WO2024067320A1

WO2024067320A1 - Virtual object rendering method and apparatus, and device and storage medium

Info

Publication number: WO2024067320A1
Application number: PCT/CN2023/120222
Authority: WO
Inventors: 蔡鑫; 刘佳成
Original assignee: 北京字跳网络技术有限公司
Priority date: 2022-09-29
Filing date: 2023-09-21
Publication date: 2024-04-04
Also published as: CN115861503A

Abstract

A virtual object rendering method and apparatus, and a device and a storage medium. The method comprises: acquiring skeleton point position information of a target object in the current image and initial position information of a plurality of vertexes of a virtual object; on the basis of the skeleton point position information, transforming the initial position information of the plurality of vertexes to obtain intermediate position information of the plurality of vertexes; on the basis of set material information, updating the intermediate position information of at least some of the plurality of vertexes of the virtual object to obtain target position information; and on the basis of the target position information, rendering the virtual object to obtain a target image.

Description

Virtual object rendering method, device, equipment and storage medium

This application claims priority to the Chinese patent application filed with the China Patent Office on September 29, 2022, with application number 202211204095.X. The entire contents of this application are incorporated by reference into this application.

Technical Field

The embodiments of the present disclosure relate to the field of augmented reality technology, for example, to a method, device, equipment and storage medium for rendering a virtual object.

Background technique

With the continuous development of augmented reality (AR) technology, the generation of virtual objects in real scenes through AR technology has been widely used. Trying on clothes for users is an application scenario of AR technology. In related technologies, the clothes tried on cannot fit the movement of the characters well, and lack the dynamics and texture of real clothes, so the try-on effect is poor.

Summary of the invention

The embodiments of the present disclosure provide a method, apparatus, device and storage medium for rendering a virtual object, so that a virtual object being tried on can fit well with the movement of a target object, and can make the virtual object have the dynamic feeling and texture of a real object, thereby improving the rendering effect.

In a first aspect, an embodiment of the present disclosure provides a method for rendering a virtual object, comprising:

Obtaining the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; wherein the multiple vertices of the virtual object are multiple vertices of a three-dimensional (3D) model corresponding to the virtual object;

Transforming the initial position information of the plurality of vertices based on the skeleton point position information to obtain intermediate position information of the plurality of vertices;

updating intermediate position information of at least some of the multiple vertices of the virtual object based on the set material information to obtain target position information;

The virtual object is rendered based on the target position information to obtain a target image; wherein the target object in the target image wears the virtual object.

In a second aspect, the present disclosure also provides a virtual object rendering device, including:

An acquisition module, configured to acquire the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; wherein the multiple vertices of the virtual object are multiple vertices of the 3D model corresponding to the virtual object;

A position information transformation module, configured to transform the initial position information of the plurality of vertices based on the position information of the skeleton points to obtain the intermediate position information of the plurality of vertices;

a target position information acquisition module, configured to update the intermediate position information of at least some of the multiple vertices of the virtual object based on the set material information to obtain the target position information;

A rendering module is configured to render the virtual object based on the target position information to obtain a target image; wherein the target object in the target image wears the virtual object.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

one or more processors;

a storage device configured to store one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the virtual object rendering method as described in the embodiment of the present disclosure.

In a fourth aspect, the embodiments of the present disclosure further provide a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the method for rendering a virtual object as described in the embodiments of the present disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

FIG1 is a schematic diagram of a flow chart of a method for rendering a virtual object provided by an embodiment of the present disclosure;

FIG2 is a schematic diagram of a rendered virtual object provided by an embodiment of the present disclosure;

FIG3 is an example diagram of a color noise diagram provided by an embodiment of the present disclosure;

FIG4a is an example diagram of a target object sampling diagram provided by an embodiment of the present disclosure;

FIG4b is an example diagram of a first mask image provided by an embodiment of the present disclosure;

FIG4c is an example diagram of a virtual object provided by an embodiment of the present disclosure;

FIG4d is an example diagram of a target image provided by an embodiment of the present disclosure;

FIG5a is an example diagram of displaying a virtual object provided by an embodiment of the present disclosure;

FIG5b is another example diagram of displaying a virtual object provided by an embodiment of the present disclosure;

FIG6 is a schematic diagram of the structure of a virtual object rendering device provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

Embodiments of the present disclosure will be described below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

It should be understood that the multiple steps described in the method embodiments of the present disclosure can be performed in different orders and/or performed in parallel. In addition, the method embodiments may include additional steps and/or omit the steps shown. The scope of the present disclosure is not limited in this respect.

The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

The concepts of “first”, “second”, etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

The modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

Before using the technical solutions disclosed in the multiple embodiments of this disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

For example, in response to receiving a user's active request, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to submit the operation to the user according to the prompt message. Software or hardware such as electronic devices, applications, servers or storage media provide personal information.

As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

The above notification and the process of obtaining user authorization are merely illustrative and do not limit the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

The data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

Figure 1 is a flow chart of a method for rendering a virtual object provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to the situation of rendering a virtual object. The method can be executed by a rendering device for a virtual object, which can be implemented in the form of software and/or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a personal computer (PC) or a server, etc.

As shown in FIG1 , the method comprises:

S110, obtaining the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object.

