Data processing methods and apparatus, computer equipment and computer-readable storage media

By recognizing two-dimensional human postures and assigning physical properties to fabrics, the problem of low efficiency in virtual try-on has been solved, achieving an efficient and realistic virtual try-on experience.

CN114556402BActive Publication Date: 2026-11-17程立苇
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202080061120.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2019-09-03
Filing Date
2020-09-03
Publication Date
2026-11-17
Estimated Expiration
2040-09-03

AI Technical Summary

Technical Problem

Existing virtual try-on technology suffers from low efficiency and poor user experience due to the inefficiency of 3D modeling.

Method used

By acquiring image data of dressed human bodies, recognizing two-dimensional human postures, and matching preset human body parts in a human posture database, the physical properties of the fabric of the garment to be tested are directly assigned, avoiding the need to construct three-dimensional human and clothing models.

Benefits of technology

It improves the efficiency and user experience of virtual try-on, reduces computing resource consumption, and enhances the realism and efficiency of try-on.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114556402B_ABST
    Figure CN114556402B_ABST
Patent Text Reader

Abstract

This invention discloses a data processing method and apparatus, a computer device, and a computer-readable storage medium. The method includes: acquiring human image data; identifying the human's two-dimensional posture based on the image data; comparing the identified two-dimensional posture with a posture database to determine a preset part of the two-dimensional posture; and assigning the parts of the preset part of the two-dimensional posture covered by the original clothing the attributes of the garment to be tested. This invention can greatly improve the efficiency of data processing, thereby improving the user experience.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] This application claims priority to Chinese Patent Application No. 201910827228.0, filed on September 3, 2019, entitled "Virtual Fitting Method and Apparatus, Computer Equipment and Computer Equipment Storage Medium", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This invention relates to the field of computer technology, and more particularly to data processing methods and apparatus, computer equipment, and computer equipment storage media. Background Technology

[0003] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0004] With the development of computer technology, virtual try-on technology has gradually gained attention and recognition from many consumers. Virtual try-on refers to the act of trying on virtual clothes in a virtual space using an avatar identical to oneself. Virtual try-on does not require users to actually change clothes, yet it achieves the effect of wearing a particular garment. The emergence of virtual try-on technology provides users with a convenient and quick try-on experience, significantly changing traditional methods of clothing fitting.

[0005] However, current virtual try-on methods require collecting 3D human body data to construct a 3D human body model, and also constructing a 3D clothing model. These two models are then merged to achieve the desired 3D try-on effect. However, both constructing the 3D human body model and the 3D clothing model consume significant computer resources, resulting in extremely low efficiency. This hinders the batch creation of 3D human body and clothing models, causing users to spend a considerable amount of time on virtual try-ons, leading to inefficiency and a significantly reduced user experience.

[0006] Therefore, existing virtual try-on systems suffer from low efficiency and poor user experience due to 3D modeling issues. Summary of the Invention

[0007] This invention provides a data processing method to improve the efficiency of virtual try-on and enhance user experience. The method includes:

[0008] Image data including a dressed human body is acquired through an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device.

[0009] The two-dimensional human posture of the dressed human body is identified based on the image data; the two-dimensional human posture reflects the projection data of the three-dimensional human body on a second plane; the second plane is the plane of symmetry between the front and back of the dressed human body.

[0010] The identified two-dimensional human poses are matched with a human pose database to determine the preset human body parts of the two-dimensional human poses.

[0011] The parts of the two-dimensional human body that are covered by the original clothing are assigned the physical properties of the fabric of the clothing to be tested.

[0012] This invention also provides a data processing device for improving the efficiency of virtual try-on and enhancing user experience. The device includes:

[0013] The image data acquisition module is used to acquire image data including a dressed human body through an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device.

[0014] The posture recognition module is used to recognize the two-dimensional human posture of a dressed human body based on image data; the two-dimensional human posture reflects the projection data of the three-dimensional human body on a second plane; the second plane is the symmetrical plane between the front and back of the dressed human body.

[0015] The pose matching module is used to match the recognized two-dimensional human pose with the human pose database to determine the preset human body parts of the two-dimensional human pose.

[0016] The virtual try-on module is used to assign the physical properties of the fabric of the garment to the parts of a two-dimensional human body that are covered by the original clothing in a preset human body posture.

[0017] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described data processing method.

[0018] This invention also provides a computer-readable storage medium storing a computer program that performs the above-described data processing method.

[0019] In this embodiment of the invention, image data including a dressed human body is acquired using an image acquisition device; then, the two-dimensional human posture of the dressed human body is identified based on the image data; and a preset human body part for the two-dimensional human posture is determined by matching in a human posture database. Finally, the physical properties of the fabric of the garment to be tested are directly assigned to the preset human body parts covered by the original clothing. This embodiment of the invention eliminates the need to construct a three-dimensional human body model or clothing model; it only requires identifying the two-dimensional human posture of the dressed human body and directly assigning the physical properties of the fabric of the garment to be tested to the preset human body parts covered by the original clothing. This greatly improves the efficiency of data processing and thus enhances the user experience. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0021] Figure 1 A flowchart illustrating the implementation of the data processing method provided in this embodiment of the invention;

[0022] Figure 2 A side view showing the position of the image acquisition device relative to the first plane according to an embodiment of the present invention;

[0023] Figure 3 A top view showing the positions of the first and second planes as provided in an embodiment of the present invention;

[0024] Figure 4 A two-dimensional human posture diagram provided for an embodiment of the present invention (the center line of the field of view is perpendicular to the second plane);

[0025] Figure 5 This is another implementation flowchart of the data processing method provided in the embodiments of the present invention;

[0026] Figure 6 A two-dimensional basic human posture diagram provided for an embodiment of the present invention (the center line of the field of vision is perpendicular to the first plane);

[0027] Figure 7 This is a flowchart illustrating the implementation of step 504 in the data processing method provided in this embodiment of the invention.

[0028] Figure 8 A schematic diagram illustrating how the data of the garment to be tested over the original garment data for the arm area, as provided in an embodiment of the present invention.

[0029] Figure 9(a) is a schematic diagram showing the torso data of the garment to be tested covering the original garment data according to an embodiment of the present invention.

[0030] Figure 9(b) is another schematic diagram showing the torso data of the garment to be tested covering the original garment data, provided in an embodiment of the present invention.

[0031] Figure 10 This is another implementation flowchart of step 504 in the data processing method provided in the embodiment of the present invention;

[0032] Figure 11 A schematic diagram illustrating the stretching and rebound of the garment data for the arm area provided in an embodiment of the present invention;

[0033] Figure 12 A schematic diagram of the stretching and rebound of the torso garment data provided in an embodiment of the present invention;

[0034] Figure 13 A flowchart illustrating another implementation of step 504 in the data processing method provided in this embodiment of the invention;

[0035] Figure 14 This is another implementation flowchart of step 504 in the data processing method provided in the embodiment of the present invention;

[0036] Figure 15 A functional block diagram of a data processing apparatus provided in an embodiment of the present invention;

[0037] Figure 16 This is another functional block diagram of the data processing apparatus provided in an embodiment of the present invention;

[0038] Figure 17 This is a structural block diagram of the clothing data overlay module 1604 in the data processing device provided in an embodiment of the present invention;

[0039] Figure 18 This is another structural block diagram of the clothing data overlay module 1604 in the data processing device provided in this embodiment of the invention;

[0040] Figure 19 Another structural block diagram of the clothing data overlay module 1604 in the data processing device provided in the embodiment of the present invention;

[0041] Figure 20 This is another structural block diagram of the clothing data overlay module 1604 in the data processing device provided in the embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0043] Figure 1 The implementation flow of the data processing method provided in the embodiment of the present invention is illustrated. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0044] like Figure 1 As shown, the data processing method includes:

[0045] Step 101: Acquire image data including a dressed human body using an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device.

[0046] Step 102: Identify the two-dimensional human posture of the dressed human body based on the image data; the two-dimensional human posture reflects the projection data of the three-dimensional human body on the second plane; the second plane is the symmetrical plane between the front and back of the dressed human body.

[0047] Step 103: Match the identified two-dimensional human pose with the human pose database to determine the preset human body parts of the two-dimensional human pose.

[0048] Step 104: Assign the physical properties of the fabric of the garment to be tested to the parts of the two-dimensional human body that are covered by the original clothing in the preset human body parts.

[0049] In this embodiment of the invention, the image acquisition device may be, for example, a regular camera capable of acquiring a single frame image, a depth camera, or a video camera capable of acquiring video images. Correspondingly, the image data may include RGB data, and may also include RGBD data (RGB data and depth data of the dressed human body at the depth camera). That is, step 101, acquiring image data including the dressed human body through the image acquisition device, includes: acquiring RGB data including the dressed human body through a camera, or acquiring RGBD data including the dressed human body through a depth camera.

