Physical modeling method, system, storage medium and computer for virtual clothing

Abstract

The present invention provides a physical modeling method, system, storage medium, and computer for virtual clothing. The method includes: performing point cloud conversion on image information of several different types of clothing to obtain point cloud images; performing point cloud projection and point cloud boundary optimization on each point cloud image to obtain point cloud boundary optimization information; performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis of each point cloud boundary optimization information to construct a symmetrical object model of each clothing; inputting the local texture optimization results of each point cloud image into the symmetrical object model for model optimization to obtain an optimized object model; constructing a corresponding demand library based on design parameters corresponding to user needs and clothing types, using the demand library and the optimized object model for model fusion, and using the fused model to implement physical modeling of virtual clothing data. The present invention uses the optimization results to optimize the symmetrical object model, thereby achieving rapid construction of the physical model of the virtual clothing.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a physical modeling method, system, storage medium and computer for virtual clothing. Background Art

[0002] With the rapid development of science and technology and the improvement of people's living standards, digital technology and the real economy have achieved deep integration to realize industrial digitalization;

[0003] Virtual clothing refers to clothing that exists in a virtual environment, created by simulating fabrics using digital technology. This is achieved through computer simulation, taking into account clothing patterns, fabric properties, body shape and human movements, as well as the shape and changes when worn. Current physical modeling methods for virtual clothing typically employ the finite element method, based on continuum mechanics, to achieve high-precision deformation simulation by solving partial differential equations. However, this approach's computational complexity increases exponentially with mesh refinement, and relies on empirical mechanical parameter settings. The boundary treatment between multiple layers of clothing is relatively rough, resulting in distorted layering effects and less-than-ideal modeling results. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a physical modeling method, system, storage medium and computer for virtual clothing, so as to at least solve the deficiencies in the above-mentioned technologies.

[0005] The present invention proposes a physical modeling method for virtual clothing, comprising:

[0006] Collecting image information of a plurality of different types of clothing, and performing point cloud conversion on each of the image information to obtain a point cloud image of each of the image information;

[0007] Performing point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images;

[0008] defining a symmetry axis of each point cloud boundary optimization information, and performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment;

[0009] Performing local texture optimization on each of the point cloud images, and inputting the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model;

[0010] Based on the types of each of the clothing, corresponding user needs are obtained, and a corresponding demand library is constructed based on the user needs and the design parameters corresponding to the types of clothing. The demand library is used to fuse the model with the optimized object model, and the fused model is used to realize physical modeling of virtual clothing data.

[0011] Furthermore, the steps of collecting image information of a plurality of different types of clothing and performing point cloud conversion on each of the image information to obtain a point cloud image of each of the image information include:

[0012] Performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of equal number;

[0013] The coordinate average value of each point cloud data group is calculated, and the point cloud data are segmented according to each coordinate average value and a preset plane threshold value to obtain a point cloud image corresponding to each image information.

[0014] Furthermore, the step of performing point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images includes:

[0015] Performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images;

[0016] The least squares method is used to smooth the boundary information of each point cloud, and based on the smoothed point cloud boundary information, the boundary fitting optimization is performed on the corresponding point cloud image to obtain point cloud boundary optimization information.

[0017] Furthermore, the steps of defining a symmetry axis of each point cloud boundary optimization information and performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment include:

[0018] defining a symmetry axis of each of the point cloud boundary optimization information, and performing an axial rotation on the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding rotation matrix;

[0019] The point cloud boundary optimization information is inversely rotated based on the symmetry axis to obtain a corresponding inverse rotation matrix, and the rotation matrix and the inverse rotation matrix are combined to construct a symmetrical object model of each of the garments.

[0020] Furthermore, the step of performing local texture optimization on each of the point cloud images includes:

[0021] Sampling all point clouds in each of the point cloud images along the corresponding contour normal direction to obtain grayscale sampling vectors corresponding to all point clouds in each of the point cloud images;

[0022] Local texture optimization is performed on each of the point cloud images according to the grayscale sampling vector to obtain a corresponding local texture optimization result.