The current image can be a static image, a real-time captured image, or a frame of an image in a video. The target object can be a person or an animal. In this application scenario, the target object is a person. The virtual object can be a pre-built 3D virtual object, such as virtual clothing or virtual accessories. The multiple vertices of the virtual object can be the multiple vertices of the 3D model corresponding to the virtual object. The initial position information of the multiple vertices of the virtual object can be understood as the three-dimensional coordinates of the multiple vertices of the virtual object in the world coordinate system.

The skeleton point position information may be the three-dimensional coordinates of the skeleton key points in the world coordinate system. In the present embodiment, the method for obtaining the skeleton point position information of the target object in the current image may be: performing skeleton key point detection or posture detection on the target object in the current image, thereby obtaining the position information of multiple skeleton key points. The skeleton point position information may be obtained by using a posture detection algorithm or a skeleton key point detection algorithm, which is not limited here.

S120, transforming the initial position information of the multiple vertices based on the skeleton point position information to obtain the intermediate position information of the multiple vertices.

In this embodiment, the virtual object moves along with the movement of the target object, that is, the position information of the multiple vertices of the virtual object changes along with the change of the position information of the skeleton points.

The method of transforming the initial position information based on the position information of the skeleton point can be: For each vertex of the multiple vertices of the body: obtain multiple skeleton points associated with the vertex of the virtual object and the position influence weights of the multiple skeleton points on the vertex of the virtual object; determine the vertex transformation information of the vertex based on the position information and the position influence weights of the multiple skeleton points; transform the initial position information of the vertex based on the vertex transformation information of the vertex to obtain the intermediate position information of the vertex.

The position influence weight can be understood as the degree of influence of the position of the bone point on the position of the vertex of the virtual object. The position influence weight is related to the distance between the bone point and the vertex of the virtual object. The closer the distance between the bone point and the vertex of the virtual object point, the greater the position influence weight of the bone point on the vertex of the virtual object. The farther the distance between the bone point and the vertex of the virtual object, the smaller the position influence weight of the bone point on the vertex of the virtual object, thereby presenting the effect that the virtual object moves with the movement of the human body. For example, for the vertex of the virtual object close to the knee bone point, it is greatly affected by the knee bone point. When the human body bends the knee, the vertex of the virtual object close to the knee bone point will have a large position change with the knee bone point.

In this embodiment, the process of obtaining multiple skeleton points associated with the vertices of the virtual object and the position influence weights of the multiple skeleton points on the vertices of the virtual object can be: first, the virtual object is bound to the skeleton points of the target object, and the multiple skeleton points associated with each vertex of the virtual object and the position influence weights of the multiple skeleton points on the vertices of the virtual object are determined according to the binding result. In this application scenario, each vertex of the virtual object is associated with four skeleton points. The method of determining the vertex transformation information of the vertex based on the position influence weights and position information of the multiple skeleton points can be: weighted summation of the position information of the multiple skeleton points based on the position influence weights to obtain the vertex transformation information of the vertex.

The vertex transformation information may be represented by a matrix, and the initial position information of the vertex may be transformed based on the vertex transformation information of the vertex by multiplying the vector corresponding to the initial position information of the vertex by the matrix corresponding to the vertex transformation information of the vertex, thereby obtaining the vector corresponding to the intermediate position information of the vertex. In this embodiment, the initial position information is transformed based on the vertex transformation information, so that the virtual object moves with the movement of the target object, thereby improving the realistic effect of the virtual object being worn on the target object.

S130, updating the intermediate position information of at least some of the vertices of the virtual object based on the set material information to obtain the target position information.

The material information may be set based on material parameter representation, and different material parameters correspond to different materials. In this embodiment, the set material may be a cloth material. First, the multiple vertices of the virtual object are divided into at least two parts according to the mapping coordinates of the multiple vertices of the virtual object, and then one or more vertices of the at least two parts are selected to update the intermediate position information of at least part of the selected vertices based on the set material information.

The method of updating the intermediate position information of at least some of the multiple vertices of the virtual object based on the set material information may be: obtaining the set material information and the motion state of at least some of the multiple vertices of the virtual object; updating the intermediate position information of at least some of the vertices based on the set material information; The material setting is performed on at least some of the vertices of the virtual object according to the material information and the motion state of at least some of the vertices to obtain the target position information.

Optionally, the target position information includes the target position information of the plurality of vertices of the virtual object. The intermediate position information of at least some of the vertices among the plurality of vertices can be obtained by performing a material setting calculation on the at least some of the vertices. For the remaining vertices among the plurality of vertices, the intermediate position information of the vertices can be directly used as the target position information of the vertices. The material setting information can be a parameter characterizing the material properties, which can include air resistance, stretch coefficient, compression coefficient, bending coefficient, etc. The material setting information can be set according to actual needs. The motion state of the vertices of the virtual object can be information such as the motion speed and motion direction of the vertices of the virtual object in the current image relative to the previous image. In this embodiment, a pre-developed material solution plug-in can be called to perform material solution. For example, the material solution plug-in performs a material setting calculation on the material parameters, the intermediate position information of at least some of the vertices, and the motion state, and outputs the target position information. In this embodiment, the material setting calculation is performed on at least some of the vertices of the virtual object according to the intermediate position information, the material setting information, and the motion state, so that the virtual object can have the dynamic and texture of the set material.