[0050] In addition, when the image acquisition device is a camera, the video images captured by the camera can be converted into single-frame images first, and then each frame image including the dressed human body can be obtained.

[0051] The clothing-clad human body can be a person wearing clothes, a clothing display mannequin, or a human skeleton or clothes hanger, etc. This embodiment of the invention does not impose any special limitations on this.

[0052] Figure 2The diagram shows a side view illustrating the position of the image acquisition device and the first plane according to an embodiment of the present invention. For ease of description, only the parts relevant to the embodiment of the present invention are shown, and are detailed below:

[0053] like Figure 2 As shown, the first plane is perpendicular to the center line of the field of view of the image acquisition device. Preferably, the image acquisition device is located in the middle area near the top of the virtual fitting terminal, which may include, for example, a smart virtual fitting mirror, or other fitting terminals including a display screen. The first plane is parallel to the plane on which the virtual fitting terminal is located, and the front of the dressed human body faces the virtual fitting terminal, etc. The image data including the dressed human body obtained by the image acquisition device reflects the projection of the three-dimensional human body onto the first plane.

[0054] Figure 3 This diagram illustrates the positions of the first and second planes provided in an embodiment of the present invention (top view). Figure 4 A two-dimensional human posture illustration provided by an embodiment of the present invention is shown (the center line of the field of view is perpendicular to the second plane). For ease of description, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0055] like Figure 3 and Figure 4 As shown, in Figure 3 Viewed from a top-down angle, the width range of the three-dimensional human body projected onto the second plane is S. Figure 4 Viewing the human body from an angle where the center line of the field of vision is perpendicular to the second plane, the three-dimensional human body is projected onto the second plane as follows: Figure 4 The two-dimensional human posture shown.

[0056] In this context, the first plane and the second plane can be parallel planes, the same plane, or different planes. When the first plane and the second plane are parallel planes, the projection of the 3D human body onto the second plane is identical to the projection of the 3D human body onto the first plane; that is, the projections of the 3D human body onto the second plane and the projections of the 3D human body onto the first plane are completely identical in size and posture. When the first plane and the second plane are the same plane, the projection of the 3D human body onto the second plane is the same as the projection of the 3D human body onto the first plane.

[0057] In most cases, such as Figure 3 As shown, the first plane and the second plane are not parallel planes, or are not the same plane. In this case, there is an angle θ between the first plane and the second plane (i.e., the dressed human body is tilted in front of the virtual fitting terminal). The image data of the dressed human body acquired by the image acquisition device is the projection data of the three-dimensional human body on the first plane. The width range of this projection data is L, and based on geometric principles, we can obtain:

[0058]

[0059] Furthermore, based on this geometric relationship and the projection data of the dressed human body on the first plane, the projection data of the dressed human body on the second plane can be determined, thereby identifying the two-dimensional human posture of the dressed human body on the second plane.

[0060] After obtaining image data of the dressed human body, the two-dimensional human pose of the dressed human body is identified based on the obtained image data. Preferably, when the acquired image data is RGBD data (RGB data and depth data of the dressed human body from the depth camera), the two-dimensional human pose of the dressed human body can be identified through the following steps.

[0061] First, the depth values ​​are extracted from the current RGBD image data, and the pixels corresponding to similar RGBD depth values ​​at close locations are clustered and combined.

[0062] Furthermore, a human pose database is invoked to perform human figure detection on the aforementioned pixel combinations. Specifically, each pixel combination is matched one by one with different human pose models in the human pose database (starting from the T-pose basic human model), selecting human poses in the database that are similar to the pixel combinations. If the similarity is low or there are no similar parts, the preset similarity standard for the depth values ​​of similar positions in the RGBD image is lowered, and the image pixels are re-clustered and combined, and matched one by one again with different human pose models in the human pose database (starting from the T-pose basic human model). This process continues until the similarity between the pixel combination of the current image and a certain human pose model in the human pose database is not less than the preset similarity, at which point the human pose model in the human pose database is determined as the human pose of the currently dressed person.

[0063] Next, for the selected human posture model (parallel to the second plane), the joints and skeletal lines are drawn to make it an objective human marker like a "stick figure". The joints are calibrated, the human body boundary is delineated, and then the two-dimensional human posture of the dressed human body containing the skeletal point position information is obtained, that is, the three-dimensional human posture projection data on the second plane.

[0064] Preferably, when the acquired image data is RGB data, the two-dimensional human posture of the dressed human body can be identified through the following steps.

[0065] First, the current RGB image data is extracted, and pixels corresponding to similar positions and colors are clustered and combined. Further, facial recognition technology is used to determine the approximate location of the human body. Then, a human pose database is accessed to perform human detection on the pixel combinations. Specifically, each pixel combination is matched against different human pose models in the human pose database (starting from the T-pose basic human model), selecting human poses in the database that are similar to the pixel combinations. If the similarity is low or there are no similar parts, the preset similarity standard for colors in similar positions in the RGB image is lowered, and the image pixels are re-clustered and combined, and again matched against different human pose models in the human pose database (starting from the T-pose basic human model). This process continues until the similarity between the pixel combination of the current image and a certain human pose model in the human pose database is not less than a preset similarity; at this point, the human pose model in the human pose database is determined to be the human pose of the currently dressed person.

[0066] Next, for the selected human posture model (parallel to the second plane), the joints and skeletal lines are drawn to make it an objective human marker like a "stick figure". The joints are calibrated, the human body boundary is delineated, and then the two-dimensional human posture of the dressed human body containing the skeletal point position information is obtained, that is, the three-dimensional human posture projection data on the second plane.

[0067] In summary, the two-dimensional human posture of the dressed human is the projection data of the three-dimensional human body onto a second plane. When defining the second plane, the human body can be approximated as a symmetrical structure; the second plane is defined as the plane of symmetry between the front and back of the human body. That is, this embodiment of the invention does not require constructing a three-dimensional human body model or a three-dimensional clothing model, but directly obtains the two-dimensional human posture of the three-dimensional human body on a plane, and then uses this two-dimensional human posture for virtual try-on, which can greatly improve the efficiency of virtual try-on and enhance the user experience.

[0068] Human pose recognition can identify the boundary range of a two-dimensional human pose in image data, that is, it delineates and identifies the boundary range of the human body. However, it cannot identify the poses of individual parts of the human body, such as the head, arms, torso, and legs. Therefore, based on the identification of the two-dimensional human pose, the two-dimensional human pose is matched against a human pose database to determine the poses of preset human body parts within the two-dimensional human pose, thereby improving the accuracy and realism of virtual try-on.

[0069] The preset human body part refers to a pre-defined human body part. As those skilled in the art will understand, the preset human body part may include one or more of the head, arms, torso, and legs. For example, it may only include the arms and torso (when virtually trying on a top), or it may only include the legs (when virtually trying on pants or skirts). This embodiment of the invention does not impose any particular limitation on this.

[0070] In addition, the human pose database is a pre-trained database of human poses using deep learning frameworks such as TensorFlow. This database contains a large number, even massive amounts, of different two-dimensional human poses. TensorFlow, Google's second-generation artificial intelligence learning system, transmits complex data structures to artificial intelligence neural networks for analysis and processing. It can be used in various machine learning and deep learning fields such as speech recognition and image recognition, and supports convolutional neural networks, recurrent neural networks, and long short-term memory networks.

[0071] Next, the identified 2D human pose of the dressed person is matched with a human pose database to determine the data set and pose of each preset human body part in the 2D human pose. Preferably, this can be achieved through the following method:

[0072] First, while recognizing the two-dimensional human posture, the skeletal point positions of each preset human body part in the two-dimensional human posture can be identified. Then, combined with the boundary data of the two-dimensional human posture, the data set of each preset human body part in the two-dimensional human posture can be determined, such as the head data set, the torso data set, the leg data set, etc.

[0073] Furthermore, in order to improve the accuracy of pose recognition for each preset human body part in two-dimensional human pose, the data of each preset human body part are combined and clustered, and data parts with similar colors are combined to further determine the details of each preset human body part, such as the upper arm and lower arm, elbow joint and finger joint of the arm part; and the knee joint, thigh and calf of the leg part.

[0074] In addition, to further improve the accuracy of posture recognition for each preset human body part in the two-dimensional human posture, the orientation and angle of the two-dimensional human posture in the human posture database that are inconsistent with the orientation and angle of the recognized two-dimensional human posture are rotated and transformed. That is, the orientation and angle of the two-dimensional human posture in the human posture database are adjusted to a position that is basically consistent with the orientation and angle of the recognized two-dimensional human posture, and then matching is performed.