[0023] The present invention also proposes a physical modeling system for virtual clothing, comprising:

[0024] A point cloud conversion module is used to collect image information of a plurality of different types of clothing and perform point cloud conversion on each of the image information to obtain a point cloud image of each of the image information;

[0025] A boundary optimization module, configured to perform point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images;

[0026] an object model construction module, configured to define a symmetry axis of each point cloud boundary optimization information, and perform boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment;

[0027] a texture optimization module, configured to perform local texture optimization on each of the point cloud images, and input the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model;

[0028] The physical modeling module is used to obtain corresponding user needs based on the type of each clothing, construct a corresponding demand library based on the user needs and the design parameters corresponding to the type of clothing, use the demand library and the optimized model to perform model fusion, and use the fused model to realize physical modeling of virtual clothing data.

[0029] Furthermore, the point cloud conversion module is specifically used to:

[0030] Performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of equal number;

[0031] The coordinate average value of each point cloud data group is calculated, and the point cloud data are segmented according to each coordinate average value and a preset plane threshold value to obtain a point cloud image corresponding to each image information.

[0032] Furthermore, the boundary optimization module is specifically used to:

[0033] Performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images;

[0034] The least squares method is used to smooth the boundary information of each point cloud, and based on the smoothed point cloud boundary information, the boundary fitting optimization is performed on the corresponding point cloud image to obtain point cloud boundary optimization information.

[0035] Furthermore, the physical model construction module is specifically used to:

[0036] defining a symmetry axis of each of the point cloud boundary optimization information, and performing an axial rotation on the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding rotation matrix;

[0037] The point cloud boundary optimization information is inversely rotated based on the symmetry axis to obtain a corresponding inverse rotation matrix, and the rotation matrix and the inverse rotation matrix are combined to construct a symmetrical object model of each of the garments.

[0038] Furthermore, the texture optimization module is specifically used to:

[0039] Sampling all point clouds in each of the point cloud images along the corresponding contour normal direction to obtain grayscale sampling vectors corresponding to all point clouds in each of the point cloud images;

[0040] Local texture optimization is performed on each of the point cloud images according to the grayscale sampling vector to obtain a corresponding local texture optimization result.

[0041] The present invention also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned physical modeling method of virtual clothing is implemented.

[0042] The present invention also provides a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned physical modeling method of virtual clothing is implemented.

[0043] The physical modeling method, system, storage medium and computer of virtual clothing in the present invention collect image information of different types of clothing, perform point cloud conversion on the collected image information, perform point cloud projection and point cloud boundary optimization on the point cloud image, filter out background-related information from the collected image to make the outline of the object boundary smoother, perform boundary rotation on the point cloud boundary optimization information, superimpose and fit a symmetrical object model, improve modeling accuracy and modeling speed through boundary rotation, perform local texture optimization on the point cloud image, use the optimization result to optimize the symmetrical object model to improve the local texture characteristics of the clothing boundary, associate the optimized model with user needs, and thus realize the rapid construction of the physical model of the virtual clothing. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of a physical modeling method for virtual clothing in a first embodiment of the present invention;

[0045] Figure 2 is a structural block diagram of a physical modeling system for virtual clothing in a second embodiment of the present invention;

[0046] Figure 3 FIG. 4 is a structural block diagram of a computer in a third embodiment of the present invention.

[0047] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0048] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0050] Example 1

[0051] See also Figure 1 , which shows a physical modeling method for virtual clothing in a first embodiment of the present invention, and specifically includes steps S101 to S105:

[0052] S101, collecting image information of a plurality of different types of clothing, and performing point cloud conversion on each of the image information to obtain a point cloud image of each of the image information;

[0053] Furthermore, the step S101 specifically includes steps S1011 to S1012:

[0054] S1011, performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of the same number;

[0055] S1012 , calculating the coordinate average value of each point cloud data group, and performing data segmentation on each point cloud data according to each coordinate average value and a preset plane threshold value, so as to obtain a point cloud image corresponding to each image information.