Optionally, the method of solving the material setting for at least part of the vertices of the virtual object according to the intermediate position information of at least part of the vertices, the set material information and the motion state of at least part of the vertices may be: if a virtual object support body is set in the current scene; obtain support information according to the virtual object support body; solve the material setting for at least part of the vertices of the virtual object according to the intermediate position information of at least part of the vertices, material parameters, the motion state of at least part of the vertices and the support information.

The virtual object support can be set according to the collision principle, that is, it can be a collision body, and the support information can be understood as collision information. In this embodiment, in the area where the virtual object support is set, the virtual object will collide with the virtual object support, that is, the virtual object cannot pass through the virtual object support, which can make the virtual object present a certain shape. In this embodiment, the virtual object support can be set by a material solution plug-in, and the material solution plug-in obtains support information according to the set virtual object support. The material solution plug-in can set the material parameters, support information, at least part of the intermediate position information and motion state of the vertices to solve the material, so as to obtain the target position information after the solution. In this embodiment, setting the virtual object support in the current scene can make the virtual object present a certain shape, so as to meet the personalized needs of the user. Exemplarily, FIG2 is a schematic diagram of the virtual object rendered in this embodiment. As shown in FIG2, the virtual object is a skirt. Since the vertices below the waist of the skirt are set to solve the material solution, the skirt below the waist has the dynamic and texture of gauze, and a virtual object support is set under the skirt, so the skirt hem presents a bulging effect.

S140, rendering the virtual object based on the target position information to obtain a target image.

The target object in the target image wears the virtual object.

In this embodiment, multiple vertices of the virtual object are rendered to corresponding positions in the picture based on the target position information, thereby obtaining a target image.

The virtual object is rendered based on the target position information, and the method for obtaining the target image can be: sampling preset color information from the color noise map based on the mapping coordinates of each vertex of the virtual object; offsetting the preset color information according to the time information of the current image to obtain the offset-processed preset color information corresponding to the vertex; adjusting the initial color of the vertex of the virtual object according to the offset-processed preset color information corresponding to the vertex and the target position information to obtain the target color of the vertex; rendering the virtual object based on the target position information and the target color of each vertex to obtain the target image.

The mapping coordinates of the multiple vertices may be the coordinates of the multiple vertices in the surface map of the virtual object. The color noise map may be a randomly generated noise map. For example, FIG. 3 is an example of a color noise map in this embodiment, FIG. 3 is a noise map after grayscale processing, and the original image is a color map. In this embodiment, the color noise map and the surface map of the virtual object have the same size, that is, the pixels between the two images correspond one to one, so that the preset color information can be sampled from the color noise map according to the mapping coordinates.

The time information of the current image can be understood as the timestamp information of the current image in the video. The color information can be represented by three color channel (RGB) values. The process of offsetting the preset color information according to the time information of the current image can be: firstly, linearly transform the time information to obtain the offset; then convert the RGB information of the preset color information into the HSV (Hue, Saturation, Value) color space, and then offset the three components in the HSV information based on the offset to obtain the HSV information after the offset, and then convert the HSV information back to RGB information. The linear transformation of the time information can be: multiply the time information by the set value to obtain the offset. The formula for offsetting the three components in the HSV information based on the offset can be expressed as: H1=H0, S1=S0+t/360, V1=V0+t/360*0.1, where S0 is the S component before the offset, S1 is the S component after the offset, V0 is the V component before the offset, and V1 is the V component after the offset.

In this embodiment, the initial color of the vertex of the virtual object is adjusted according to the preset color information and target position information after the offset processing corresponding to the vertex, and the target color of the vertex can be obtained by: determining the normal direction and viewing direction of each vertex of the virtual object according to the target position information; determining the color transformation information corresponding to the vertex according to the preset color information after the offset processing corresponding to the vertex; determining the color adjustment amount of the vertex according to the color transformation information corresponding to the vertex, the normal direction of the vertex and the viewing direction of the vertex; and accumulating the color adjustment amount of the vertex with the initial color of the vertex of the virtual object to obtain the target color of the vertex.

The normal direction of the vertex of the virtual object may be the normal direction of the section where the vertex of the virtual object is located, and the viewing direction of the vertex of the virtual object may be the direction in which the optical center of the camera points to the vertex of the virtual object. The color transformation information may be represented by a color transformation matrix. The process of determining the color transformation information corresponding to the vertex based on the color information can be: converting the three channel color values of the preset color information corresponding to the vertex after the offset processing into angle information, then calculating the sine and cosine of the three angle information, and finally constructing the color transformation matrix corresponding to the vertex based on the sine and cosine of the three angle information. Exemplarily, the formula for converting the three channel color values into angle information can be expressed as: angle information = (RGB-a)*b*π, where a and b are set values, for example: a can be 0.5 and b can be 2. Assuming X＝(Ra)*b*π, Y＝(Ga)*b*π, Z＝(Ba)*b*π, the color transformation matrix can be expressed as: [sinY*cosZ, cosY*sinZ*sinX-sinY*cosX, cosY*sinZ*sinX+sinY*cosX, sinY*cosZ, sinY*cosX+sinY*sinZ*sinX, conY*sinZ*sinX-sinX*conZ, -sinZ, cosZ*sinX, sinZ*cosX].