[0075] After determining the data sets of each preset human body part in the two-dimensional human posture (for ease of description, let's assume the two-dimensional human posture is represented by A0), the data sets of each preset human body part in the two-dimensional human posture A0 are matched with the two-dimensional human postures in the human posture database. When the similarity between the data sets of each preset human body part in the two-dimensional human posture A0 and each preset human body part of a certain two-dimensional human posture A1 in the human posture database is not less than a preset similarity, the two-dimensional human posture A1 in the human posture database is determined as a matching two-dimensional human posture. Then, based on the postures of each preset human body part in the two-dimensional human posture A1 in the human posture database, the postures of each preset human body part in the two-dimensional human posture A0 are determined.

[0076] After determining the data set and posture of each preset human body part in the two-dimensional human body posture, the parts of each human body part covered by the original clothing are directly assigned the physical properties of the fabric of the clothing to be tried on, so as to perform virtual try-on operation.

[0077] Among them, the physical properties of the fabric refer to the maximum and minimum variable distance (stretch scale) between two adjacent pixels in the fabric. The physical properties of the fabric of each garment to be tested and the original garment worn by the human body are known and pre-prepared data. When assigning physical properties to the fabric of the garment, it can be done by receiving user instructions (e.g., the user enters instructions by clicking, or the physical properties of the fabric of the garment are pre-coded and the instructions are entered by entering the number of the physical properties of the fabric of the garment).

[0078] Alternatively, high-definition cameras can be used to acquire the physical properties of clothing fabrics, creating a database of all clothing fabric physical properties. The resolution of high-definition cameras is generally not limited, ranging from 460x320 to 4K, 8K, 16K, etc., with the maximum limit determined by the hardware. Alternatively, machine learning can be used to acquire the physical properties of clothing fabrics, creating a database of all clothing fabric physical properties. When assigning physical properties to clothing, the properties of the garment to be tested can be determined from the database.

[0079] In this embodiment of the invention, image data including a dressed human body is acquired through an image acquisition device; then, the two-dimensional human posture of the dressed human body is identified based on the image data; and a preset human body part of the two-dimensional human posture is determined by matching in a human posture database. Finally, the physical properties of the fabric of the garment to be tried on are directly assigned to the parts of the preset human body parts of the two-dimensional human posture that are covered by the original clothing. This embodiment of the invention does not require the construction of a three-dimensional human body model or clothing model; it only needs to identify the two-dimensional human posture of the dressed human body and directly assign the physical properties of the fabric of the garment to be tried on to the preset human body parts of the two-dimensional human posture that are covered by the original clothing. This can greatly improve the efficiency of virtual try-on and thus improve the user experience.

[0080] Figure 5 Another implementation flow of the data processing method provided in the embodiment of the present invention is shown. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0081] In one embodiment of the present invention, such as Figure 5 As shown above, in the above Figure 1 Based on the steps shown, the data processing method also includes:

[0082] Step 501: Based on the basic two-dimensional human body posture, determine the posture changes of each preset human body part in the two-dimensional human body posture; the basic two-dimensional human body posture is the projection data of the three-dimensional basic human body model on the first plane.

[0083] Step 502: Assign the physical properties of the original clothing to the preset human body parts covered by the original clothing in the two-dimensional human body pose to form the original clothing data.

[0084] Step 503: Assign the physical properties of the fabric of the garment to the preset human body parts covered by the garment to be tested in the basic two-dimensional human body posture to form the garment data.

[0085] Step 504: Based on the posture changes of each preset human body part in the two-dimensional human posture, the original clothing data of each preset human body part in the two-dimensional human posture is overwritten with the clothing data of each preset human body part in the two-dimensional human posture to form a two-dimensional human posture containing clothing data.

[0086] In this embodiment of the invention, there exists a three-dimensional basic human body model, which is a standard T-pose model. In the standard T-pose three-dimensional basic human body model, both arms are raised horizontally and perpendicular to the shoulders, resembling a T shape, hence the name T-pose model. The two-dimensional basic human body posture is the projection data of the T-pose three-dimensional basic human body model onto a first plane.

[0087] Figure 6A schematic diagram of a two-dimensional human body basic posture provided by an embodiment of the present invention is shown (the center line of the field of view is perpendicular to the first plane). For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0088] like Figure 6 As shown in the figure, the human posture shown is the projection data of the T-pose three-dimensional basic human body model on the first plane, that is, the two-dimensional basic human posture.

[0089] To improve the realism of virtual try-on, the following steps are first taken based on the basic posture of the two-dimensional human body to determine... Figure 4 The pose changes of each preset human body part in the two-dimensional human body pose shown in the figure lay the foundation for subsequent coverage of the physical properties of the fabric and virtual try-on.

[0090] Since the physical properties of the fabric of the garment to be tried on are directly assigned to the preset human body parts covered by the original garment in a two-dimensional human pose, the realism of virtual try-on will be compromised. In order to improve the realism of virtual try-on, the physical properties of the fabric of the garment to be tried on can be used to cover the physical properties of the fabric of the original garment.

[0091] Specifically, in a two-dimensional human body pose, the preset human body parts covered by the original clothing are directly assigned the physical properties of the original clothing fabric, forming the original clothing data; while in a two-dimensional human body base pose, the preset human body parts covered by the clothing to be tested are assigned the physical properties of the clothing to be tested fabric, forming the clothing to be tested data.

[0092] After determining the original clothing data in the two-dimensional human body pose and the clothing data to be tried in the two-dimensional human body basic pose, the posture changes of each preset human body part in the two-dimensional human body pose are then adjusted according to the posture changes of each preset human body part in the two-dimensional human body pose. For example, the posture of each preset human body part in the two-dimensional human body basic pose is adjusted to be consistent with the posture of each preset human body part in the two-dimensional human body pose. The clothing data to be tried in each preset human body part in the two-dimensional human body basic pose is then used to cover the original clothing data of each preset human body part in the two-dimensional human body pose. That is, different human body parts are covered separately, and finally a two-dimensional human body pose containing the clothing data to be tried is formed to complete the virtual try-on operation.

[0093] In this embodiment of the invention, the posture changes of each preset human body part in the two-dimensional human body posture are determined based on the basic posture of the two-dimensional human body. The preset human body parts covered by the original clothing in the two-dimensional human body posture are assigned the physical properties of the original clothing to form the original clothing data. The preset human body parts covered by the clothing to be tried in the basic posture of the two-dimensional human body are assigned the physical properties of the clothing to be tried to form the clothing to be tried data. Then, according to the posture changes of each preset human body part in the two-dimensional human body posture, the clothing to be tried data of each preset human body part in the basic posture of the two-dimensional human body is used to cover the original clothing data of each preset human body part in the two-dimensional human body posture, which can improve the realism of virtual try-on.

[0094] Figure 7 The implementation flow of step 504 in the data processing method provided by the embodiment of the present invention is shown. For ease of description, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0095] In one embodiment of the present invention, the preset human body parts include the arms and torso. For example... Figure 7 As shown, step 504 involves, based on the posture changes of each preset human body part in the two-dimensional human pose, overwriting the original clothing data of each preset human body part in the two-dimensional human pose with the clothing data to be tested for each preset human body part in the two-dimensional human pose, thereby forming a two-dimensional human pose containing the clothing data to be tested, including:

[0096] Step 701: Based on the posture changes of the arm part in the two-dimensional human body posture, cover the original clothing data of the arm part in the two-dimensional human body posture with the clothing data to be tested in the basic two-dimensional human body posture to form an arm part containing the clothing data to be tested; wherein, the first preset vertex and the first preset boundary of the clothing data to be tested in the arm part in the basic two-dimensional human body posture coincide with the first preset vertex and the first preset boundary of the original clothing data of the arm part in the two-dimensional human body posture, or the second preset boundary and the center of the second preset boundary of the clothing data to be tested in the arm part in the basic two-dimensional human body posture coincide with the second preset boundary and the center of the second preset boundary of the original clothing data of the arm part in the two-dimensional human body posture.

[0097] Step 702: Overlay the original clothing data of the torso position in the two-dimensional human body basic posture with the clothing data to be tested in the torso position, forming a torso position containing the clothing data to be tested; wherein, the third preset vertex and the third preset boundary of the clothing data to be tested in the torso position in the two-dimensional human body basic posture coincide with the third preset vertex and the third preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture, or the fourth preset boundary and the center of the fourth preset boundary of the clothing data to be tested in the torso position in the two-dimensional human body basic posture coincide with the fourth preset boundary and the center of the fourth preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture.

[0098] In this embodiment of the invention, the preset human body parts include the arms and torso (i.e., applicable when the garment to be tested is an upper garment).

