WO2023045961A1 - Virtual object generation method and apparatus, and electronic device and storage medium - Google Patents

Abstract

The present disclosure relates to a virtual object generation method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring, from an original virtual object, a target part to be processed; according to hue information of the target part, dividing the target part into a plurality of target regions; according to a preset color parameter, respectively performing, on the plurality of target regions, rendering processing that matches the hues of the target regions, so as to obtain a plurality of rendering results; and on the basis of the plurality of rendering results, generating a target virtual object.

Description

Method and device for generating virtual object, electronic device and storage medium

Cross References to Related Applications

This disclosure is based on the Chinese patent application with the application number 202111137693.5, the application date is September 27, 2021, and the application name is "virtual object generation method and device, electronic equipment and storage medium", and requires the priority of the Chinese patent application Right, the entire content of this Chinese patent application is hereby incorporated into this disclosure as a reference.

technical field

The present disclosure relates to the field of computer vision, and relates to a method and device for generating a virtual object, electronic equipment and a storage medium.

Background technique

With the development of computer vision technology, virtual objects that can interact with users have been more and more widely used in people's lives, such as anthropomorphic objects in various smart devices.

However, with different application scenarios, these anthropomorphic objects may need to be changed in image or color. How to make the changed objects still have a more realistic and natural character effect has become an urgent problem to be solved.

Contents of the invention

The present disclosure proposes a virtual object generation scheme.

According to an aspect of the present disclosure, there is provided a method comprising:

Obtain the target part to be processed in the original virtual object; divide the target part into multiple target areas according to the color tone information of the target part; A plurality of rendering results are obtained through the rendering processing of the tone matching of the target area; based on the plurality of rendering results, a target virtual object is generated.

In a possible implementation manner, the obtaining the target part to be processed in the original virtual object includes: obtaining the original virtual object, wherein the original virtual object is generated according to virtual information; according to the virtual information, the The target part to be processed is extracted from the original virtual object.

In a possible implementation manner, the virtual information includes at least one of the following: preset virtual object generation information, and virtual object control information generated in response to user actions.

In a possible implementation manner, the tone information includes at least one of the following: highlight information, shadow information, and midtone information; according to the tone information of the target portion, the target portion is divided into multiple targets The area includes at least one of the following: based on the highlight information of the target part, a highlight area is extracted from the target part; based on the shadow information of the target part, a shadow area is extracted from the target part; The midtone information of the target part is extracted from the target part to obtain a midtone area.

In a possible implementation manner, the extracting the highlight area from the target part based on the highlight information of the target part includes: performing multiplicative blending based on the grayscale image of the target part to obtain The first mixing result; according to the first mixing result, determine the first transparency of the pixels in the target part; according to the first preset transparency threshold and the first transparency, perform a process on the pixels in the target part Extract to get the highlight area.

In a possible implementation manner, the extracting the shadow area from the target part based on the shadow information of the target part includes: performing multiplication and blending based on the reverse grayscale image of the target part , to obtain the second mixed result; according to the second mixed result, determine the second transparency of the pixel in the target part; according to the second preset transparency threshold and the second transparency, for the pixel in the target part Points are extracted to get the shaded area.

In a possible implementation manner, the extracting the midtone area from the target part based on the midtone information of the target part includes: performing exclusion mixing based on the grayscale image of the target part to obtain The third mixing result; according to the third mixing result, determine the third transparency of the pixels in the target part; according to the third preset transparency threshold and the third transparency, perform a process on the pixels in the target part Extract to obtain the midtone region.

In a possible implementation manner, the performing rendering processing on the multiple target areas according to the preset color parameters to match the color tone of the target areas to obtain multiple rendering results includes: Color parameters are set, and the multiple target areas are respectively rendered to obtain multiple intermediate rendering results; according to the hues of the multiple target areas, the processing methods corresponding to the multiple target areas are determined; The processing manners corresponding to the target areas respectively mix the grayscale images of the target parts with the multiple intermediate rendering results to obtain multiple rendering results.

