient's mouth to collect data for 3D reconstruction. During the scanning process, the intraoral scanner continuously acquires two-dimensional (2D) images of the patient's mouth through its imaging module, performing multi-view imaging of the teeth and gingival regions, including structured fringe maps and color images. Image registration and pose estimation algorithms are used to perform feature matching and spatial alignment on adjacent or consecutively acquired 2D images, thereby progressively calculating the scanner's pose information, including the spatial position and orientation of the intraoral scanner at each imaging moment, to describe the geometric relationship between the 2D image and 3D space. Based on the pose information, 2D images acquired from different perspectives can be mapped to the same 3D coordinate system, achieving point cloud fusion and 3D oral cavity model reconstruction. The reconstructed 3D oral cavity model can be represented using mesh data, including 3D point sets and patch sets based on the 3D point sets.

[0022] For a patient's natural teeth, adjacent teeth are generally closely connected and very close together. In this case, due to limitations in 3D model reconstruction algorithms, the close-proximity parts between adjacent teeth will appear as a single, connected element in the reconstructed 3D model, which does not match the actual shape. Therefore, embodiments of this disclosure provide a method for optimizing a 3D oral cavity model. The overall concept is to introduce 2D images (e.g., color images) simultaneously acquired during the intraoral scan as an auxiliary basis for judgment, based on the 3D oral cavity model obtained through intraoral scanning reconstruction. Since the 2D images directly reflect the actual visual morphology of the patient's mouth, by performing correlation analysis between the 2D images and the 3D oral cavity model, structures located in the interdental regions of the 3D oral cavity model can be accurately identified, erroneous connection areas caused by 3D reconstruction errors can be identified, and these erroneous connection areas can be repaired, thereby enabling the optimized 3D oral cavity model to more accurately reproduce the patient's oral cavity morphology.

[0023] Figure 1 A schematic flowchart of a method 100 for optimizing a 3D oral cavity model according to some embodiments of the present disclosure is shown. Method 100 can be implemented by a computing-capable electronic device (e.g., a laptop computer, desktop computer, server, mobile device, etc.). Method 100 may also include additional actions not shown and / or actions shown may be omitted; the scope of the present disclosure is not limited in this respect.

[0024] In box 110, based on the 3D oral cavity model reconstructed through intraoral scanning, one or more candidate 3D point sets located in the interdental region of the 3D oral cavity model are identified, wherein each candidate 3D point set forms a 3D surface that spans between adjacent teeth. This operation is used for pre-detection of erroneous connections between teeth in the 3D oral cavity model. The resulting candidate 3D point sets located in the interdental region can be 3D points in the mesh data representing the 3D oral cavity model, where the 3D surface formed by each candidate 3D point set visually represents a connection between adjacent teeth.

[0025] In box 120, based on two-dimensional (2D) images acquired during intraoral scanning, erroneous 3D point sets from one or more candidate 3D point sets are identified, where, in the reconstructed 3D oral model, the erroneous 3D point sets form 3D surfaces that incorrectly connect adjacent teeth. In some implementations, the 2D images can be color images. In this operation, using 2D images reflecting the true morphology of the oral cavity, several pre-detected interdental regions are further detected to identify erroneous 3D point sets from one or more candidate 3D point sets, where the erroneous 3D point sets form 3D surfaces that incorrectly connect adjacent teeth. Exemplarily, if adjacent teeth are connected in the 2D image (e.g., due to tartar), the pre-detected interdental region is correctly connected; if adjacent teeth are separated in the 2D image, the pre-detected interdental region is incorrectly connected. Erroneously connected interdental regions can be repaired sequentially to obtain a more accurate oral model. See below for further details. Figures 3 to 6 More implementation details of method 100 are described below.

[0026] Figure 2 A schematic flowchart of a process 200 for detecting interdental regions according to some embodiments of the present disclosure is shown. Process 200 can be considered as... Figure 1 An exemplary specific implementation of box 110.