[0099] Figure 8 This illustration shows the coverage of the original clothing data with the arm area data provided in an embodiment of the present invention. For ease of description, only the parts relevant to the embodiment of the present invention are shown, and are detailed below:

[0100] like Figure 8 As shown, when using the data of the garment to be tested to cover the original garment data for the arm part, the posture of the arm part in the basic posture of the two-dimensional human body containing the data of the garment to be tested is adjusted to be consistent with the posture of the arm part in the posture of the two-dimensional human body containing the original garment data, based on the posture change of the arm part in the two-dimensional human body posture. Then, the data of the garment to be tested for the arm part covers the original garment data of the arm part, thus forming the arm part containing the data of the garment to be tested.

[0101] like Figure 8 As shown (using the right arm as an example, the left arm is similar), the first preset vertex is the upper vertex of the contact point between the arm and the torso. In the basic 2D human posture, the first preset vertex of the clothing data to be tried on in the arm is A1, and the first preset vertex of the original clothing data in the arm is A2. The first preset boundary is the upper boundary of the arm. In the basic 2D human posture, the first preset boundary of the clothing data to be tried on in the arm is P1, and the first preset boundary of the original clothing data in the arm is P2. Specifically, during the overlay process, the first preset vertex A1 of the clothing data to be tried on in the arm coincides with the first preset vertex A2 of the original clothing data in the arm, and the first preset boundary P1 of the clothing data to be tried on in the arm coincides with the first preset boundary P2 of the original clothing data in the arm, thus completing the overlay. In this embodiment of the invention, the overlay is performed by coinciding with the first preset vertex and the first preset boundary, which can further improve the realism of the virtual try-on.

[0102] In addition, the first preset vertex can be any other vertex besides the aforementioned vertex A1 (A2), and the first preset boundary can be any other boundary besides the aforementioned boundary P1 (P2). This embodiment of the invention does not impose any special restrictions on this.

[0103] In this embodiment of the invention, the virtual try-on is further improved by covering the first preset vertex and first preset boundary of the clothing data to be tried on the arm area with the first preset vertex and first preset boundary of the original clothing data on the arm area.

[0104] In one embodiment of the present invention, the second preset boundary is the upper boundary of the arm area (consistent with the first preset boundary mentioned above). The second preset boundary of the clothing data to be tried on in the arm area of ​​the basic two-dimensional human posture is P1, and the second preset boundary of the original clothing data in the arm area of ​​the two-dimensional human posture is P2. Specifically, during the overlay process, the second preset boundary P1 of the clothing data to be tried on in the arm area of ​​the basic two-dimensional human posture coincides with the second preset boundary P2 of the original clothing data in the arm area of ​​the two-dimensional human posture, and the centers of the second preset boundary P1 and the second preset boundary P2 coincide (not shown in the figure). In this embodiment of the present invention, overlaying with the second preset boundary and its center coinciding further improves the realism of the virtual try-on.

[0105] In addition, the second preset boundary can also be any other boundary besides the aforementioned boundary P1 (P2), and the embodiments of the present invention do not impose any special restrictions on this.

[0106] In this embodiment of the invention, the virtual try-on is further improved by covering the second preset boundary and the center of the second preset boundary of the clothing data to be tried on the arm area with the second preset boundary and the center of the second preset boundary of the original clothing data on the arm area.

[0107] Figure 9(a) illustrates a schematic diagram of the torso area clothing data covering the original clothing data provided in an embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0108] As shown in Figure 9(a), when using the data of the garment to be tested to cover the original garment data for the torso position, since the posture of the torso part does not change much in the two-dimensional plane, the torso part can be approximated as a square in the two-dimensional plane. Here, the data of the garment to be tested for the torso position can be directly covered with the original garment data of the torso position to form a torso position containing the data of the garment to be tested.

[0109] As shown in Figure 9(a), the third preset vertex can be the upper vertex where the torso and arm meet. In the basic two-dimensional human posture, the third preset vertex of the clothing data to be tested in the torso is B1 (in this embodiment, it is essentially the same as vertex A1). In the two-dimensional human posture, the third preset vertex of the original clothing data in the torso is B2. The third preset boundary is the upper boundary and the left boundary of the torso. In the basic two-dimensional human posture, the third preset boundary of the clothing data to be tested in the torso is the upper boundary Q1 and the left boundary Q2. In the two-dimensional human posture, the third preset boundary of the original clothing data in the torso is the upper boundary Q3 and the left boundary Q4. Specifically, during the coverage process, the third preset vertex B1 of the clothing data to be tried on in the torso position of the two-dimensional human body's basic posture coincides with the third preset vertex B2 of the original clothing data in the torso position of the two-dimensional human body's basic posture; the upper boundary Q1 of the clothing data to be tried on in the torso position of the two-dimensional human body's basic posture coincides with the upper boundary Q3 of the original clothing data in the torso position of the two-dimensional human body's basic posture; and the left boundary Q2 of the clothing data to be tried on in the torso position of the two-dimensional human body's basic posture coincides with the left boundary Q4 of the original clothing data in the arm position of the two-dimensional human body's basic posture, thus completing the coverage. In this embodiment of the invention, coverage is performed by coinciding the third preset vertex and the third preset boundary of the torso position, which can further improve the realism of virtual try-on.

[0110] In addition, the third preset vertex can be any other vertex besides the vertex B1 (B2) mentioned above, such as the upper vertex of the position where the torso and the right arm make contact. The third preset boundary can also be any other boundary besides the boundaries Q1 and Q2 (Q3 and Q4) mentioned above, such as the upper boundary and the right boundary of the torso. The embodiments of the present invention do not impose any special restrictions on this.

[0111] In this embodiment of the invention, the virtual try-on is further improved by covering the third preset vertex and third preset boundary of the clothing data to be tried on in the torso position of the two-dimensional human body basic posture with the third preset vertex and third preset boundary of the original clothing data torso position in the two-dimensional human body posture.

[0112] Figure 9(b) shows another illustration of the torso data of the garment to be tested covering the original garment data, provided in an embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0113] As shown in Figure 9(b), in one embodiment of the present invention, the fourth preset boundary is the upper boundary of the torso (consistent with the third preset boundary in the above embodiment). In the basic two-dimensional human posture, the fourth preset boundary of the torso clothing data to be tried is Q1, and the center of the fourth preset boundary Q1 is O1. In the two-dimensional human posture, the fourth preset boundary of the original clothing data of the torso is Q3, and the center of the fourth preset boundary Q3 is O2. Specifically, during the overlay process, the fourth preset boundary Q1 of the torso clothing data to be tried coincides with the fourth preset boundary Q3 of the original clothing data of the torso in the two-dimensional human posture, and the center O1 of the fourth preset boundary Q1 coincides with the center O2 of the fourth preset boundary Q3. In this embodiment of the present invention, overlaying with the fourth preset boundary and its center coinciding further improves the realism of the virtual try-on.

[0114] In this embodiment of the invention, the virtual try-on is further improved by covering the torso clothing data in the two-dimensional human body basic posture with the fourth preset boundary and the center of the fourth preset boundary of the original clothing data in the torso position in the two-dimensional human body posture.

[0115] Figure 10 Another implementation flow of step 504 in the data processing method provided by the embodiment of the present invention is shown. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0116] In one embodiment of the present invention, such as Figure 10 As shown, in step 504, in the above Figure 7 In addition to the steps shown, the method also includes:

[0117] Step 1001: Based on the tensile strength of the physical properties of the original garment fabric and the tensile strength of the physical properties of the garment fabric to be tested, stretch or spring back the data of the garment to be tested for the arm part in the two-dimensional human body basic posture along the extension direction of the arm part in the two-dimensional human body posture to form an arm part containing the stretched or springback data of the garment to be tested.

[0118] Step 1002: Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, stretch or spring back the torso data of the torso position in the two-dimensional human body basic posture along the extension direction of the torso position in the two-dimensional human body posture to form a torso position containing the stretched or springback clothing data.

[0119] Given that different garments have different physical properties, these properties reflect varying tensile strengths in the garment data. By applying stretching or rebound techniques to the physical properties of the fabric in the original garment data and the garment to be tested, the realism of the virtual fitting can be further enhanced. Furthermore, when the physical properties of the garment fabric are known, the tensile strength of those properties is also known.

[0120] Figure 11 The illustration shows the stretching and rebound of the arm area of ​​the garment under test provided in an embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0121] like Figure 11 As shown, in one embodiment of the present invention, after the data of the garment to be tested for the arm part of the two-dimensional human body basic posture is overlaid on the original garment data of the arm part of the two-dimensional human body posture, the stretching scale or the rebound scale of the arm part is determined according to the tensile force of the physical properties of the original garment fabric and the tensile force of the physical properties of the garment to be tested for the arm part.