[0056] During specific implementation, image acquisition equipment is used to capture images of different types of clothing to obtain image information of each clothing, wherein the image acquisition equipment includes but is not limited to cameras, depth cameras and other equipment with image acquisition functions. In this embodiment, the type of clothing includes the outline shape of the clothing after it is flattened. For example, the outline shape of a shirt after it is flattened is a silhouette that is wide at the top and narrow at the bottom, similar to the shape of the letter T. Therefore, clothing similar to shirts (for example, T-shirts) are classified as T-type, and the outline shape of a pleated skirt after it is flattened is a silhouette that is narrow at the top and wide at the bottom, similar to the shape of a trapezoid. Therefore, clothing similar to a pleated skirt is classified as a trapezoid.

[0057] Specifically, the collected image information is converted into a point cloud, and the point cloud of the image acquisition device is vertically projected onto the camera coordinate system to realize the conversion of the three-dimensional image into a two-dimensional point cloud, thereby obtaining the point cloud data of each image information;

[0058] Furthermore, since the collected image information contains background information, the point cloud data obtained above is filtered using a filter to eliminate noise points such as the background and the point cloud of the support, ensuring that the object point cloud of the clothing can be independently extracted. The processed point cloud data is randomly split into a number of point cloud data groups of the same number (in this embodiment, the number of point cloud data groups randomly split from each image information is 20 groups, with 20 point cloud data in each group), and the coordinate average value of each point cloud data group is solved. The calculated coordinate average value is compared with a preset plane threshold (in this embodiment, the plane threshold is set by the user), and points greater than the plane threshold are retained. The independent point cloud of the object can be segmented, thereby obtaining the point cloud image corresponding to each image information.

[0059] S102, performing point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images;

[0060] Furthermore, the step S102 specifically includes steps S1021 and S1022:

[0061] S1021, performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images;

[0062] S1022: Smoothing the boundary information of each point cloud using the least squares method, and performing boundary fitting optimization on the corresponding point cloud image based on the smoothed boundary information of each point cloud to obtain point cloud boundary optimization information.

[0063] In the specific implementation, the ICP registration algorithm is used to perform point cloud registration on each point cloud image, all the point clouds involved in the registration are superimposed on the point cloud of the first frame, and vertically projected onto a certain plane, and the projected point cloud boundary is extracted to obtain the point cloud boundary information corresponding to each point cloud image;

[0064] Furthermore, the least squares method is used to smooth the boundary information of each point cloud to smooth the discrete points on the surface, and the boundary fitting optimization is performed on the point cloud image corresponding to the smoothed point cloud boundary information. The error function is defined to find a set of straight line parameters that satisfies the minimum sum of the distances from all points in the initial boundary to the straight line. Assume that the coordinates of a point cloud in the point cloud boundary information are , the straight line parameters are and , the equation of the straight line is defined as , the error function is defined as , solve the error function about and Partial derivative of:

[0065] ;

[0066] Solve for parameters and Respectively with coordinates The relationship between them is used to determine the fitted boundary line, and the fitted boundary line is superimposed on the original point cloud boundary to optimize the point cloud boundary information, thereby obtaining the point cloud boundary optimization information corresponding to each point cloud image.

[0067] S103, defining a symmetry axis of each point cloud boundary optimization information, and performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment;

[0068] Furthermore, the step S103 specifically includes steps S1031 and S1032:

[0069] S1031, defining a symmetry axis of each of the point cloud boundary optimization information, and performing an axial rotation on the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding rotation matrix;

[0070] S1032: Inversely rotate the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding inverse rotation matrix, and combine the rotation matrix and the inverse rotation matrix to construct a symmetrical object model of each of the garments.

[0071] In the specific implementation, a point of the point cloud boundary information For example, define the point The symmetry axis of the corresponding point cloud boundary optimization information is Perform axial rotation to obtain another rotation point , according to connecting the point With the rotation point , and rotate it in the X-axis direction to obtain the corresponding rotation matrix ;

[0072] Click With the rotation point Rotate on the Y axis and Z axis to obtain the corresponding rotation matrix 、 After obtaining the corresponding rotation matrix, perform the inverse rotation according to the above steps. Since the matrix in the Z-axis direction remains unchanged during the rotation and inverse rotation process, two inverse rotation matrices will be obtained. as well as , combine the rotation matrix and the inverse rotation matrix to obtain the rotation matrix for any angle around the rotation axis:

[0073] ;

[0074] The unit vector defining the rotation axis is , construct the unit vector and the rotation matrix obtained above The correlation matrix is:

[0075] ;

[0076] Where, Indicates the rotation angle.