In a possible implementation manner, the target area includes at least one of the following: a highlight area, a shadow area, and a midtone area; according to the hues of the multiple target areas, it is determined that the multiple target areas correspond to The processing method includes: in the case that the target area includes a highlight area, determining that the processing method includes color filter blending; in the case that the target area includes a shadow area, determining that the processing method includes multiply blending ; If the target area includes a midtone area, determine that the processing method includes normal mixing.

In a possible implementation manner, the generating the target virtual object based on the multiple rendering results includes: superimposing the multiple rendering results to obtain the target rendering result; based on preset rendering parameters, using the The target rendering result renders the target part in the original virtual object to obtain the target virtual object.

In a possible implementation manner, the method further includes: in response to an interaction operation on the target virtual object, controlling the target virtual object to perform matching with the interaction information according to interaction information in the interaction operation. virtual action.

According to an aspect of the present disclosure, a device for generating a virtual object is provided, including:

The acquisition part is used to obtain the target part to be processed in the original virtual object; the division part is used to divide the target part into multiple target areas according to the hue information of the target part; the rendering part is used to divide the target part into multiple target areas according to the preset The color parameter is used to perform rendering processing on the multiple target areas to match the color tone of the target areas to obtain multiple rendering results; the generating part is configured to generate the target virtual object based on the multiple rendering results.

In a possible implementation manner, the acquiring part is configured to: acquire an original virtual object, wherein the original virtual object is generated according to virtual information; extract the original virtual object from the original virtual object according to the virtual information Describe the target site to be treated.

In a possible implementation manner, the virtual information includes at least one of the following: preset virtual object generation information, and virtual object control information generated in response to user actions.

In a possible implementation manner, the tone information includes at least one of the following: highlight information, shadow information, and midtone information; the division part is used for at least one of the following: based on the highlight information of the target part, from extracting a highlight area from the target part; extracting a shadow area from the target part based on the shadow information of the target part; extracting a midtone from the target part based on the midtone information of the target part area.

In a possible implementation manner, the dividing part is further configured to: perform multiply blending based on the grayscale image of the target part to obtain a first blending result; determine the first blending result according to the first blending result The first transparency of the pixels in the target part; according to the first preset transparency threshold and the first transparency, extract the pixels in the target part to obtain the highlight area.

In a possible implementation manner, the dividing part is further configured to: perform multiplicative blending based on the reverse grayscale image of the target part to obtain a second blending result; according to the second blending result, Determine the second transparency of the pixels in the target part; extract the pixels in the target part according to a second preset transparency threshold and the second transparency to obtain the shadow area.

In a possible implementation manner, the dividing part is further configured to: perform exclusion mixing based on the grayscale image of the target part to obtain a third mixing result; determine the target The third transparency of the pixels in the part; according to the third preset transparency threshold and the third transparency, extract the pixels in the target part to obtain the midtone area.

In a possible implementation manner, the rendering part is configured to: respectively render the multiple target areas according to the preset color parameters to obtain multiple intermediate rendering results; Tone, determine the processing methods corresponding to the multiple target areas respectively; according to the processing modes corresponding to the multiple target areas, respectively mix the grayscale image of the target part with the multiple intermediate rendering results , to get multiple rendering results.

In a possible implementation manner, the target area includes at least one of the following: a highlight area, a shadow area, and a midtone area; the rendering part is further configured to: when the target area includes a highlight area, determining that the processing includes screen blending; determining that the processing includes multiply blending if the target area includes a shadow area; determining that the processing includes a midtone area if the target area includes a Methods include normal mixing.

In a possible implementation manner, the generating part is configured to: superimpose the multiple rendering results to obtain a target rendering result; based on preset rendering parameters, use the target rendering result to process the original virtual object Render the target part in the image to obtain the target virtual object.

In a possible implementation manner, the device is further configured to: in response to an interaction operation on the target virtual object, according to interaction information in the interaction operation, control the target virtual object to perform an interaction with the target virtual object. Information matching virtual action.