[0122] Ideally, the tensile strength or elasticity of the arm area can be determined based on the difference between the tensile strength of the original fabric at the arm area and the tensile strength of the fabric to be tested at the arm area. For example, the tensile strength or elasticity of the arm area can be determined using the following formula:

[0123] ΔG 12 =G1-G2;

[0124] Wherein, ΔG 12 G1 represents the tensile force of the original clothing fabric in the arm area during a two-dimensional human pose, while G2 represents the tensile force of the clothing fabric to be tested in the arm area during a two-dimensional human pose.

[0125] The difference ΔG between the tensile strength of the original fabric at the arm area and the tensile strength of the fabric being tested at the arm area. 12 When it is a positive value, the difference between the two is ΔG 12 The arm area is stretched to a certain extent, and based on this stretching, the physical properties of the garment fabric being tested are determined along the extension direction of the arm area in a two-dimensional human posture. Figure 11 The arm area (in the direction of the arrow in the last image) is stretched to form an arm area that contains the stretched data of the garment to be tested.

[0126] The difference ΔG between the tensile strength of the original fabric at the arm area and the tensile strength of the fabric being tested at the arm area. 12When the value is negative, the difference between the two is ΔG. 12 The elasticity of the arm area is used as the elasticity scale. Based on this elasticity scale, the physical properties of the garment fabric to be tested in the arm area are determined in the opposite direction to the extension direction of the arm area in the two-dimensional human posture. Figure 11 The arm area in the last image (in the opposite direction of the arrow) rebounds, forming an arm area containing the data of the garment to be tested after the rebound.

[0127] In this embodiment of the invention, based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested on the arm area is stretched or rebounded along the extension direction of the arm area in the two-dimensional human body posture, which can further improve the realism of virtual try-on.

[0128] Figure 12 The illustration shows the stretching and rebound of the torso area clothing data provided in the embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0129] like Figure 12 As shown, in one embodiment of the present invention, after the torso data of the two-dimensional human body basic posture is covered by the original clothing data of the torso of the two-dimensional human body posture, the tensile strength of the torso or the elasticity of the torso is determined according to the tensile strength of the physical properties of the original clothing fabric and the tensile strength of the physical properties of the clothing fabric to be tested in the torso.

[0130] Preferably, the tensile strength or elasticity of the torso area can be determined based on the difference between the tensile strength of the original fabric in the torso area and the tensile strength of the fabric to be tested in the torso area. Specifically, the tensile strength or elasticity of the torso area can be determined using the following formula:

[0131] ΔG 34 =G3-G4;

[0132] Wherein, ΔG 34 G3 represents the tensile strength of the original clothing fabric in the torso position in a two-dimensional human body posture, and G4 represents the tensile strength of the clothing fabric to be tested in the torso position in a two-dimensional human body posture.

[0133] The principle is similar for the torso. Generally speaking, the tensile strength of the fabric being tested in the torso area of ​​a two-dimensional human body in a basic pose is consistent with the tensile strength of the fabric being tested in the arm area of ​​a two-dimensional human body in a basic pose; the tensile strength of the original fabric in the torso area of ​​a two-dimensional human body in a pose is consistent with the tensile strength of the original fabric in the arm area of ​​a two-dimensional human body in a pose.

[0134] The difference ΔG between the tensile strength of the original clothing fabric in the torso area and the tensile strength of the clothing fabric being tested in the torso area. 34 When it is a positive value, the difference between the two is ΔG 34 The torso stretching dimension is used as the basis for determining the physical properties of the garment fabric to be tested along the extension direction of the torso in a two-dimensional human posture. Figure 12 The torso section in the last image (in the direction of the arrow) is stretched to form a torso section containing the stretched data of the garment to be tested.

[0135] The difference ΔG between the tensile strength of the original clothing fabric in the torso area and the tensile strength of the clothing fabric being tested in the torso area. 34 When the value is negative, the difference between the two is ΔG. 34 The torso's resilience is used as the springback scale. Based on this torso's resilience scale, the physical properties of the clothing fabric being tested are determined along a direction opposite to the extension direction of the torso in the two-dimensional human posture. Figure 12 The torso section in the last figure (in the opposite direction of the arrow) rebounds to form a torso section containing the data of the garment to be tested after the rebound.

[0136] In this embodiment of the invention, based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested in the torso position is stretched or rebounded along the extension direction of the torso position in the two-dimensional human posture, which can further improve the realism of virtual try-on.

[0137] Figure 13 This paper illustrates another implementation flow of step 504 in the data processing method provided by an embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0138] In one embodiment of the present invention, the preset human body parts include the legs. For example... Figure 13 As shown, step 504 involves, based on the posture changes of each preset human body part in the two-dimensional human pose, overwriting the original clothing data of each preset human body part in the two-dimensional human pose with the clothing data to be tested for each preset human body part in the two-dimensional human pose, thereby forming a two-dimensional human pose containing the clothing data to be tested, including:

[0139] Step 1301: Overlay the original clothing data of the leg part in the two-dimensional human body basic posture with the clothing data to be tested for the leg part, forming a leg part containing the clothing data to be tested; wherein, the fifth preset vertex and the fifth preset boundary of the clothing data to be tested for the leg part in the two-dimensional human body basic posture coincide with the fifth preset vertex and the fifth preset boundary of the original clothing data of the leg part in the two-dimensional human body basic posture, or the sixth preset boundary and the center of the sixth preset boundary of the clothing data to be tested for the leg part in the two-dimensional human body basic posture coincide with the sixth preset boundary and the center of the sixth preset boundary of the original clothing data of the leg part in the two-dimensional human body basic posture.

[0140] The principle for covering the original garment data with the data of the garment to be tried on the leg area is similar to that for the arms and torso. When using the data of the garment to be tried on the leg area to cover the original garment data, since the posture of the leg part does not change much in a two-dimensional plane, the leg part can be approximated as a regular square. Here, the data of the garment to be tried on the leg area can be directly overlaid on the original garment data of the leg area to form the leg area containing the data of the garment to be tried on.

[0141] The fifth preset vertex can be the left vertex where the torso and legs meet, and the fifth preset boundary is the boundary formed by the part where the torso and legs meet. Specifically, during the overlay process, the fifth preset vertex of the clothing data to be tried on for the legs in the basic 2D human posture coincides with the fifth preset vertex of the original clothing data for the legs in the 2D human posture, and the fifth preset boundary of the clothing data to be tried on for the legs in the basic 2D human posture coincides with the fifth preset boundary of the original clothing data for the legs in the 2D human posture, thus completing the overlay. In this embodiment of the invention, the overlay is performed by coinciding the fifth preset vertex and the fifth preset boundary of the legs, which can further improve the realism of the virtual try-on.

[0142] In addition, the fifth preset vertex can also be other vertices besides the above-mentioned vertices, such as the right vertex of the contact position between the torso and the leg. The fifth preset boundary can also be other boundaries besides the above-mentioned boundaries, such as the left or right boundary of the leg. The embodiments of the present invention do not impose any special restrictions on this.

[0143] In this embodiment of the invention, the virtual try-on is further improved by covering the leg area clothing data with the fifth preset vertex and fifth preset boundary of the leg area clothing data in a way that coincides with the fifth preset vertex and fifth preset boundary of the original leg area clothing data.

[0144] In one embodiment of the present invention, the sixth preset boundary is the boundary formed by the portion of the torso and the legs in contact (consistent with the fifth preset boundary in the above embodiment). Specifically, during the overlay process, the sixth preset boundary of the clothing data to be tried on for the legs in the basic two-dimensional human posture coincides with the sixth preset boundary of the original clothing data for the legs in the two-dimensional human posture, and the center of the sixth preset boundary of the clothing data to be tried on for the legs in the basic two-dimensional human posture coincides with the center of the sixth preset boundary of the original clothing data for the legs in the two-dimensional human posture. In this embodiment of the present invention, overlaying with the sixth preset boundary and the center of the sixth preset boundary coinciding can further improve the realism of virtual try-on.

[0145] In this embodiment of the invention, the virtual try-on is further improved by covering the data of the clothing to be tried on in the leg area of ​​the two-dimensional human body in the basic posture with the sixth preset boundary and the center of the sixth preset boundary of the original clothing data of the leg area in the two-dimensional human body in the posture.

[0146] Figure 14 This paper illustrates another implementation flow of step 504 in the data processing method provided by an embodiment of the present invention. For ease of description, only the parts related to the embodiment of the present invention are shown, and are detailed below:

[0147] In one embodiment of the present invention, such as Figure 14 As shown, in step 504, in the above Figure 13 In addition to the steps shown, the method also includes:

[0148] Step 1401: Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, stretch or rebound the clothing data of the leg part in the two-dimensional human body basic posture along the extension direction of the leg part in the two-dimensional human body posture to form a leg part containing the stretched or rebounded clothing data.