[0027] In box 210, a 3D oral cavity model is acquired through intraoral scanning, and the teeth are extracted to obtain a 3D tooth model. After scanning the patient's intraoral cavity with a scanner, the 3D oral cavity model is obtained through imaging, reconstruction, and post-processing. In some implementations, the teeth in the 3D oral cavity model can be identified through automated recognition (e.g., a trained artificial intelligence AI model) to obtain a 3D tooth model for subsequent geometric analysis.

[0028] During intraoral imaging and reconstruction, the intraoral scanner records the registration relationship between the 2D image and 3D space, establishing a corresponding mapping between pixels in the 2D image and 3D points in the 3D model. Specifically, each 3D point in the 3D oral cavity model can be associated with one or more 2D image pixel locations used to generate that 3D point, thus establishing a mapping relationship from 2D points to the 3D image, as well as a back projection relationship from the 2D image to the 3D model. Through this mapping relationship, any 3D point in the 3D model can be projected onto the corresponding 2D image, or pixel information in the 2D image can be mapped to the corresponding location in the 3D model.

[0029] In box 220, the curvature of the 3D tooth model is calculated, and edge lines are extracted based on the curvature information. In some embodiments, the curvature of each 3D point in the 3D tooth model can be calculated, for example, the average curvature of the principal curvature can be calculated to characterize the geometric changes of the tooth surface at different locations. Since the tooth surface typically has large curvature changes at structural junctions, abrupt morphological changes, or anomalous connections, regions with significant curvature changes can be identified by analyzing the curvature distribution.

[0030] In some embodiments, edge lines in the 3D tooth model can be further extracted based on the calculated curvature information. Edge lines are used to characterize linear structures in the 3D tooth model where curvature changes significantly, such as closed or semi-closed contours formed along the boundaries between adjacent teeth, the transition between teeth and gingiva, or anomalous connection areas.

[0031] In box 230, by identifying regions with curvature exceeding a threshold, one or more candidate 3D point sets located in the interdental regions are determined. In some implementations, a curvature threshold can be set, and 3D points in the tooth 3D model with curvature greater than the threshold can be marked, thus obtaining several regions with large curvature. Subsequently, one or more morphological operations, such as region merging, region filtering, or region smoothing, can be performed on the marked regions to eliminate noise points and make the marked regions present a blocky discrete distribution. After the above processing, interdental regions in the tooth 3D model that may be connected (including correctly connected regions and incorrectly connected interdental regions due to 3D reconstruction errors) will fall into the marked regions, thus forming one or more candidate 3D point sets located in the interdental regions. The obtained 3D point sets can be used as candidate regions for further determination of whether they are incorrectly connected interdental regions.

[0032] Figure 3 A schematic diagram illustrating two exemplary connection types is shown. (For example...) Figure 3 As shown, the connected tooth gaps can be of two types. Type 1 (31) connects two adjacent teeth in a tubular shape, and the gap area does not contact the gingiva. Type 2 (32) connects two adjacent teeth in a strip-like shape, and the gap area contacts the gingiva. Based on whether or not it contacts the gingiva in the 3D oral model, each erroneous 3D point set obtained after pre-detection can be classified as either Type 1 (31) or Type 2 (32). It should be noted that there may be one or more connections within a tooth gap area (corresponding to one or more detected candidate 3D point sets). Type 1 connections can be one or more, while Type 2 connections can be at most one, located at the bottom (for example, the lower dental arch). Different connection types affect the subsequent repair methods, which will be explained in detail below when describing the repair of the oral model.

[0033] For the first type of interdental region, the closed edge line within the tooth model can be calculated based on the 3D curvature, and the 3D points falling on the closed edge line are identified as pre-detected interdental regions. For the second type of interdental region, the boundary of the tooth model is further extracted and the 2D curvature on the boundary is calculated to obtain the convex points on the boundary. For example, the convex points of each second type of interdental region may include the midpoint located at the junction of the interdental gap (identified as a tooth in the 3D oral model) and the gingival junction, one on the lingual side and one on the labial side, i.e., one convex point on each side. Further, four feature points distributed on the edge of the interdental region can be calculated based on these two convex points for subsequent interdental repair. For example, extending to the left and right sides from each convex point yields two feature points, each of which is the corner point of the adjacent tooth with respect to the gingiva.

