A method for simulating defect in point cloud of physical scanning of mechanical parts considering multiple factors

By constructing point cloud rays and multi-viewpoint data to simulate the defects of scanning point clouds of mechanical parts, the problem of point cloud missing caused by multiple factors in the existing technology is solved, a variety of defect simulation methods are provided, and the efficiency and economy of point cloud processing are improved.

CN120064318BActive Publication Date: 2025-09-09ZHEJIANG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510513451.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-04-23
Publication Date
2025-09-09
Estimated Expiration
2045-04-23

AI Technical Summary

Technical Problem

The existing technology lacks an effective method to simulate the defects of scanning point clouds of mechanical parts, which leads to the loss or damage of point cloud data when reflective areas, scanning blind spots, identification points and the bottom are missing, and there is a lack of simulation methods that take multiple factors into consideration.

Method used

By constructing point cloud rays, obtaining visible points, simulating defects caused by reflections, blind spots and identification points, and combining multi-viewpoint data, a diverse defect point cloud is generated, including surface reflective holes, scanning blind spots, scanning identification point holes and missing parts at the bottom of the workpiece.

Benefits of technology

It provides a rich benchmark dataset, enhances the realism and complexity of point cloud missing processing, reduces the actual acquisition cost and time constraints, improves the efficiency of point cloud processing, and provides support for research and technological development in related fields.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120064318B_ABST
    Figure CN120064318B_ABST
Patent Text Reader

Abstract

The present invention discloses a method for simulating defects in scanning point clouds of physical mechanical parts taking into account multiple factors. The method comprises: obtaining a defect-free scanning point cloud of a physical mechanical part and constructing a point cloud ray under a single viewpoint, and then constructing a single viewpoint visible point cloud; obtaining a simulated reflective defect point cloud according to the reflection intensity of each visible point; constructing a multi-viewpoint visible point cloud under multiple viewpoints, and obtaining a simulated blind area defect point cloud after intersecting and merging the multi-viewpoint visible point cloud and the reflective defect point cloud; then removing the defect circle and the bottom defect point to obtain the final simulated defect point cloud. The method of the present invention can simulate common missing or damaged situations in the actual point cloud acquisition process, can cover a wide range of scenarios, provide diversified defect simulations, enhance the realism and complexity of point cloud missing processing, reduce the time limit problem that may be encountered in the actual acquisition process, improve the efficiency of point cloud processing, and provide strong support for research and technological development in related fields.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a point cloud defect simulation method, and in particular to a point cloud defect simulation method for physical scanning of mechanical parts taking multiple factors into consideration. Background Art

[0002] In the actual acquisition process, point cloud data of mechanical parts are often missing or damaged due to various factors. If the reflectivity of the workpiece surface material is high, the scanned point cloud will have holes in the reflective area; if the workpiece surface is complex or has depressions, the point cloud will be missing due to blind spots during scanning; if identification points are attached to the workpiece surface before scanning, the point cloud obtained after scanning will have holes at the identification points; if the workpiece is placed on the workbench surface and only one side is scanned, the bottom point cloud obtained will be missing. The above situations often occur at the same time, resulting in defects and missing scanned point clouds. However, there is currently a lack of a defect simulation method that can effectively simulate the above situations. Summary of the Invention

[0003] To address the issues presented in the prior art, the present invention provides a multi-factor point cloud defect simulation method for scanning physical mechanical parts. This method can provide a richer and more diverse benchmark dataset for testing and optimizing point cloud completion algorithms. It can simulate common missing or damaged conditions during actual point cloud acquisition, and offers new insights and approaches for addressing missing point clouds, providing strong support for research and technological development in related fields.

[0004] The technical solution adopted in the present invention is:

[0005] The method for simulating defect of a point cloud of a physical scanning of a mechanical part taking multiple factors into consideration of the present invention comprises:

[0006] Step S1: Obtain a defect-free scanning point cloud of a physical mechanical part, and construct a point cloud ray under a single viewpoint. Obtain visible points in the defect-free scanning point cloud based on the point cloud ray, thereby constructing a single viewpoint visible point cloud.

[0007] Step S2: Obtain the reflection intensity of each visible point in step S1, obtain the non-reflective points among the visible points according to the reflection intensity, and obtain a simulated reflection defect point cloud.