The color adjustment amount may be a brightness value. In this embodiment, the process of determining the color adjustment amount of the vertex according to the color transformation information corresponding to the vertex, the normal direction of the vertex, and the viewing direction of the vertex may be: performing dot multiplication of the color transformation matrix corresponding to the color transformation information with the vector corresponding to the normal direction and the vector corresponding to the viewing direction in turn to obtain the color adjustment amount. Finally, the color adjustment amount of each vertex is accumulated with the initial color of the vertex of the virtual object to obtain the target color of the vertex. In this embodiment, the color of the vertex of the virtual object is adjusted according to the preset color information, normal direction, and viewing direction after the time information offset processing, so as to generate a flickering effect in which the virtual object changes dynamically with the movement of the target object. Exemplarily, as shown in FIG2 , a flickering effect is presented on the "skirt".

In this embodiment, the virtual object is rendered based on the target position information, and the target image is obtained by: sampling the current image according to the virtual 3D target object model and the virtual object model to obtain a target object sampling map; converting the target object sampling map into a first mask map; fusing the current image and the virtual object map based on the first mask map to obtain a target image; and rendering the target image to the current screen.

The virtual 3D target object model can be a virtual 3D model obtained by binding the standard target object model to the posture of the target object in the current image. The virtual object model can be understood as a 3D model corresponding to the virtual object. The process of sampling the current image according to the virtual 3D target object model and the virtual object model can be: first, the occlusion relationship between the target object and the virtual object is determined according to the virtual 3D target object model and the virtual object model, and the pixel points of the target object that are not occluded are sampled from the current image based on the occlusion relationship, thereby obtaining a target object sampling map. Exemplarily, Figure 4a is an example diagram of the target object sampling map in this embodiment. As shown in Figure 4a, the non-black area in Figure 4a is the pixel points of the target object that are not occluded.

The method of converting the target object sampling map into the first mask map may be: identifying the target object in the target object sampling map to obtain the first mask map. Exemplarily, FIG4b is an example of the first mask map, as shown in FIG4b, the white area in FIG4b is the target object area.

The virtual object map can be understood as a two-dimensional (2D) map obtained by projecting the virtual object onto the screen according to the target position information. For example, FIG4c is an example of a virtual object in this embodiment. As shown in FIG4c , the denim jacket in FIG4c is a virtual object.

The method of fusing the current image and the virtual object image based on the first mask image may be: determining a weighted weight according to pixel values of pixels in the first mask image, and fusing the current image and the virtual object image based on the weighted weight.

Exemplarily, assuming that the pixel value of the pixel point in the first mask image is a, a is used as the weighted weight of the current image, and 1-a is used as the weighted weight of the virtual object image, then the fusion formula can be expressed as: a*current image+(1-a)*virtual object image. Exemplarily, FIG4d is an example of a target image in this embodiment.

In this embodiment, the current image and the virtual object image are fused based on the first mask image corresponding to the target object sampling image, so that the virtual object can be accurately worn on the target object.

Optionally, the current image and the virtual object image are fused based on the first mask image to obtain the target image by: blurring the first mask image; and fusing the current image and the virtual object image based on the blurred first mask image to obtain the target image.

The blurring process may adopt a blurring process algorithm, which is not limited here. The method of fusing the current image and the virtual object image based on the blurred first mask image may be: determining a weighted weight according to the pixel value of the pixel point in the blurred first mask image, and fusing the current image and the virtual object image based on the weighted weight.

Exemplarily, assuming that the pixel value of the pixel point in the first mask image after blurring is b, b is used as the weighted weight of the current image, and 1-b is used as the weighted weight of the virtual object image. The fusion formula can be expressed as: b*current image+(1-b)*virtual object image.

In this embodiment, the current image and the virtual object image are fused based on the first mask image after blur processing, so that a smooth transition can be achieved between the target object and the virtual object.

The virtual object is rendered based on the target position information, and a method for obtaining the target image may be: obtaining a virtual 3D target object model corresponding to the target object in the current image; determining a second mask image according to the normal direction and viewing direction of the virtual 3D target object model; and fusing the current image and the virtual object image based on the second mask image to obtain the target image.

In this embodiment, the standard target object model is bound to the posture of the target object in the current image to obtain a virtual 3D target object model. The normal direction of the virtual 3D target object model can be understood as the normal direction of the section where the 3D points in the virtual 3D target object model are located, and the viewing angle direction of the virtual 3D target object model can be the direction in which the optical center of the camera points to the 3D points in the virtual 3D target object model. The method for determining the second mask image based on the normal direction and the viewing angle direction of the virtual 3D target object model can be: dot multiplying the normal direction and the viewing angle direction, and using the dot multiplication result as the pixel value of the pixel point in the second mask image. The method for fusing the current image and the virtual object image based on the second mask image can be: based on The weighted weight is determined according to the pixel value of the pixel point in the second mask image, and the current image and the virtual object image are fused based on the weighted weight. Exemplarily, assuming that the pixel value of the pixel point in the second mask image is c, c is used as the weighted weight of the current image, and 1-c is used as the weighted weight of the virtual object image. The fusion formula can be expressed as: c*current image+(1-c)*virtual object image. In this embodiment, the fusion efficiency can be improved by determining the second mask image based on the normal direction and the viewing direction of the virtual 3D target object model to fuse the current image and the virtual object image.