[0034] In some embodiments, for both types of interdental gap regions, the true interdental gap regions can be further determined based on the geometric topology of the tooth model to avoid misjudgment. For example, interference from non-interdental gap structures (such as model noise, defects, or non-physiological gaps) can be eliminated by analyzing surface curvature, adjacency relationships, and continuity features. The 3D point set of the interdental gap region can also be appropriately pruned to minimize the number of correctly shaped 3D points (i.e., 3D points belonging to the teeth themselves), ensuring it only contains redundant regions due to reconstruction errors. Finally, these pre-detected interdental gap regions on the tooth model are mapped back to the initial 3D oral cavity model.

[0035] Figure 4 A schematic flowchart of a process 400 for identifying misconnected interdental regions according to some embodiments of the present disclosure is shown. Process 400 can be considered as... Figure 1 An exemplary implementation of box 120. For each candidate 3D point set obtained from the pre-detection, process 400 is executed to determine whether the 3D point set is an erroneous 3D point set.

[0036] In general, the 2D image-based judgment process 400 can be understood as follows: for the suspected incorrectly connected interdental gap regions obtained in the aforementioned 3D pre-detection process, a set of 2D images containing the corresponding 3D points of the interdental gap region is selected from the 2D images synchronously acquired by the intraoral scanner during the scanning process. Based on these 2D images, it is finally determined whether the interdental gap region is an incorrectly connected region. The process 400 will be explained below using the first candidate 3D point set in the candidate 3D point set obtained from the pre-detection as an example.

[0037] In box 410, based on the mapping relationship between the 2D images acquired during intraoral scanning and the 3D points in the 3D oral cavity model, a first 2D image including at least a portion of the 3D points of the first candidate 3D point set is obtained. As mentioned earlier, during intraoral scanning, the scanner records the imaging pose information corresponding to the 2D images while acquiring them, thereby establishing a spatial correspondence between the 2D images and the 3D oral cavity model. Based on this mapping relationship, one or more 2D images corresponding to the 3D points in the first candidate 3D point set during scanning can be determined, and at least one 2D image containing at least a portion of the 3D points of the first candidate 3D point set can be selected as the first 2D image for subsequent judgment and processing.

[0038] In some embodiments, a first candidate 3D point set may be downsampled, and then one or more 2D images may be obtained according to a mapping relationship. In some embodiments, a suitable image may be selected from these images as the first 2D image based on the pose information of the 2D images.

[0039] In some embodiments, the first 2D image for the first candidate 3D point set may include one or more images. For example, the first 2D image may include 2D images with imaging directions along the labial, lingual, and occlusal surfaces of the teeth. Since the scanning path and imaging angle of an intraoral scanner differ when scanning different tooth positions, 2D images with different imaging directions are suitable for judgment in different tooth regions. For example, in the molar region, 2D images with imaging directions consistent with the normal direction of the occlusal surface are more advantageous for detecting interdental regions, while in the incisor region, 2D images with labial and lingual directions are more suitable for detection. Furthermore, considering that the appearance of the same interdental region may differ under different imaging perspectives—for example, appearing connected in one perspective and separated in another—in some embodiments, 2D images from multiple imaging perspectives can be combined to comprehensively determine whether the first candidate 3D point set is an erroneous 3D point set, thereby improving the accuracy of the judgment result.

[0040] In box 420, based on the projection of the first candidate 3D point set onto the first 2D image, it is determined whether the first candidate 3D point set is an erroneous 3D point set. In some embodiments, this determination process can be implemented through a series of actions shown in boxes 422 to 426, thereby combining the actual intraoral morphology reflected in the 2D image to further confirm the interdental regions in the 3D oral model and determine whether they are erroneous connections.