[0008] Step S3: Obtain visible points under multiple viewpoints according to each visible point cloud in step S1, thereby constructing a multi-viewpoint visible point cloud, and intersect and merge the multi-viewpoint visible point cloud and the reflective defect point cloud to obtain a simulated blind spot defect point cloud.

[0009] Step S4: setting several defect centers in the blind area defect point cloud and removing defect circles to obtain a marked defect point cloud, and then removing the bottom defect points to obtain the final simulated defect point cloud.

[0010] The step S1 is as follows:

[0011] Step S11: generating an interval light source and viewpoint on the defect-free scanning point cloud of the actual mechanical part, and illuminating the defect-free scanning point cloud with the light source.

[0012] Step S12: Taking the viewpoint as the starting point, construct rays from the viewpoint to each point in the defect-free scan point cloud, and then normalize the ray directions of each ray.

[0013] Step S13: For each normalized ray and the point in the defect-free scanning point cloud through which it passes, determine the nearest intersection point between the normalized ray and the defect-free scanning point cloud, thereby obtaining a first distance D between the starting point of the normalized ray and the nearest intersection point, and at the same time obtain a second distance d between the starting point and the point in the defect-free scanning point cloud through which the normalized ray passes. If the first distance D is equal to the second distance d, retain the current point as a visible point; if the first distance D is less than the second distance d, remove the current point as an invisible point.

[0014] In step S11, the center of gravity of the point cloud is obtained based on the enclosing size of the initial complete three-dimensional point cloud model. With the center of gravity of the defect-free scanned point cloud as the center of the circle, a spherical shell area is generated with an area larger than the area of ​​the defect-free scanned point cloud at a preset first radius R. The generated light source and viewpoint are located in the interval area between the defect-free scanned point cloud and the spherical shell area to avoid the light source and viewpoint being too close or too far from the point cloud.

[0015] In the step S2, the reflection intensities of the visible points are arranged in order of size, and the visible points whose reflection intensities exceed a preset reflection threshold are removed as reflective points, and the remaining non-reflective points are retained.

[0016] In step S3, the viewpoint is rotated around the center of gravity of the single-viewpoint visible point cloud to generate several new viewpoints evenly spaced on the same circle around the single-viewpoint visible point cloud. For each new viewpoint, several visible points are obtained according to the same operation as the single viewpoint in step S1. The visible points under each new viewpoint are intersected and merged to construct a multi-viewpoint visible point cloud.

[0017] In the step S4, the curvature of each point in the blind spot defect point cloud is obtained, and the point whose curvature is lower than the preset curvature threshold is selected as the defect center. At the same time, the distance between each two defect centers is greater than the preset distance threshold. For each defect center, a defect circle is generated and removed at a preset second radius with the defect center as the center of the circle to simulate the scanning defect caused by the attached identification point. The preset second radius is the radius of the attached identification point.

[0018] In the blind area defect point cloud, for each point, a local neighborhood of the point is obtained through nearest neighbor search, and then the curvature of the point is obtained.

[0019] In step S4, in the identified defective point cloud, points with z-axis coordinates within the range of ±z', including points with z = 0, are removed. z' is a preset range of values ​​less than 1, determined based on the order of magnitude of the point cloud model size, thereby removing bottom defective points. A coordinate system is established with the contact point of the actual mechanical part placed on the workbench as the origin.

[0020] The electronic device of the present invention comprises: a memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method described above.

[0021] The readable storage medium of the present invention stores program data thereon, and when the program data is executed by a processor, the method described above is implemented.

[0022] The beneficial effects of the present invention are:

[0023] The method described in this paper can simulate common defects or damage during actual point cloud acquisition. By simulating typical defects, including surface reflective holes, scanning blind spots, holes in scanning marker points, and missing parts at the bottom of the workpiece, it can cover a wider range of scenarios and provide diverse defect simulations. This enhances the realism and complexity of point cloud defect processing, reduces the cost and time constraints that may be encountered during actual acquisition, and improves the efficiency and cost-effectiveness of point cloud processing, providing strong support for research and technological development in related fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 Schematic diagram of the process of the present invention;

[0025] Figure 2 This is a schematic diagram of the simulation of scanning point cloud defects caused by reflection;

[0026] Figure 3 This is a schematic diagram of the simulation of scanning point cloud defects caused by scanning blind areas;

[0027] Figure 4 This is a schematic diagram of the simulation of scan point cloud defects caused by attaching marker points;