[0077] Calculation is performed every 5° rotation to obtain a number of boundary information, and the boundaries are superimposed to obtain the corresponding symmetrical object model.

[0078] S104, performing local texture optimization on each of the point cloud images, and inputting the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model;

[0079] Furthermore, the step S104 specifically includes steps S1041 and S1042:

[0080] S1041, sampling all point clouds in each point cloud image along the corresponding contour normal direction to obtain grayscale sampling vectors corresponding to all point clouds in each point cloud image;

[0081] S1042: Perform local texture optimization on each of the point cloud images according to the grayscale sampling vector to obtain a corresponding local texture optimization result.

[0082] In the specific implementation, all point clouds of each point cloud image are sampled along the corresponding contour normal direction to obtain the grayscale sampling vectors corresponding to all point clouds in the point cloud image, and local texture optimization is performed on the point cloud image according to the grayscale sampling vectors to obtain the corresponding local texture optimization results;

[0083] Specifically, taking a single point cloud as an example, a line perpendicular to the line connecting the two adjacent points is drawn through the point, i.e., the profile line. The grayscale values ​​of several pixels at both ends of the feature point are taken, and all the pixel grayscale values ​​are constructed into a corresponding grayscale sequence:

[0084] ;

[0085] Where, Indicates the In the point cloud image The grayscale sequence of points, Indicates the number of grayscale values ​​extracted;

[0086] Furthermore, the grayscale sequence is differentially processed to obtain the corresponding differential vector:

[0087] ;

[0088] Among them, the length of the difference vector is ;

[0089] The obtained difference vector is normalized to obtain a normalized difference vector:

[0090] ;

[0091] Further, calculate the first The average of the normalized difference vectors:

[0092] ;

[0093] Where, Indicates the number of all point cloud images;

[0094] Calculate the covariance matrix of the above means:

[0095] ;

[0096] The covariance matrix is ​​input into the symmetrical object model obtained above to perform model optimization to obtain the corresponding optimized object model.

[0097] S105, obtaining corresponding user needs based on the types of each of the clothing, constructing a corresponding demand library based on the user needs and the design parameters corresponding to the types of the clothing, using the demand library and the optimized object model to perform model fusion, and using the fused model to realize physical modeling of virtual clothing data.

[0098] In specific implementation, the corresponding user needs are obtained based on the type of clothing. For example, user needs for sportswear are usually comfort and lightness. User needs also include clothing color, clothing fabric, clothing pattern, etc. All user needs are mapped with the corresponding clothing types to build a corresponding demand library. The demand library is then fused with the optimized object model, and the fused model is used to realize physical modeling of virtual clothing data.

[0099] Specifically, the fused model is used for virtual rendering, and the data related to user needs is extracted from the virtual clothing data. After rendering, it is used as the main rendering condition for virtual wearing, and the obtained wearing results are stored to form a physical model corresponding to the virtual clothing data.

[0100] In summary, the physical modeling method of virtual clothing in the above-mentioned embodiment of the present invention collects image information of different types of clothing, performs point cloud conversion on the collected image information, performs point cloud projection and point cloud boundary optimization on the point cloud image, filters out background-related information from the collected image, makes the outline of the object boundary smoother, rotates the point cloud boundary optimization information, and superimposes and fits a symmetrical object model, improves modeling accuracy and modeling speed through boundary rotation, performs local texture optimization on the point cloud image, and uses the optimization result to optimize the symmetrical object model to improve the local texture characteristics of the clothing boundary, and associates the optimized model with user needs, thereby realizing the rapid construction of the physical model of the virtual clothing.