[0041] In box 422, the tooth portion in the first 2D image is detected, and the interdental regions in the first 2D image are identified. In some embodiments, an AI model can be used to analyze the first 2D image, predict the regions in the image corresponding to teeth, and construct a binary image of the teeth based on the prediction results. Subsequently, the binary image of the teeth can be processed using the topological relationships of the image, for example, determining the enclosing regions of the tooth regions and subtracting the tooth regions from the enclosing regions, thereby obtaining a binary image composed of interdental and non-interdental regions.

[0042] In box 424, the projection of each 3D point in the first candidate 3D point set onto the first 2D image is calculated, and it is determined whether the projected point is located in the interdental region of the first 2D image. Specifically, based on the imaging pose relationship corresponding to the first 2D image, the 3D points in the first candidate 3D point set can be projected onto the first 2D image to obtain the corresponding projection point positions. In some embodiments, a 2D image with a suitable imaging direction is selected according to the tooth position information, so that the interdental region has clearer and more distinguishable features in the 2D image, which helps to improve the accuracy of the judgment.

[0043] In box 426, if the number of 3D points projected onto the interdental space from the first candidate 3D point set exceeds a preset threshold, or the proportion of 3D points projected onto the interdental space exceeds a preset threshold, then the first candidate 3D point set is determined to be an erroneous 3D point set. That is, this 3D point set belongs to an erroneous connection, and therefore repair processing can be performed on it. Conversely, if the number or proportion of 3D points projected onto the interdental space does not reach the threshold, then the first candidate 3D point set is determined not to be an erroneous 3D point set, and no repair processing is performed on this 3D point set.

[0044] Figure 5 An exemplary 2D image and its corresponding binarized image for identifying faulty connections are shown. Figure 5 (a) shows a 2D image obtained by an intraoral scanner with the imaging orientation (pose) aligned with the occlusal surface of the teeth, and the imaging orientation is perpendicular to the occlusal surface. Figure 5 (b) shows a binary image of a tooth, where white represents teeth and black represents non-tooth areas. Figure 5 (c) shows a binarized image of tooth gaps, where white represents tooth gaps and black represents non-gap areas. For a 3D point set, if it falls within... Figure 5 When the number or proportion of projection points in the interdental region of (c) exceeds the threshold, it indicates that the 3D projection model does not match the real shape of the tooth, that is, the 3D point set belongs to the erroneous connection caused by the three-dimensional reconstruction algorithm.

[0045] To repair a 3D oral cavity model, after identifying erroneous 3D point sets, these sets can be removed. With the removal of these erroneous point sets, one or more holes will form at the corresponding locations in the 3D oral cavity model. Subsequently, repair processing can be performed on these holes to eliminate the geometric anomalies caused by the erroneous connections, restoring a more accurate intraoral morphology in the interdental regions of the repaired 3D oral cavity model. As mentioned earlier, erroneous 3D point sets in the interdental spaces can be divided into two different types; therefore, different hole repair methods can be used for different types of erroneous connection areas.

[0046] In some embodiments, one or more cavities are repaired based on the type of the removed erroneous 3D point set, which can be a first type that does not contact the gingiva or a second type that does contact the gingiva. (See reference) Figure 3 When the first type of error 3D point set 31 is removed, two independent holes will be formed on the surfaces of two adjacent teeth respectively; while when the second type of error 3D point set is removed, a connected hole will be formed on the side of the adjacent teeth and in the contact area between the teeth and the gums.

[0047] In some embodiments, when the removed erroneous 3D point set is of type 1, the two holes located on adjacent teeth are repaired separately. Specifically, for the type 1 erroneous connection region, after removing the corresponding interdental 3D point set, a hole will be formed on the surface of each of the two adjacent teeth. Triangulation operations can be performed on these two holes separately, and the hole areas can be refined and smoothed after triangulation. Simultaneously, parameters during the smoothing process can be controlled to prevent the two holes from intersecting or overlapping during the repair process, thereby ensuring that the repaired tooth surface maintains a geometrically reasonable and natural shape.