[0149] Similarly, the stretching or rebound principle of the garment data for the leg area is similar to that for the arm or torso area.

[0150] Specifically, after the data of the leg part of the two-dimensional human body in the basic posture is covered by the original data of the leg part of the two-dimensional human body posture, the stretching scale or the rebound scale of the leg part is determined according to the tensile strength of the physical properties of the original clothing fabric and the tensile strength of the physical properties of the clothing fabric to be tested in the leg part.

[0151] Ideally, the stretch or rebound measurement of the leg area can be determined based on the difference between the tensile strength of the original fabric and the tensile strength of the fabric to be tested in the leg area. Specifically, the stretch or rebound measurement of the leg area can be determined using the following formula:

[0152] ΔG 56 =G5-G6;

[0153] Wherein, ΔG 56 G5 represents the tensile strength of the original clothing fabric in the leg area during a two-dimensional human pose, while G6 represents the tensile strength of the clothing fabric to be tested in the leg area during a two-dimensional human pose.

[0154] The difference ΔG between the tensile strength of the original garment fabric at the leg area and the tensile strength of the garment fabric to be tested at the leg area. 56 When it is a positive value, the difference between the two is ΔG 56 The leg area is stretched to a certain scale. Based on this stretching scale, the physical properties of the fabric of the garment to be tested are stretched along the extension direction of the leg area in the two-dimensional human posture to form a leg area containing the stretched data of the garment to be tested.

[0155] The difference ΔG between the tensile strength of the original garment fabric at the leg area and the tensile strength of the garment fabric to be tested at the leg area. 56 When the value is negative, the difference between the two is ΔG. 56 The rebound scale of the leg area is used as a reference. Based on the rebound scale of the leg area, the physical properties of the fabric of the garment to be tested are adjusted, and the rebound is performed in the opposite direction to the extension direction of the leg area in the two-dimensional human posture, to form a leg area containing the rebound data of the garment to be tested.

[0156] In this embodiment of the invention, based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested for the leg part in the two-dimensional human body basic posture is stretched or rebounded along the extension direction of the leg part in the two-dimensional human body posture, which can further improve the realism of virtual try-on.

[0157] This invention also provides a data processing apparatus, as described in the following embodiments. Since the principles by which these apparatuses solve problems are similar to those of the data processing methods, the implementation of these apparatuses can be found in the implementation of the methods, and repeated details will not be elaborated further.

[0158] Figure 15 The functional modules of the data processing apparatus provided in the embodiments of the present invention are shown. For ease of explanation, only the parts related to the embodiments of the present invention are shown, and are described in detail below:

[0159] refer to Figure 15 The data processing device includes various modules for performing... Figure 1 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 1 as well as Figure 1 The relevant descriptions in the corresponding embodiments will not be repeated here. In this embodiment of the invention, the data processing device includes an image data acquisition module 1501, a posture recognition module 1502, a posture matching module 1503, and a virtual try-on module 1504.

[0160] The image data acquisition module 1501 is used to acquire image data including a dressed human body through an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device.

[0161] The posture recognition module 1502 is used to recognize the two-dimensional human posture of a dressed human body based on image data; the two-dimensional human posture reflects the projection data of the three-dimensional human body on a second plane; the second plane is a symmetrical plane between the front and back of the dressed human body.

[0162] The posture matching module 1503 is used to match the recognized two-dimensional human posture with the human posture database to determine the preset human body parts of the two-dimensional human posture.

[0163] The virtual try-on module 1504 is used to assign the physical properties of the fabric of the garment to the parts of the two-dimensional human body that are covered by the original clothing in the preset human body parts.

[0164] In this embodiment of the invention, the image data acquisition module 1501 acquires image data including a dressed human body through an image acquisition device. Then, the posture recognition module 1502 identifies the two-dimensional human posture of the dressed human body based on the image data. The posture matching module 1503 matches the two-dimensional human posture in a human posture database to determine preset human body parts for the two-dimensional human posture. Finally, the virtual try-on module 1504 directly assigns the physical properties of the fabric of the garment to be tried on to the preset human body parts covered by the original clothing. This embodiment of the invention eliminates the need to construct a three-dimensional human body model or clothing model; it only requires identifying the two-dimensional human posture of the dressed human body and directly assigning the physical properties of the fabric of the garment to be tried on to the preset human body parts covered by the original clothing. This greatly improves the efficiency of virtual try-on and thus enhances the user experience.

[0165] Figure 16 Another functional module of the data processing apparatus provided in an embodiment of the present invention is shown. For ease of explanation, only the part related to the embodiment of the present invention is shown, and is described in detail below:

[0166] In one embodiment of the present invention, reference is made to... Figure 16The data processing device includes various modules for performing... Figure 5 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 5 as well as Figure 5 The relevant descriptions in the corresponding embodiments will not be repeated here. In the embodiments of the present invention, in the above... Figure 15 Based on the module structure shown, the data processing device further includes a posture change determination module 1601, a raw clothing data formation module 1602, a clothing data formation module 1603, and a clothing data overlay module 1604.

[0167] The posture change determination module 1601 is used to determine the posture changes of each preset human body part based on the basic posture of the two-dimensional human body; the basic posture of the two-dimensional human body is the projection data of the three-dimensional basic human body model on the first plane.

[0168] The original clothing data generation module 1602 is used to assign the physical properties of the original clothing to the preset human body parts covered by the original clothing in the two-dimensional human body posture, thereby generating original clothing data.

[0169] The garment data generation module 1603 is used to assign the physical properties of the garment fabric to the preset human body parts covered by the garment in the two-dimensional human body basic posture, thereby generating garment data.

[0170] The clothing data overlay module 1604 is used to overlay the original clothing data of each preset human body part in the two-dimensional human posture with the clothing data of each preset human body part in the two-dimensional human posture according to the posture changes of each preset human body part in the two-dimensional human posture, so as to form a two-dimensional human posture containing clothing data to be tested.

[0171] In this embodiment of the invention, the posture change determination module 1601 determines the posture changes of each preset human body part in the two-dimensional human body posture based on the basic posture of the two-dimensional human body. The original clothing data formation module 1602 assigns the physical properties of the original clothing to the preset human body parts covered by the original clothing in the two-dimensional human body posture to form original clothing data. The clothing data formation module 1603 assigns the physical properties of the clothing to be tested to the preset human body parts covered by the clothing to be tested in the basic posture of the two-dimensional human body to form clothing data to be tested. Then, the clothing data covering module 1604 covers the original clothing data of each preset human body part in the two-dimensional human body posture with the clothing data to be tested of each preset human body part in the basic posture of the two-dimensional human body according to the posture changes of each preset human body part in the two-dimensional human body posture, which can improve the realism of virtual try-on.

[0172] Figure 17The diagram illustrates the structure of the clothing data overlay module 1604 in the data processing apparatus provided in an embodiment of the present invention. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below:

[0173] In one embodiment of the present invention, the preset human body parts include the arms and torso. (See reference) Figure 17 The various units included in the clothing data overlay module 1604 are used to perform... Figure 7 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 7 as well as Figure 7 The relevant descriptions in the corresponding embodiments will not be repeated here. In this embodiment of the invention, the clothing data coverage module 1604 includes an arm area coverage unit 1701 and a torso area coverage unit 1702.

[0174] The arm part covering unit 1701 is used to cover the original clothing data of the arm part in the two-dimensional human body posture with the clothing data to be tested in the two-dimensional human body posture according to the posture change of the arm part in the two-dimensional human body posture, so as to form an arm part containing the clothing data to be tested; wherein, the first preset vertex and the first preset boundary of the clothing data to be tested in the arm part in the two-dimensional human body posture coincide with the first preset vertex and the first preset boundary of the original clothing data of the arm part in the two-dimensional human body posture, or the second preset boundary and the center of the second preset boundary of the clothing data to be tested in the arm part in the two-dimensional human body posture coincide with the second preset boundary and the center of the second preset boundary of the original clothing data of the arm part in the two-dimensional human body posture.

[0175] The torso coverage unit 1702 is used to cover the original clothing data of the torso in the two-dimensional human body posture with the clothing data to be tested in the torso of the two-dimensional human body posture, forming a torso containing the clothing data to be tested; wherein, the third preset vertex and the third preset boundary of the clothing data to be tested in the torso of the two-dimensional human body posture coincide with the third preset vertex and the third preset boundary of the original clothing data of the torso of the two-dimensional human body posture, or the fourth preset boundary and the center of the fourth preset boundary of the clothing data to be tested in the torso of the two-dimensional human body posture coincide with the fourth preset boundary and the center of the fourth preset boundary of the original clothing data of the torso of the two-dimensional human body posture.