Optionally, before obtaining the skeleton point position information of the target object in the current image, the following step is also included: gradually rendering and displaying the virtual object in a set order within a set time period according to the initial position information and/or mapping coordinates of multiple vertices of the virtual object.

The setting order can be from top to bottom, from bottom to top, from left to right, or from right to left. The setting duration can be any value between 1 and 2 seconds. The gradual rendering display can be an iterative rendering display or a gradual rendering display in different areas. In this application scenario, when the user enters the clothing fitting tool and a person is detected, the clothing to be tried on begins to be displayed in a gradual display manner.

In this embodiment, the method of iteratively rendering and displaying the virtual object in a set order within a set time length according to the initial position information and/or mapping coordinates of multiple vertices of the virtual object can be: determining the vertices of the virtual object to be displayed at each moment within the set time length according to the initial position information and/or mapping coordinates, and displaying the vertices of the virtual object to be displayed in the screen corresponding to the moment, thereby obtaining a video of the virtual object being gradually displayed. Exemplarily, Figures 5a-5b are example diagrams for displaying virtual objects. As shown in Figure 5a, a portion of clothing is displayed at this moment, and as shown in Figure 5b, the clothing is fully displayed. In this embodiment, iteratively displaying virtual objects can improve the display effect.

The method for iteratively rendering and displaying the virtual object in a set order within a set time length according to the initial position information and/or mapping coordinates of multiple vertices of the virtual object can be: for the current moment within the set time length, determining the control parameters according to the current moment; determining the target reference value of each vertex of the virtual object according to the initial position information and/or mapping coordinates of the vertex; determining the vertex of the virtual object to be displayed at the current moment according to the target reference value and control parameters of each vertex; and rendering the vertices of the virtual object to be displayed at the current moment.

The method of determining the control parameter according to the current moment may be: obtaining the progress of the current moment within the set time length, and determining the control parameter according to the progress. For example, assuming that the set time length is T, the time length between the current moment and the start moment is t, and the progress is t/T, then the progress can be used as the control parameter.

The role of the target reference is to determine whether the vertex of the corresponding virtual object is rendered. The method of determining the target reference of each vertex according to the initial position information and/or mapping coordinates of each vertex of the virtual object can be: for each of the multiple vertices of the virtual object, determine the first reference according to the initial position information of the vertex of the virtual object; sample the gray value from the set noise map according to the mapping coordinates of the vertex of the virtual object, and determine the sampled gray value as the second reference; The consideration and/or the second reference quantity determines a target reference quantity for the vertex.

The initial position information of the vertices of the virtual object can be understood as the initial three-dimensional coordinates of the vertices constituting the virtual object in the world coordinate system, that is, the initial position information includes three coordinate components x, y, and z. The process of determining the first reference amount according to the initial position information of the vertices of the virtual object can be: firstly, the distance between the vertices of the virtual object and the origin after being projected to the xz plane is calculated, and then the distance is linearly transformed, and then the y component is exponentially calculated, and finally the linear transformation result and the exponential transformation result are accumulated to obtain the first reference amount. Among them, the distance between the vertices of the virtual object and the origin after being projected to the xz plane can be expressed as: length(xz), and the exponential calculation of the y component can be expressed as pow(y, a), which means to obtain y to the power of a. Then the calculation formula of the first reference amount can be: first reference amount = (1-b*length(xz))*c+pow(y*d, a)*e, where a, b, c, d and e are set values. Optionally, after obtaining the first reference value, the first reference value may be restricted in value range so that the first reference value is within a set range, and the first reference value after the value range restriction is subjected to exponential calculation. The set range may be 0-1.5.

The mapping coordinates can be understood as the coordinates of the surface map corresponding to the virtual object. The surface map has the same size as the set noise map, that is, the pixels in the two images correspond one to one, so the grayscale value corresponding to each pixel of the surface map can be sampled from the set noise map according to the mapping coordinates, and finally the grayscale value is used as the second reference. Optionally, the second reference can also be multiplied by the set influence factor to obtain the final second reference.

Determining the target reference amount based on the first reference amount and/or the second reference amount can be understood as: using the first reference amount as the target reference amount, or using the second reference amount as the target reference amount, or using the weighted sum of the first reference amount and the second reference amount as the target reference amount. In this embodiment, determining the target reference amount based on the initial position information and/or the mapping coordinates can improve the calculation accuracy.

The method for determining the vertices of the virtual object to be displayed at the current moment based on the target reference value and the control parameter can be: if the target reference value is less than the control parameter, the vertices of the virtual object are not the vertices of the virtual object to be displayed; if the target reference value is greater than or equal to the control parameter, the vertices based on the virtual object are the vertices of the virtual object to be displayed.

The method of rendering the vertices of the virtual object to be displayed at the current moment may be: determining the special effect color of the vertices of the virtual object according to the target reference amount and the control parameter; and rendering the vertices of the virtual object to be displayed at the current moment according to the special effect color.