[0048] In some embodiments, when the removed erroneous 3D point set is of the second type, connecting holes located on adjacent teeth and gingiva are repaired based on multiple feature points in the interdental region where the removed erroneous 3D point set is located. Connecting holes include vertical portions located on the sides of two teeth and horizontal portions located in the area where the teeth contact the gingiva. For this purpose, feature points at the edges of the interdental region can be used to structurally divide and constrain the connecting holes.

[0049] Specifically, the boundary of the tooth model can be extracted first, and its 2D curvature can be calculated to identify two convex points on the boundary. These two convex points are located at the midpoint of the tooth-gingival contact area on the labial and lingual sides, respectively. Then, based on these two convex points, four feature points can be calculated by extending left and right, distributed along the edge of the interdental region. Based on these four feature points, the connecting cavity can be divided into two vertical parts on the tooth lateral surface and one horizontal part in the tooth-gingival contact area, and triangulation can be performed on each part. Afterward, the entire cavity area can be refined and smoothed, with smoothing parameters controlled to avoid self-intersection in the restoration result, thus obtaining a continuous, smooth, and accurate restoration of the intraoral structure.

[0050] Figure 6 Exemplary repair results for two types of faulty connections are shown. Among them, Figure 6 (a) shows a schematic of the first type of faulty connection before repair and the corresponding repair result; Figure 6 (b) shows a schematic of the second type of faulty connection before repair and the corresponding repair result.

[0051] Figure 7 A schematic block diagram of an apparatus 700 for optimizing a 3D oral cavity model according to some embodiments of the present disclosure is shown. The apparatus 700 can be implemented in an electronic device with computing capabilities. Figure 7 As shown, the device 700 includes a gap region determination unit 710, configured to determine one or more candidate 3D point sets located in gap regions of the 3D oral model based on a 3D oral model reconstructed through an intraoral scan, wherein each candidate 3D point set forms a 3D surface that spans between adjacent teeth. The device 700 also includes an error connection identification unit 720, configured to identify erroneous 3D point sets in one or more candidate 3D point sets based on 2D images acquired during the intraoral scan, wherein the 3D surfaces formed by the erroneous 3D point sets incorrectly connect adjacent teeth in the reconstructed 3D oral model. Optionally, in some embodiments, the device 700 may further include a repair unit (not shown), configured to remove the erroneous 3D point sets from the 3D oral model and repair one or more holes formed in the 3D oral model after the removal of the erroneous 3D point sets.

[0052] It should be noted that the reference Figures 1 to 6 More actions or steps can be shown through Figure 7 The illustrated device 700 is used to implement this. For example, device 700 may include more modules or units to implement the actions or steps described above, or Figure 7 Some of the units or modules shown can be further configured to implement the actions or steps described above. This will not be repeated here.

[0053] Based on the above references Figures 1 to 7 The exemplary embodiments described herein. This disclosure further optimizes the structure of interdental regions in a 3D oral model by introducing 2D images acquired synchronously during intraoral scanning as auxiliary information. Since 2D images directly reflect the true visual morphology within the mouth, correlation analysis between the 3D point set corresponding to the interdental regions and the 2D images allows for more accurate identification of erroneous connections in the 3D oral model caused by reconstruction errors. Furthermore, this disclosure performs subsequent repair processing on the interdental regions identified as erroneously connected, making the repaired 3D oral model more closely resemble the actual morphology of the patient's mouth. This approach improves the accuracy of the optimized 3D oral model in morphological representation, facilitating its use in subsequent applications.

[0054] Figure 8 A schematic block diagram of an electronic device 800 that can be used to implement embodiments of the present disclosure is shown. As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 may also be stored in the RAM 803. The computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0055] Multiple components in electronic device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0056] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above. For example, in some embodiments, any method described in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of any of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the methods provided in this disclosure by any other suitable means (e.g., by means of firmware).

[0057] In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.

[0058] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0059] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media within the respective computing / processing device.