[0101] Example 2

[0102] Another aspect of the present invention is to provide a physical modeling system for virtual clothing. Figure 2 , which shows a physical modeling system for virtual clothing in a second embodiment of the present invention, the system includes:

[0103] The point cloud conversion module 11 is used to collect image information of a plurality of different types of clothing and perform point cloud conversion on each of the image information to obtain a point cloud image of each of the image information;

[0104] A boundary optimization module 12 is used to perform point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images;

[0105] An object model construction module 13 is used to define a symmetry axis of each point cloud boundary optimization information, and perform boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment;

[0106] The texture optimization module 14 is used to perform local texture optimization on each of the point cloud images, and input the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model;

[0107] The physical modeling module 15 is used to obtain corresponding user needs based on the types of each of the clothing, construct a corresponding demand library based on the user needs and the design parameters corresponding to the type of clothing, use the demand library and the optimized model to perform model fusion, and use the fused model to realize physical modeling of virtual clothing data.

[0108] Furthermore, the point cloud conversion module 11 is specifically used to:

[0109] Performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of equal number;

[0110] The coordinate average value of each point cloud data group is calculated, and the point cloud data are segmented according to each coordinate average value and a preset plane threshold value to obtain a point cloud image corresponding to each image information.

[0111] Furthermore, the boundary optimization module 12 is specifically configured to:

[0112] Performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images;

[0113] The least squares method is used to smooth the boundary information of each point cloud, and based on the smoothed point cloud boundary information, the boundary fitting optimization is performed on the corresponding point cloud image to obtain point cloud boundary optimization information.

[0114] Furthermore, the object model building module 13 is specifically used to:

[0115] defining a symmetry axis of each of the point cloud boundary optimization information, and performing an axial rotation on the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding rotation matrix;

[0116] The point cloud boundary optimization information is inversely rotated based on the symmetry axis to obtain a corresponding inverse rotation matrix, and the rotation matrix and the inverse rotation matrix are combined to construct a symmetrical object model of each of the garments.

[0117] Furthermore, the texture optimization module 14 is specifically configured to:

[0118] Sampling all point clouds in each of the point cloud images along the corresponding contour normal direction to obtain grayscale sampling vectors corresponding to all point clouds in each of the point cloud images;

[0119] Local texture optimization is performed on each of the point cloud images according to the grayscale sampling vector to obtain a corresponding local texture optimization result.

[0120] The functions or operation steps implemented when the above modules and units are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0121] The implementation principle and technical effects of the physical modeling system for virtual clothing provided in the embodiment of the present invention are the same as those of the aforementioned method embodiment. For the sake of brief description, any matters not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0122] Example 3

[0123] The present invention also provides a computer, see Figure 3 , shown is a computer in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned physical modeling method of virtual clothing is implemented.

[0124] The memory 10 includes at least one type of storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 10 may be an internal storage unit of a computer, such as the computer's hard disk. In other embodiments, the memory 10 may also be an external storage device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the memory 10 may include both an internal storage unit of the computer and an external storage device. The memory 10 can be used not only to store application software installed in the computer and various types of data, but also to temporarily store data that has been output or is about to be output.

[0125] Among them, in some embodiments, the processor 20 can be an electronic control unit (Electronic Control Unit, abbreviated as ECU, also known as a vehicle computer), a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, used to run the program code stored in the memory 10 or process data, such as executing access restriction programs.

[0126] It should be pointed out that Figure 3 The structure shown does not constitute a limitation of the computer. In other embodiments, the computer may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0127] An embodiment of the present invention further provides a storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned physical modeling method for virtual clothing.

[0128] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0129] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting, or processing it in another suitable manner as necessary, and then storing it in a computer memory.

[0130] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0131] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A physical modeling method for virtual clothing, characterized in that: include: Collecting image information of a plurality of different types of clothing, and performing point cloud conversion on each of the image information to obtain a point cloud image of each of the image information; Performing point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images; defining a symmetry axis of each point cloud boundary optimization information, and performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment; Performing local texture optimization on each of the point cloud images, and inputting the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model; Based on the types of each of the clothing, corresponding user needs are obtained, and a corresponding demand library is constructed based on the user needs and the design parameters corresponding to the types of clothing. The demand library is used to fuse the model with the optimized object model, and the fused model is used to realize physical modeling of virtual clothing data.