[0176] In this embodiment of the invention, the arm covering unit 1701 covers the arm area by coinciding with the first preset vertex and first preset boundary of the arm area clothing data to be tried in the basic two-dimensional human body posture and the first preset vertex and first preset boundary of the original arm area clothing data in the two-dimensional human body posture, or by coinciding with the second preset boundary and second preset boundary center of the arm area clothing data to be tried in the basic two-dimensional human body posture and the second preset boundary and second preset boundary center of the original arm area clothing data in the two-dimensional human body posture, which can further improve the realism of virtual try-on.

[0177] In this embodiment of the invention, the torso covering unit 1702 covers the torso clothing data to be tried in the two-dimensional human body basic posture by coinciding with the third preset vertex and third preset boundary of the torso clothing data in the two-dimensional human body basic posture, or by coinciding with the fourth preset boundary and fourth preset boundary center of the torso clothing data in the two-dimensional human body basic posture, which can further improve the realism of virtual try-on.

[0178] Figure 18 Another structural schematic of the clothing data overlay module 1604 in the data processing device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0179] In one embodiment of the present invention, reference is made to... Figure 18 The various units included in the clothing data overlay module 1604 are used to perform... Figure 10 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 10 as well as Figure 10 The relevant descriptions in the corresponding embodiments will not be repeated here. In the embodiments of the present invention, in the above... Figure 17 Based on the unit structure shown, the clothing data coverage module 1604 also includes an arm stretch rebound unit 1801 and a torso stretch rebound unit 1802.

[0180] The arm stretching and rebound unit 1801 is used to stretch or rebound the arm data of the garment to be tested in the two-dimensional human body basic posture along the extension direction of the arm in the two-dimensional human body posture, based on the tensile force of the original physical properties of the garment fabric and the tensile force of the physical properties of the garment fabric to be tested, to form an arm containing the stretched or rebounded garment data of the garment to be tested.

[0181] The torso stretching and rebound unit 1802 is used to stretch or rebound the torso data of the test garment in the two-dimensional human body basic posture along the extension direction of the torso in the two-dimensional human body posture according to the tensile force of the physical properties of the original garment fabric and the tensile force of the physical properties of the garment fabric to be tested, so as to form a torso containing the stretched or rebounded garment data.

[0182] In this embodiment of the invention, the arm stretching and rebound unit 1801 stretches or rebounds the data of the garment to be tested in the arm part of the two-dimensional human body basic posture along the extension direction of the arm part in the two-dimensional human body posture according to the tensile force of the original physical properties of the garment fabric and the tensile force of the physical properties of the garment fabric to be tested, which can further improve the realism of virtual try-on.

[0183] In this embodiment of the invention, the torso stretching and rebounding unit 1802 stretches or rebounds the torso data of the garment to be tested along the extension direction of the torso in the two-dimensional human body posture based on the tensile force of the original clothing fabric and the tensile force of the clothing fabric to be tested, thereby further improving the realism of virtual try-on.

[0184] Figure 19 The following is another structural schematic of the clothing data overlay module 1604 in the data processing device provided in an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0185] In one embodiment of the present invention, the preset human body part includes the legs. (See reference) Figure 19 The various units included in the clothing data overlay module 1604 are used to perform... Figure 13 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 13 as well as Figure 13 The relevant descriptions in the corresponding embodiments will not be repeated here. In this embodiment of the invention, the clothing data coverage module 1604 includes a leg area coverage unit 1901.

[0186] The leg part covering unit 1901 is used to cover the original clothing data of the leg part in the two-dimensional human body basic posture with the clothing data to be tested in the leg part, forming a leg part containing the clothing data to be tested; wherein, the fifth preset vertex and the fifth preset boundary of the clothing data to be tested in the leg part in the two-dimensional human body basic posture coincide with the fifth preset vertex and the fifth preset boundary of the original clothing data of the leg part in the two-dimensional human body basic posture, or the sixth preset boundary and the center of the sixth preset boundary of the clothing data to be tested in the leg part in the two-dimensional human body basic posture coincide with the sixth preset boundary and the center of the sixth preset boundary of the original clothing data of the leg part in the two-dimensional human body basic posture.

[0187] In this embodiment of the invention, the leg area covering unit 1901 covers the leg area by coinciding with the fifth preset vertex and fifth preset boundary of the leg area clothing data to be tried in the two-dimensional human body basic posture and the fifth preset vertex and fifth preset boundary of the original leg area clothing data in the two-dimensional human body posture, or by coinciding with the sixth preset boundary and sixth preset boundary center of the leg area clothing data to be tried in the two-dimensional human body basic posture and the sixth preset boundary and sixth preset boundary center of the original leg area clothing data in the two-dimensional human body posture, which can further improve the realism of virtual try-on.

[0188] Figure 20 This illustration shows another structural diagram of the clothing data overlay module 1604 in the data processing device provided in an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0189] In one embodiment of the present invention, reference is made to... Figure 20 The various units included in the clothing data overlay module 1604 are used to perform... Figure 14 For details of each step in the corresponding embodiment, please refer to [link / reference]. Figure 14 as well as Figure 14 The relevant descriptions in the corresponding embodiments will not be repeated here. In the embodiments of the present invention, in the above... Figure 19 Based on the unit structure shown, the clothing data coverage module 1604 also includes a leg stretch rebound unit 2001.

[0190] The leg stretching and rebound unit 2001 is used to stretch or rebound the leg data of the test garment in the two-dimensional human body basic posture along the extension direction of the leg in the two-dimensional human body posture according to the tensile force of the physical properties of the original garment fabric and the tensile force of the physical properties of the test garment fabric, so as to form a leg part containing the stretched or rebounded test garment data.

[0191] In this embodiment of the invention, the leg stretching and rebound unit 2001 stretches or rebounds the data of the garment to be tested in the leg part of the two-dimensional human body basic posture along the extension direction of the leg part in the two-dimensional human body posture according to the tensile force of the original physical properties of the garment fabric and the tensile force of the physical properties of the garment fabric to be tested, which can further improve the realism of virtual try-on.

[0192] In this specification, the color changes of the pixels on the first and second planes are synchronized.

[0193] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described data processing method.

[0194] This invention also provides a computer-readable storage medium storing a computer program that performs the above-described data processing method.

[0195] In summary, in this embodiment of the invention, image data including a dressed human body is acquired through an image acquisition device; then, the two-dimensional human posture of the dressed human body is identified based on the image data; and a preset human body part is determined by matching in a human posture database. Finally, the physical properties of the fabric of the garment to be tried on are directly assigned to the preset human body parts covered by the original clothing. This embodiment of the invention does not require the construction of a three-dimensional human body model or clothing model; it only needs to identify the two-dimensional human posture of the dressed human body and directly assign the physical properties of the fabric of the garment to be tried on the preset human body parts covered by the original clothing. This can greatly improve the efficiency of virtual try-on and thus improve the user experience.