[0060] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​and conventional procedural programming languages. The computer-readable program instructions may execute entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0061] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0062] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0063] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0064] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for optimizing a three-dimensional (3D) oral cavity model, comprising: Based on the 3D oral cavity model reconstructed by intraoral scanning, one or more candidate 3D point sets located in the interdental region of the 3D oral cavity model are determined, wherein the 3D surface formed by each candidate 3D point set is connected between adjacent teeth. as well as For the first candidate 3D point set in the one or more candidate 3D point sets... Based on the mapping relationship between the two-dimensional (2D) images acquired during the intraoral scan and the 3D points in the 3D oral cavity model, a first 2D image is selected, wherein the first 2D image includes at least a portion of the 3D points from the first candidate 3D point set. Identify the interdental regions in the selected first 2D image, and In response to the projection of more than a threshold number of 3D points or more than a threshold proportion of 3D points from the first candidate 3D point set onto the interdental region, the first candidate 3D point set is determined as an erroneous 3D point set as a whole, wherein, in the reconstructed 3D oral model, the 3D surface formed by the erroneous 3D point set incorrectly connects adjacent teeth.

2. The method according to claim 1, wherein, Determining one or more candidate 3D point sets located in the interdental region of the 3D oral model includes: Identify the 3D tooth model in the 3D oral cavity model; Calculate the curvature of the 3D model of the teeth; and By identifying regions where the curvature exceeds a threshold, one or more candidate 3D point sets located in the interdental region are determined.

3. The method according to claim 1, wherein, The first 2D image includes at least one of the following: an image whose imaging direction is consistent with the normal direction of the occlusal surface of the tooth, an image whose imaging direction is consistent with the labial direction of the tooth, or an image whose imaging direction is consistent with the lingual direction of the tooth.

4. The method according to any one of claims 1 to 3, further comprising: Remove the identified set of erroneous 3D points from the 3D oral cavity model; as well as Repair one or more holes formed on the 3D oral cavity model after the removal of the erroneous 3D point set.

5. The method according to claim 4, wherein, Repairing one or more holes formed on the 3D oral cavity model corresponding to the removed erroneous 3D point set includes: Based on the type of the removed erroneous 3D point set, repair one or more holes, wherein the type is either a first type where the erroneous 3D point set does not contact the gingiva or a second type where the erroneous 3D point set contacts the gingiva.

6. The method according to claim 5, wherein, When the removed set of erroneous 3D points is of the first type, repair the two holes located on adjacent teeth.

7. The method according to claim 5, wherein, When the removed erroneous 3D point set is of type 2, Based on multiple feature points in the interdental region at the removed erroneous 3D point set, repair the connecting holes located on adjacent teeth and gums.

8. An apparatus for optimizing a 3D oral cavity model, comprising: The interdental region determination unit is configured to determine one or more candidate 3D point sets located in the interdental region of the 3D oral model based on a 3D oral model reconstructed by intraoral scanning, wherein each candidate 3D point set forms a 3D surface that spans between adjacent teeth. as well as The error connection identification unit is configured to: for the first candidate 3D point set in the one or more candidate 3D point sets, Based on the mapping relationship between the two-dimensional (2D) images acquired during the intraoral scan and the 3D points in the 3D oral cavity model, a first 2D image is selected, wherein the first 2D image includes at least a portion of the 3D points from the first candidate 3D point set. Identify the interdental regions in the selected first 2D image, and In response to the projection of more than a threshold number of 3D points or more than a threshold proportion of 3D points in the first candidate 3D point set onto the interdental region, the first candidate 3D point set is identified as an erroneous 3D point set as a whole, wherein, in the reconstructed 3D oral model, the 3D surface formed by the erroneous 3D point set incorrectly connects adjacent teeth.

9. An electronic device, comprising: Processing unit; as well as A memory, coupled to the processing unit and containing instructions stored thereon, which, when executed by the processing unit, cause the device to perform the method according to any one of claims 1 to 7.

10. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 7.

Images