In this embodiment, if the target reference value is less than the control parameter, it indicates that the vertices of the virtual object corresponding to the target reference value do not need to be rendered at the current moment, so the vertices of the virtual object are ignored. If the target reference value is greater than or equal to the control parameter, it indicates that the vertices of the virtual object corresponding to the target reference value need to be rendered at the current moment. At this time, it is necessary to determine the special effect color corresponding to the vertices of the virtual object, so as to render the virtual object at the current moment according to the special effect color. In this embodiment, the vertices of the virtual object to be rendered at the current moment are determined by comparing the target reference value with the control parameter, so that the virtual object appears to be gradually rendered. The effect of display.

The method of determining the special effect color of the vertex of the virtual object based on the target reference amount and the control parameters can be: obtaining the special effect control range; performing smooth transition processing on the target reference amount based on the special effect control range and the control parameters to obtain the special effect adjustment amount; adjusting the set color based on the special effect adjustment amount to obtain the special effect color.

The upper and lower limits of special effect control. The special effect control range is set by the user and is not limited here.

The smooth transition processing method may be to set a smooth transition processing function, for example, a smoothstep function.

In this embodiment, the process of performing smooth transition processing on the target reference amount based on the special effect control range and the control parameter can be: firstly, performing a first smooth transition processing on the target reference amount based on the control parameter and the special effect control upper limit value to obtain the first sub-special effect adjustment amount; then performing a second smooth transition processing on the target reference amount based on the control parameter, the special effect control upper limit value and the special effect control lower limit value to obtain the second sub-special effect adjustment amount; finally, the first sub-special effect adjustment amount and the second sub-special effect adjustment amount are accumulated to obtain the special effect adjustment amount. Exemplarily, the first smooth transition processing can be expressed as: smoothstep(U, U+a*D1, A), and the second smooth transition processing can be expressed as: smoothstep(U-a*D2, U+a*D1, A), where U represents the control parameter, D1 represents the special effect control upper limit value, D2 represents the special effect control lower limit value, A represents the target reference amount, and a is a set value, for example, a is 0.1.

In this embodiment, the method of adjusting the set color based on the special effect adjustment amount can be: multiplying the special effect adjustment amount by the set color to obtain the special effect color. In this embodiment, the target reference amount is smoothly transitioned based on the special effect control range and control parameters to generate an edge glow effect.

The technical solution of the disclosed embodiment obtains the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; transforms the initial position information of multiple vertices of the virtual object based on the skeleton point position information to obtain the intermediate position information of multiple vertices of the virtual object; updates the intermediate position information of at least part of the vertices of the virtual object based on the set material information to obtain the target position information; renders the virtual object based on the target position information to obtain the target image; wherein the target object in the target image wears the virtual object. The virtual object rendering method provided by the disclosed embodiment transforms the initial position information of multiple vertices of the virtual object based on the skeleton point position information of the target object, and updates the intermediate position information of at least part of the vertices of the virtual object based on the set material information, so that the virtual object being tried on can fit well with the movement of the target object, and can make the virtual object have the dynamic and texture of the real object, thereby improving the rendering effect.

FIG6 is a schematic diagram of the structure of a virtual object rendering device provided by an embodiment of the present disclosure. As shown in FIG6 , the device includes: an acquisition module 610 configured to acquire the bone structure of a target object in a current image; The skeleton point position information and the initial position information of multiple vertices of the virtual object; wherein the multiple vertices of the virtual object are the multiple vertices of the 3D model corresponding to the virtual object; a position information transformation module 620 is configured to transform the initial position information of the multiple vertices based on the skeleton point position information to obtain the intermediate position information of the multiple vertices; a target position information acquisition module 630 is configured to update the intermediate position information of at least part of the multiple vertices of the virtual object based on the set material information to obtain the target position information; a rendering module 640 is configured to render the virtual object based on the target position information to obtain a target image; wherein the target object in the target image wears the virtual object.

Optionally, the position information transformation module 620 is configured to: obtain multiple bone points associated with each vertex of the virtual object and the position influence weights of the multiple bone points on each vertex of the virtual object; determine the vertex transformation information of each vertex based on the position information of the multiple bone points and the position influence weights; transform the initial position information of each vertex based on the vertex transformation information of each vertex to obtain the intermediate position information of each vertex.

Optionally, the target position information acquisition module 630 is configured to: obtain set material information and the motion state of at least some of the vertices of the virtual object; solve the set material of at least some of the vertices of the virtual object according to the intermediate position information of at least some of the vertices, the set material information and the motion state of at least some of the vertices to obtain the target position information.

Optionally, the target position information acquisition module 630 is configured to solve the set material of at least some of the vertices of the virtual object according to the intermediate position information of at least some of the vertices, the set material information and the motion state of at least some of the vertices in the following manner: if a virtual object support body is set in the current scene; obtain support information according to the virtual object support body; solve the set material of at least some of the vertices of the virtual object according to the intermediate position information of at least some of the vertices, the material parameters, the motion state of at least some of the vertices and the support information.