2. The physical modeling method of virtual clothing according to claim 1, characterized in that: The steps of collecting image information of a plurality of different types of clothing and performing point cloud conversion on each of the image information to obtain a point cloud image of each of the image information include: Performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of equal number; The coordinate average value of each point cloud data group is calculated, and the point cloud data are segmented according to each coordinate average value and a preset plane threshold value to obtain a point cloud image corresponding to each image information.

3. The physical modeling method of virtual clothing according to claim 1, characterized in that: The step of performing point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images includes: Performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images; The least squares method is used to smooth the boundary information of each point cloud, and based on the smoothed point cloud boundary information, the boundary fitting optimization is performed on the corresponding point cloud image to obtain point cloud boundary optimization information.

4. The physical modeling method of virtual clothing according to claim 1, characterized in that: The steps of defining a symmetry axis of each point cloud boundary optimization information and performing boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment include: defining a symmetry axis of each of the point cloud boundary optimization information, and performing an axial rotation on the point cloud boundary optimization information based on the symmetry axis to obtain a corresponding rotation matrix; The point cloud boundary optimization information is inversely rotated based on the symmetry axis to obtain a corresponding inverse rotation matrix, and the rotation matrix and the inverse rotation matrix are combined to construct a symmetrical object model of each of the garments.

5. The physical modeling method of virtual clothing according to claim 1, characterized in that: The step of performing local texture optimization on each of the point cloud images includes: Sampling all point clouds in each of the point cloud images along the corresponding contour normal direction to obtain grayscale sampling vectors corresponding to all point clouds in each of the point cloud images; Local texture optimization is performed on each of the point cloud images according to the grayscale sampling vector to obtain a corresponding local texture optimization result.

6. A physical modeling system for virtual clothing, characterized in that: include: A point cloud conversion module is used to collect image information of a plurality of different types of clothing and perform point cloud conversion on each of the image information to obtain a point cloud image of each of the image information; A boundary optimization module, configured to perform point cloud projection and point cloud boundary optimization on each of the point cloud images to obtain point cloud boundary optimization information corresponding to each of the point cloud images; an object model construction module, configured to define a symmetry axis of each point cloud boundary optimization information, and perform boundary rotation on the point cloud boundary optimization information based on the symmetry axis to construct a symmetrical object model of each garment; a texture optimization module, configured to perform local texture optimization on each of the point cloud images, and input the obtained local texture optimization results into the symmetrical object model for model optimization to obtain a corresponding optimized object model; The physical modeling module is used to obtain corresponding user needs based on the type of each clothing, construct a corresponding demand library based on the user needs and the design parameters corresponding to the type of clothing, use the demand library and the optimized model to perform model fusion, and use the fused model to realize physical modeling of virtual clothing data.

7. The physical modeling system of virtual clothing according to claim 6, characterized in that: The point cloud conversion module is specifically used for: Performing point cloud conversion on each of the image information, and randomly splitting the point cloud data of each of the image information into a plurality of point cloud data groups of equal number; The coordinate average value of each point cloud data group is calculated, and the point cloud data are segmented according to each coordinate average value and a preset plane threshold value to obtain a point cloud image corresponding to each image information.

8. The physical modeling system of virtual clothing according to claim 6, characterized in that: The boundary optimization module is specifically used for: Performing point cloud projection and point cloud boundary extraction on each of the point cloud images to obtain point cloud boundary information corresponding to each of the point cloud images; The least squares method is used to smooth the boundary information of each point cloud, and based on the smoothed point cloud boundary information, the boundary fitting optimization is performed on the corresponding point cloud image to obtain point cloud boundary optimization information.

9. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the physical modeling method of virtual clothing according to any one of claims 1 to 5 is implemented.

10. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the physical modeling method of virtual clothing according to any one of claims 1 to 5 is implemented.

Images