[0028] Figure 5 Schematic diagram of the scan point cloud defect simulation with the bottom missing. DETAILED DESCRIPTION

[0029] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods consistent with some aspects of the present invention as detailed in the appended claims. The terms used in the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms of "a", "said" and "the" used in the present invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0030] like Figure 1 As shown, this example provides a method for simulating defect in a point cloud scanned from a mechanical part taking multiple factors into consideration, which specifically includes the following steps:

[0031] First, obtain a defect-free scanning point cloud of a physical mechanical part. In a specific embodiment of the present invention, the original point cloud is obtained by sampling based on a grid model, so the coordinate system of the point cloud is defined relative to the grid model. Initialize and calculate the point cloud to obtain the point cloud model bounding box size (0.55676186, 0.64289296, 0.67855352) and the center of gravity coordinates of the point cloud (0.27859916, 0.3216921, 0.2979903); then construct a point cloud ray under a single viewpoint, and generate an interval of light source and viewpoint on the defect-free scanning point cloud of the physical mechanical part. When generating the light source and viewpoint, it is necessary to obtain the center of gravity of the point cloud based on the initial complete three-dimensional point cloud model bounding size, and use the center of gravity of the defect-free scanning point cloud as the center of the circle to generate an area larger than the defect-free scanning point under the preset first radius R. The spherical shell area of ​​the cloud area, the defect-free scanning point cloud is contained in the spherical shell area. In the specific implementation, the preset first radius R is taken as 3. In the specific implementation, the coordinates of the light source are (3.40833147, 2.40880656, 1.32348524), and the coordinates of the viewpoint are (0.17890525, 1.1228733, -0.61864617). The generated light source and viewpoint are located in the interval area between the defect-free scanning point cloud and the spherical shell area to avoid the light source and the viewpoint being too close or too far from the point cloud.

[0032] The defect-free scan point cloud is illuminated by a light source, and a ray is constructed from the viewpoint to each point in the defect-free scan point cloud with the viewpoint as the starting point. Then, the ray direction of each ray is normalized. For each normalized ray and the point in the defect-free scan point cloud it passes through, the nearest intersection point between the normalized ray and the defect-free scan point cloud is determined, thereby obtaining a first distance D between the starting point of the normalized ray and the nearest intersection point. At the same time, a second distance d between the starting point and the point in the defect-free scan point cloud through which the normalized ray passes is obtained. If the first distance D is equal to the second distance d, D=d, then the current point is considered visible and retained as a visible point. If the first distance D is less than the second distance d, D<d, then the current point is considered invisible and the current point is removed as an invisible point. The visible points in the defect-free scan point cloud obtained according to the point cloud ray are constructed into a single-viewpoint visible point cloud.

[0033] Then, the reflection intensity of each visible point in the single-viewpoint visible point cloud is obtained. By considering factors such as lighting conditions and surface reflection, the light source, observer position and object surface normal are used to calculate the mirror reflection intensity, thereby simulating the point cloud defects caused by reflection. L The details are as follows:

[0034] L =( K s I / r 2 )max(0,cos α ) p

[0035] in, K s Indicates the absorption rate of light by the point, set to 0.5; I / r 2 It represents the light intensity reaching the point from the light source. I Indicates the light intensity, set to 1; r Indicates the distance from the light source to the point; α It represents the angle between the line of sight and the angle bisector of the incident light and the normal line; p Indicates the exponent for accelerating decay, set to 20.

[0036] After calculating the reflection intensity of each point in the visible part of the point cloud, obtain the non-reflective points among the visible points according to the reflection intensity, sort the reflection intensity of each visible point in order of size, and remove the top 5% of the visible points as the reflective part. That is, remove the visible points whose reflection intensity exceeds the preset reflection threshold as reflective points, and retain the remaining non-reflective points. Figure 2As shown, when the present invention is implemented, the scanning point cloud defects caused by the reflection of the physical surface of the mechanical part simulated by the nut point cloud model can be obtained and finally removed.