Optionally, the rendering module 640 is configured to: sample preset color information from a color noise map based on the texture coordinates of each vertex of the virtual object; perform offset processing on the preset color information according to the time information of the current image to obtain the offset processed preset color information corresponding to each vertex; adjust the initial color of each vertex of the virtual object according to the offset processed preset color information corresponding to each vertex and the target position information to obtain the target color of each vertex;

The virtual object is rendered based on the target position information and the target color of each vertex to obtain a target image.

Optionally, the rendering module 640 is configured to adjust the initial color of each vertex of the virtual object according to the preset color information after the offset processing corresponding to each vertex and the target position information to obtain the target color of each vertex in the following manner: determining The normal direction and viewing direction of each vertex of the virtual object; determining the color transformation information corresponding to each vertex according to the preset color information after offset processing corresponding to each vertex; determining the color adjustment amount of each vertex according to the color transformation information corresponding to each vertex, the normal direction of each vertex and the viewing direction of each vertex; adding the color adjustment amount of each vertex with the initial color of the vertex of the virtual object to obtain the target color of the vertex.

Optionally, the rendering module 640 is configured to: sample the current image according to the virtual 3D target object model and the virtual object model to obtain a target object sampling map; convert the target object sampling map into a first mask map; fuse the current image and the virtual object map based on the first mask map to obtain a target image; and render the target image to the current screen.

Optionally, the rendering module 640 is configured to fuse the current image and the virtual object image based on the first mask image to obtain a target image in the following manner: blurring the first mask image; and fusing the current image and the virtual object image based on the blurred first mask image to obtain a target image.

Optionally, the rendering module 640 is configured to: obtain a virtual 3D target object model corresponding to the target object in the current image; determine a second mask image according to the normal direction and viewing direction of the virtual 3D target object model; and fuse the current image and the virtual object image based on the second mask image to obtain a target image.

Optionally, it also includes: a virtual object display module, configured to: gradually render and display the virtual object in a set order within a set time period according to the initial position information and/or mapping coordinates of multiple vertices of the virtual object.

Optionally, the virtual object display module is configured to: for the current moment within the set time length, determine the control parameters according to the current moment; determine the target reference value of each vertex of the virtual object according to the initial position information and/or mapping coordinates of each vertex; determine the vertices of the virtual object to be displayed at the current moment according to the target reference value and control parameters of each vertex; and render the vertices of the virtual object to be displayed at the current moment.

The virtual object rendering device provided in the embodiments of the present disclosure can execute the virtual object rendering method provided in any embodiment of the present disclosure, and has the functional modules and effects corresponding to the execution method.

The multiple units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the names of the multiple units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

FIG7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Referring to FIG7 below, it shows a schematic diagram of the structure of an electronic device (e.g., a terminal device or server in FIG7) 500 suitable for implementing an embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include, but is not limited to, a mobile The electronic device shown in FIG7 is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

As shown in FIG. 7 , the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to the bus 504.

Typically, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although FIG. 7 shows an electronic device 500 having a variety of devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

The electronic device provided by the embodiment of the present disclosure and the method for rendering a virtual object provided by the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, reference can be made to the above embodiment, and this embodiment has the same effect as the above embodiment.

The embodiments of the present disclosure provide a computer storage medium on which a computer program is stored. When the program is executed by a processor, the method for rendering a virtual object provided in the above embodiments is implemented.

The computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, RAM, ROM, an erasable programmable read-only memory (EPROM) or flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination of the above.

In some embodiments, the client and the server may communicate using any currently known or future developed network protocol, such as HyperText Transfer Protocol (HTTP), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; transforms the initial position information of the multiple vertices based on the skeleton point position information to obtain the intermediate position information of the multiple vertices; updates the intermediate position information of at least part of the multiple vertices of the virtual object based on the set material information to obtain the target position information; renders the virtual object based on the target position information to obtain the target image; wherein, the target object in the target image wears the virtual object.

Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including (LAN or WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to the various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and/or flow chart, and the combination of the boxes in the block diagram and/or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

The units and modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The names of the units and modules do not limit the units themselves. For example, the acquisition module may also be described as "a module for acquiring the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object".

The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), etc.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Machine-readable storage medium More specific examples would include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM or flash memory, optical fibers, portable CD-ROMs, optical storage devices, magnetic storage devices, or any suitable combination of the above.

Although a plurality of operations are described in a particular order, this should not be construed as requiring these operations to be performed in the particular order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. The various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.

Although the subject matter has been described using language specific to structural features and/or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. The specific features and acts described above are merely example forms of implementing the claims.

Claims

A method for rendering a virtual object, comprising:

Obtaining the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; wherein the multiple vertices of the virtual object are multiple vertices of the three-dimensional 3D model corresponding to the virtual object;

Transforming initial position information of a plurality of vertices based on the position information of the skeleton points to obtain intermediate position information of the plurality of vertices;

Update the intermediate position information of at least some of the vertices of the plurality of vertices of the virtual object based on the set material information to obtain the target position information;

The virtual object is rendered based on the target position information to obtain a target image; wherein the target object in the target image wears the virtual object.
The method according to claim 1, wherein the initial position information of the plurality of vertices is transformed based on the skeleton point position information to obtain the intermediate position information of the plurality of vertices, comprising:

Acquire multiple skeleton points associated with each vertex of the virtual object and position influence weights of the multiple skeleton points on each vertex of the virtual object;