[0196] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0197] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0198] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0199] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0200] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A data processing method, characterized by, include: Image data including a dressed human body is acquired through an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device. Identify the two-dimensional human posture of a dressed person based on image data; Two-dimensional human posture reflects the projection data of three-dimensional human body on a second plane; the second plane is the plane of symmetry between the front and back of the dressed human body. The identified two-dimensional human poses are matched with a human pose database to determine the preset human body parts of the two-dimensional human poses. Assign the physical properties of the fabric of the garment to be tested to the parts of the pre-defined human body parts in the two-dimensional human posture that are covered by the original clothing. Based on the basic two-dimensional human body posture, determine the posture changes of each preset human body part in the two-dimensional human body posture. The two-dimensional human body basic pose is the projection data of the three-dimensional basic human body model on the first plane; the preset human body parts covered by the original clothing in the two-dimensional human body pose are given the physical properties of the original clothing fabric to form the original clothing data. The physical properties of the fabric of the garment to be tested are assigned to the preset human body parts covered by the garment in the basic two-dimensional human body posture, forming the garment data. Based on the posture changes of each preset human body part in the two-dimensional human body posture, the original garment data of each preset human body part in the two-dimensional human body posture is overlaid with the garment data of each preset human body part in the basic two-dimensional human body posture, forming a two-dimensional human body posture containing the garment data. An angle exists between the first plane and the second plane. Based on geometric relationships And the projection data of the three-dimensional human body on the first plane, to determine the projection data of the dressed human body on the second plane, wherein The width of the three-dimensional human body projected onto the first plane. The width of the three-dimensional human body projected onto the second plane; Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested, which is a preset human body part in the two-dimensional human body basic posture, is stretched or rebounded along the extension direction of the preset human body part in the two-dimensional human body posture, forming a preset human body part containing the stretched or rebounded data of the clothing to be tested. When the preset human body parts include the arms and torso, the resulting two-dimensional human posture containing the data of the clothing to be tried includes: Based on the posture changes of the arm portion in a two-dimensional human body pose, the clothing data to be tested for the arm portion in the basic two-dimensional human body pose is overlaid with the original clothing data for the arm portion in the basic two-dimensional human body pose, forming an arm portion containing the clothing data to be tested; wherein, the first preset vertex and the first preset boundary of the clothing data to be tested for the arm portion in the basic two-dimensional human body pose coincide with the first preset vertex and the first preset boundary of the original clothing data for the arm portion in the basic two-dimensional human body pose, or the second preset boundary and the center of the second preset boundary of the clothing data to be tested for the arm portion in the basic two-dimensional human body pose coincide with the second preset boundary and the center of the second preset boundary of the original clothing data for the arm portion in the basic two-dimensional human body pose; and Overlay the original clothing data of the torso position in the two-dimensional human body basic posture with the clothing data of the torso position in the two-dimensional human body basic posture to form a torso position containing the clothing data to be tested; wherein, the third preset vertex and the third preset boundary of the clothing data of the torso position in the two-dimensional human body basic posture coincide with the third preset vertex and the third preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture, or the fourth preset boundary and the center of the fourth preset boundary of the clothing data of the torso position in the two-dimensional human body basic posture coincide with the fourth preset boundary and the center of the fourth preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture. When the preset human body part includes the legs, the formation of a two-dimensional human posture containing the data of the clothing to be tried on includes: The clothing data to be tested for the leg part in the basic two-dimensional human body posture is overlaid on the original clothing data for the leg part in the basic two-dimensional human body posture to form a leg part containing the clothing data to be tested; wherein, the fifth preset vertex and the fifth preset boundary of the clothing data to be tested for the leg part in the basic two-dimensional human body posture coincide with the fifth preset vertex and the fifth preset boundary of the original clothing data for the leg part in the basic two-dimensional human body posture, or the sixth preset boundary and the center of the sixth preset boundary of the clothing data to be tested for the leg part in the basic two-dimensional human body posture coincide with the sixth preset boundary and the center of the sixth preset boundary of the original clothing data for the leg part in the basic two-dimensional human body posture. The physical properties of the fabric are the variable maximum and minimum distances between two adjacent pixels in the fabric; when stretching or rebounding, the stretching or rebounding scale is determined based on the difference between the tensile force of the original clothing fabric and the tensile force of the clothing fabric to be tested; when the difference is positive, the stretching is performed along the extension direction of the preset human body part in the two-dimensional human posture; when the difference is negative, the rebound is performed in the opposite direction to the extension direction of the preset human body part in the two-dimensional human posture.

2. The data processing method as described in claim 1, characterized in that, The first plane and the second plane are the same plane, or the first plane and the second plane are different planes.

3. The data processing method as described in claim 1, characterized in that, Also includes: Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested for the arm part in the basic two-dimensional human body posture is stretched or rebounded along the extension direction of the arm part in the two-dimensional human body posture to form an arm part containing the stretched or rebounded data of the clothing to be tested. Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the torso in the basic two-dimensional human body posture is stretched or rebounded along the extension direction of the torso in the two-dimensional human body posture to form a torso containing the stretched or rebounded data of the clothing to be tested.

4. The data processing method as described in claim 1, characterized in that, Also includes: Based on the tensile strength of the original clothing fabric and the tensile strength of the clothing fabric to be tested, the data of the clothing to be tested for the leg part in the two-dimensional human body basic posture is stretched or rebounded along the extension direction of the leg part in the two-dimensional human body posture, forming a leg part containing the stretched or rebounded data of the clothing to be tested.

5. A data processing apparatus, characterized in that, include: The image data acquisition module is used to acquire image data including a dressed human body through an image acquisition device; the image data of the dressed human body reflects the projection data of the three-dimensional human body on a first plane perpendicular to the center line of the field of view of the image acquisition device. The posture recognition module is used to identify the two-dimensional human posture of a dressed person based on image data; Two-dimensional human posture reflects the projection data of a three-dimensional human body onto a second plane; The second plane is a symmetrical plane between the front and back of the dressed human body; The pose matching module is used to match the recognized two-dimensional human pose with the human pose database to determine the preset human body parts of the two-dimensional human pose. The virtual try-on module is used to assign the physical properties of the fabric of the garment to the parts of the two-dimensional human body that are covered by the original clothing in a preset human body posture. The device further includes: The posture change determination module is used to determine the posture changes of each preset human body part based on the basic posture of the two-dimensional human body; the basic posture of the two-dimensional human body is the projection data of the three-dimensional basic human body model on the first plane. The original clothing data generation module is used to assign the physical properties of the original clothing to the preset human body parts covered by the original clothing in the two-dimensional human body posture, thereby generating original clothing data. The garment data generation module is used to assign the physical properties of the garment fabric to the preset human body parts covered by the garment in the basic two-dimensional human body posture, thereby generating garment data. The clothing data overlay module is used to overlay the original clothing data of each preset human body part in the two-dimensional human pose with the clothing data of the preset human body parts in the basic two-dimensional human pose, based on the pose changes of each preset human body part in the two-dimensional human pose, thus forming a two-dimensional human pose containing the clothing data to be tested; there is an angle between the first plane and the second plane. Based on geometric relationships And the projection data of the three-dimensional human body on the first plane, to determine the projection data of the dressed human body on the second plane, wherein The width of the three-dimensional human body projected onto the first plane. The projection width of the three-dimensional human body on the second plane; based on the tensile force of the physical properties of the original clothing fabric and the tensile force of the physical properties of the clothing fabric to be tested, the clothing data of the preset human body parts in the two-dimensional human body basic posture is stretched or rebounded along the extension direction of the preset human body parts in the two-dimensional human body posture to form a preset human body part containing the stretched or rebounded clothing data to be tested. When the preset human body parts include the arms and torso, the resulting two-dimensional human posture containing the data of the clothing to be tried includes: Based on the posture changes of the arm portion in a two-dimensional human body pose, the clothing data to be tested for the arm portion in the basic two-dimensional human body pose is overlaid with the original clothing data for the arm portion in the basic two-dimensional human body pose, forming an arm portion containing the clothing data to be tested; wherein, the first preset vertex and the first preset boundary of the clothing data to be tested for the arm portion in the basic two-dimensional human body pose coincide with the first preset vertex and the first preset boundary of the original clothing data for the arm portion in the basic two-dimensional human body pose, or the second preset boundary and the center of the second preset boundary of the clothing data to be tested for the arm portion in the basic two-dimensional human body pose coincide with the second preset boundary and the center of the second preset boundary of the original clothing data for the arm portion in the basic two-dimensional human body pose; and Overlay the original clothing data of the torso position in the two-dimensional human body basic posture with the clothing data of the torso position in the two-dimensional human body basic posture to form a torso position containing the clothing data to be tested; wherein, the third preset vertex and the third preset boundary of the clothing data of the torso position in the two-dimensional human body basic posture coincide with the third preset vertex and the third preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture, or the fourth preset boundary and the center of the fourth preset boundary of the clothing data of the torso position in the two-dimensional human body basic posture coincide with the fourth preset boundary and the center of the fourth preset boundary of the original clothing data of the torso position in the two-dimensional human body basic posture. When the preset human body part includes the legs, the formation of a two-dimensional human posture containing the data of the clothing to be tried on includes: The clothing data to be tested for the leg part in the basic two-dimensional human body posture is overlaid on the original clothing data for the leg part in the basic two-dimensional human body posture to form a leg part containing the clothing data to be tested; wherein, the fifth preset vertex and the fifth preset boundary of the clothing data to be tested for the leg part in the basic two-dimensional human body posture coincide with the fifth preset vertex and the fifth preset boundary of the original clothing data for the leg part in the basic two-dimensional human body posture, or the sixth preset boundary and the center of the sixth preset boundary of the clothing data to be tested for the leg part in the basic two-dimensional human body posture coincide with the sixth preset boundary and the center of the sixth preset boundary of the original clothing data for the leg part in the basic two-dimensional human body posture. The physical properties of the fabric are the variable maximum and minimum distances between two adjacent pixels in the fabric; when stretching or rebounding, the stretching or rebounding scale is determined based on the difference between the tensile force of the original clothing fabric and the tensile force of the clothing fabric to be tested; when the difference is positive, the stretching is performed along the extension direction of the preset human body part in the two-dimensional human posture; when the difference is negative, the rebound is performed in the opposite direction to the extension direction of the preset human body part in the two-dimensional human posture.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the data processing method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that performs the data processing method according to any one of claims 1 to 4.

Citation Information

Patent Citations

  • Virtual fitting method, device and system and three-dimensional fabric material library establishment method and device

    CN106502399A

  • Method and device for realizing virtual try-on

    CN107622428A

  • Image deformation method oriented to two-dimensional virtual fitting

    CN107798713A