[0037] Then, based on each visible point cloud in the single-viewpoint visible point cloud, visible points are obtained under multiple viewpoints. The point cloud data obtained from different viewpoints are combined to generate visible point clouds with different scanning angles and viewpoint characteristics, thereby simulating the scanning blind area defects caused by complex surfaces. The viewpoint is rotated around the center of gravity of the single-viewpoint visible point cloud to generate 20 new viewpoints that are evenly spaced on the same circle around the single-viewpoint visible point cloud. They are evenly spaced on the unit circle in the (x, y) direction. For each new viewpoint, several visible points are obtained according to the same operation as the single viewpoint. The visible points under each new viewpoint are intersected and merged to construct a multi-viewpoint visible point cloud. The multi-viewpoint visible point cloud and the reflective defect point cloud are intersected and merged to obtain a simulated blind area defect point cloud. Figure 3 As shown, when the present invention is implemented, the scanning point cloud defects caused by the scanning blind areas due to the complex surface of the part or environmental limitations when scanning the actual mechanical part simulated by the nut point cloud model can be obtained and finally removed.

[0038] Obtain the curvature of each point in the blind spot defect point cloud. When the present invention is implemented, for each point, the local neighborhood of the point is obtained through nearest neighbor search, and then the curvature of the point is obtained. The point whose curvature is lower than the preset curvature threshold is selected as the defect center, and the threshold is set to the lower quartile of all curvatures. The low curvature point below the threshold is randomly selected as the circular defect center. At the same time, the distance between every two defect centers is greater than the preset distance threshold. The distance between the defect centers is specifically set to be greater than 0.06. For each defect center, with the defect center as the center of the circle, a defect circle is generated and removed at a preset second radius. The preset second radius is the radius of the attached identification point. When implemented, a circular defect circle area is constructed with a radius of 0.03 and removed to obtain the identification defect point cloud. By dividing the low curvature area, a reasonably distributed circular defect is generated, thereby simulating the hole defect at the attached scanning identification point, that is, simulating the scanning defect caused by the attached identification point. As Figure 4 As shown, when the present invention is implemented, the scanning point cloud defects caused by the attachment of identification points on the physical surface of the mechanical part can be obtained by simulating the nut point cloud model and finally removed.

[0039] Finally, the bottom defect points need to be removed. In the defect point cloud, the points with z-axis coordinates in the range of ±z' are removed, including the point z=0. z' is a preset range value less than 1, which is determined according to the order of magnitude of the point cloud model size. In specific implementation, the value of z' is 0.01, thereby removing the bottom defect points. In specific implementation, the contact point of the mechanical part placed on the workbench is used as the origin to establish a coordinate system. By limiting the range of the z coordinate to simulate the defect area on the surface of the contact workbench, the final simulated defect point cloud is obtained. Figure 5 As shown, when the present invention is implemented, a nut point cloud model can be obtained to simulate the bottom missing scanning point cloud defect caused by the bottom of the physical mechanical part contacting the workbench surface, and finally remove it.

[0040] The present invention also designs a mechanical parts physical scanning point cloud defect simulation system that considers multiple factors. The mechanical parts physical scanning point cloud defect simulation system includes a data acquisition module, a single viewpoint visible point cloud construction module, a reflective defect point cloud construction module, a blind area defect point cloud construction module and a final defect point cloud construction module. The data acquisition module obtains the defect-free scanning point cloud of the mechanical parts physical object and displays it on the display; the single viewpoint visible point cloud construction module constructs point cloud rays under a single viewpoint, obtains visible points in the defect-free scanning point cloud according to the point cloud rays, thereby constructing a single viewpoint visible point cloud and displaying it on the display; the reflective defect point cloud construction module obtains The reflection intensity of each visible point is obtained, and the non-reflective points in each visible point are obtained according to the reflection intensity, and a simulated reflective defect point cloud is obtained and displayed on the display; the blind spot defect point cloud construction module obtains visible points under multiple viewpoints according to each visible point cloud, thereby constructing a multi-viewpoint visible point cloud, and intersects and merges the multi-viewpoint visible point cloud and the reflective defect point cloud to obtain a simulated blind spot defect point cloud, and displays it on the display; the final defect point cloud construction module sets several defect centers in the blind spot defect point cloud and removes the defect circles to obtain the identified defect point cloud, and then removes the bottom defect point to obtain the final simulated defect point cloud, and displays it on the display.

[0041] The point cloud defect simulation method for physical scanning of mechanical parts taking multiple factors into consideration in the present invention can simulate common missing or damage situations in the actual point cloud acquisition process, and can provide a richer and more diverse benchmark data set for the testing and optimization of the point cloud completion algorithm. By simulating typical defects, including surface reflective holes, scanning blind spots, scanning identification point holes, and missing workpiece bottoms, it can cover a wider range of scenarios and provide diversified defect simulations, thereby enhancing the realism and complexity of point cloud missing processing, reducing the cost and time constraints that may be encountered in the actual acquisition process, and improving the efficiency and economy of point cloud processing. It provides new ideas and methods for point cloud missing processing and provides strong support for research and technological development in related fields.