Determine vertex transformation information of each vertex based on the position information of the plurality of skeleton points and the position influence weight;

The initial position information of each vertex is transformed based on the vertex transformation information of each vertex to obtain the intermediate position information of each vertex.
The method according to claim 1, wherein updating the intermediate position information of at least some of the multiple vertices of the virtual object based on the set material information to obtain the target position information comprises:

Acquire set material information and motion states of at least part of the vertices of the virtual object;

The set material of at least part of the vertices of the virtual object is solved according to the intermediate position information of at least part of the vertices, the set material information and the motion state of at least part of the vertices to obtain the target position information.
The method according to claim 3, wherein the step of solving the set material for at least some of the vertices of the virtual object according to the intermediate position information of at least some of the vertices, the set material information and the motion state of at least some of the vertices comprises:

In the case where a virtual object support is provided in the current scene, obtaining support information according to the virtual object support;

According to the intermediate position information of at least some of the vertices, the material parameters, the at least some of the vertices The motion state of the point and the support information are used to solve the material setting for at least part of the vertices of the virtual object.
The method according to claim 1, wherein rendering the virtual object based on the target position information to obtain the target image comprises:

Sampling preset color information from a color noise map based on the texture coordinates of each vertex of the virtual object;

Performing an offset process on the preset color information according to the time information of the current image to obtain the preset color information after the offset process corresponding to each vertex;

Adjusting the initial color of each vertex of the virtual object according to the preset color information after the offset processing corresponding to each vertex and the target position information to obtain the target color of each vertex;

The virtual object is rendered based on the target position information and the target color of each vertex to obtain a target image.
The method according to claim 5, wherein adjusting the initial color of each vertex of the virtual object according to the preset color information after offset processing corresponding to each vertex and the target position information to obtain the target color of each vertex comprises:

Determine the normal direction and viewing angle direction of each vertex of the virtual object according to the target position information;

Determine the color transformation information corresponding to each vertex according to the preset color information corresponding to each vertex after the offset processing;

Determining a color adjustment amount for each vertex according to color transformation information corresponding to each vertex, a normal direction of each vertex, and a viewing direction of each vertex;

The color adjustment amount of each vertex is accumulated with the initial color of each vertex to obtain the target color of each vertex.
The method according to claim 1, wherein rendering the virtual object based on the target position information to obtain the target image comprises:

Sampling the current image according to a virtual 3D target object model and a virtual object model to obtain a target object sampling map; wherein the virtual object model is a 3D model corresponding to the virtual object;

Converting the target object sampling image into a first mask image;

fusing the current image and the virtual object image based on the first mask image to obtain a target image, wherein the virtual object image is a two-dimensional 2D image obtained by projecting the virtual object onto a screen according to the target position information;

Render the target image to the current screen.
The method according to claim 7, wherein fusing the current image and the virtual object based on the first mask image to obtain a target image comprises:

Performing blur processing on the first mask image;

The current image and the virtual object image are fused based on the blurred first mask image to obtain a target image.
The method according to claim 1, characterized in that rendering the virtual object based on the target position information to obtain a target image comprises:

Acquire a virtual 3D target object model corresponding to the target object in the current image;

Determining a second mask image according to the normal direction and the viewing direction of the virtual 3D target object model;

The current image and the virtual object image are fused based on the second mask image to obtain a target image, wherein the virtual object image is a 2D image obtained by projecting the virtual object onto a screen according to the target position information.
The method according to claim 1, wherein before obtaining the skeleton point position information of the target object in the current image, it also includes:

The virtual object is gradually rendered and displayed in a set order within a set time period according to the initial position information and/or mapping coordinates of the multiple vertices of the virtual object.
The method according to claim 10, wherein gradually rendering and displaying the virtual object in a set order within a set time period according to the initial position information and/or mapping coordinates of the multiple vertices of the virtual object comprises:

For a current moment within the set duration, determining a control parameter according to the current moment;

Determine a target reference amount of each vertex of the virtual object according to initial position information and/or mapping coordinates of each vertex;

Determine the vertex of the virtual object to be displayed at the current moment according to the target reference amount of each vertex and the control parameter;

Rendering the vertices of the virtual object to be displayed at the current moment.
A virtual object rendering device, comprising:

An acquisition module, configured to acquire the skeleton point position information of the target object in the current image and the initial position information of multiple vertices of the virtual object; wherein the multiple vertices of the virtual object are multiple vertices of the three-dimensional 3D model corresponding to the virtual object;

A position information transformation module is configured to transform the initial positions of the plurality of vertices based on the position information of the skeleton points. The initial position information is transformed to obtain the intermediate position information of the plurality of vertices;

a target position information acquisition module, configured to update the intermediate position information of at least some of the multiple vertices of the virtual object based on the set material information to obtain the target position information;

A rendering module is configured to render the virtual object based on the target position information to obtain a target image; wherein the target object in the target image wears the virtual object.
An electronic device, comprising:

at least one processor;

a storage device configured to store at least one program,

When the at least one program is executed by the at least one processor, the at least one processor implements the virtual object rendering method as described in any one of claims 1-11.
A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the virtual object rendering method as claimed in any one of claims 1 to 11 when executed by a computer processor.