[0042] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0043] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application may be implemented in various computer languages. The present application is described in terms of flowcharts of the methods, systems, and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0044] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the present invention is intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0045] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the equivalent technology of the present invention, the present application is intended to include these modifications and variations.

Claims

1. A method for simulating defect in point cloud of physical scanning of mechanical parts considering multiple factors, characterized in that: include: Step S1: Obtain a defect-free scanning point cloud of a physical mechanical part, and construct a point cloud ray under a single viewpoint. Obtain visible points in the defect-free scanning point cloud based on the point cloud ray, thereby constructing a single viewpoint visible point cloud. Step S2: Obtain the reflection intensity of each visible point in step S1, obtain the non-reflective points among the visible points according to the reflection intensity, and obtain a simulated reflection defect point cloud; Step S3: Obtain visible points under multiple viewpoints based on each visible point cloud in step S1, thereby constructing a multi-viewpoint visible point cloud, and intersecting and merging the multi-viewpoint visible point cloud and the reflective defect point cloud to obtain a simulated blind spot defect point cloud; Step S4: setting several defect centers in the blind area defect point cloud and removing defect circles to obtain a marked defect point cloud, and then removing the bottom defect point to obtain the final simulated defect point cloud; The step S1 is as follows: Step S11: generating an interval light source and viewpoint on the defect-free scan point cloud of the mechanical part object, and illuminating the defect-free scan point cloud with the light source; Step S12: Taking the viewpoint as the starting point, construct rays from the viewpoint to each point in the defect-free scan point cloud, and then normalize the ray directions of each ray; Step S13: For each normalized ray and the point in the defect-free scanning point cloud through which it passes, determine the nearest intersection point between the normalized ray and the defect-free scanning point cloud, thereby obtaining a first distance D between the starting point of the normalized ray and the nearest intersection point, and at the same time obtain a second distance d between the starting point and the point in the defect-free scanning point cloud through which the normalized ray passes. If the first distance D is equal to the second distance d, retain the current point as a visible point; if the first distance D is less than the second distance d, remove the current point as an invisible point.

2. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 1, characterized in that: In the step S11, a spherical shell area is generated with the center of gravity of the defect-free scanning point cloud as the center of the circle under a preset first radius R, and the area is larger than the area of ​​the defect-free scanning point cloud. The generated light source and viewpoint are located in the interval area between the defect-free scanning point cloud and the spherical shell area.

3. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 1, characterized in that: In the step S2, the reflection intensities of the visible points are arranged in order of size, and the visible points whose reflection intensities exceed a preset reflection threshold are removed as reflective points, and the remaining non-reflective points are retained.

4. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 1, characterized in that: In step S3, the viewpoint is rotated around the center of gravity of the single-viewpoint visible point cloud to generate several new viewpoints evenly spaced on the same circle around the single-viewpoint visible point cloud. For each new viewpoint, several visible points are obtained according to the same operation as the single viewpoint in step S1. The visible points under each new viewpoint are intersected and merged to construct a multi-viewpoint visible point cloud.

5. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 1, characterized in that: In step S4, the curvature of each point in the blind spot defect point cloud is obtained, and the point whose curvature is lower than the preset curvature threshold is selected as the defect center. At the same time, the distance between each two defect centers is greater than the preset distance threshold. For each defect center, a defect circle is generated with the defect center as the center and is removed at a preset second radius.

6. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 5, characterized in that: In the blind area defect point cloud, for each point, the local neighborhood of the point is obtained through nearest neighbor search, and then the curvature of the point is obtained.

7. The method for simulating defect of a mechanical part scanning point cloud considering multiple factors according to claim 1, characterized in that: In the step S4, in the identified defect point cloud, points with z-axis coordinates in the range of ±z' are removed, where z' is a preset range value less than 1, thereby removing the bottom defect points.

8. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program data, and the processor calls the program data to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having program data stored thereon, characterized in that: When the program data is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Point cloud data generation method and device, equipment and storage medium

    CN117034579A

  • Industrial part three-dimensional point cloud repairing method and device based on deep learning

    CN117671131A