According to an aspect of the present disclosure, there is provided an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to: execute the method for generating the above-mentioned virtual object.

According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above method for generating a virtual object is realized.

According to an aspect of the present disclosure, a computer program product is provided, the computer program product includes a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is executed to realize the above virtual object. generate method.

In the embodiment of the present disclosure, by responding to the acquisition of the target parts to be processed in the original virtual object, and according to the hue information of the target parts, the target parts are divided into multiple target areas, and according to the preset color parameters, the multiple target parts The areas are respectively subjected to rendering processing matching the tone of the target area to obtain multiple rendering results, and the target virtual object is generated according to the multiple rendering results. Through the above process, based on the hue of the target part of the virtual object, the target part can be divided into multiple target areas, and corresponding rendering processing is performed on the multiple target areas, so that in the process of changing the image of the virtual object, Using the original tone information of the original virtual object, the target virtual object with a more realistic and natural effect can still be obtained. For example, the target part can be divided into a highlight area, a shadow area, and a mid-tone area according to the tones such as highlights, shadows, and mid-tones. In the process of rendering the highlight area, increase the rendering brightness as much as possible, in the process of rendering the shadow area, reduce the rendering brightness as much as possible, and in the process of rendering the midtone area, keep the The brightness of the rendering enables the rendering effect of the target virtual object to match the original tone distribution of the original virtual object, improving the authenticity and naturalness of the target virtual object.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Description of drawings

The accompanying drawings here are incorporated into the description and constitute a part of the present description. These drawings show embodiments consistent with the present disclosure, and are used together with the description to explain the technical solution of the present disclosure.

Fig. 1 shows a flowchart of a method for generating a virtual object according to an embodiment of the present disclosure.

FIG. 2 shows a schematic diagram of a target site according to an embodiment of the present disclosure.

FIG. 3 shows a schematic diagram of a first mixing result according to an embodiment of the present disclosure.

FIG. 4 shows a schematic diagram of a highlight region according to an embodiment of the disclosure.

FIG. 5 shows a schematic diagram of a second mixing result according to an embodiment of the present disclosure.

FIG. 6 shows a schematic diagram of a shaded area according to an embodiment of the present disclosure.

FIG. 7 shows a schematic diagram of a third mixing result according to an embodiment of the present disclosure.

FIG. 8 shows a schematic diagram of a midtone region according to an embodiment of the present disclosure.

Fig. 9 shows a schematic diagram of a rendering result of a highlight area according to an embodiment of the present disclosure.

Fig. 10 shows a schematic diagram of a rendering result of a shadow area according to an embodiment of the present disclosure.

Fig. 11 shows a schematic diagram of a rendering result of a midtone region according to an embodiment of the present disclosure.

Fig. 12 shows a schematic diagram of a target virtual object according to an embodiment of the present disclosure.

Fig. 13 shows a block diagram of an apparatus for generating a virtual object according to an embodiment of the present disclosure.

Fig. 14 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Fig. 15 shows a block diagram of an electronic device according to an embodiment of the present disclosure.

Detailed ways

For purposes of the following, various exemplary embodiments, features, and aspects of the present disclosure will be described in detail with reference to the accompanying drawings. The same reference numbers in the figures indicate functionally identical or similar elements. While various aspects of the embodiments are shown in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as superior or better than other embodiments.

The term "and/or" in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B can mean: A exists alone, A and B exist simultaneously, and there exists alone B these three situations. In addition, the term "at least one" herein means any one of a variety or any combination of at least two of the more, for example, including at least one of A, B, and C, which may mean including from A, Any one or more elements selected from the set formed by B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific implementation manners. It will be understood by those skilled in the art that the present disclosure may be practiced without some of the specific details. In some instances, methods, means, components and circuits that are well known to those skilled in the art have not been described in detail so as to obscure the gist of the present disclosure.

Fig. 1 shows a flowchart of a method for generating a virtual object according to an embodiment of the present disclosure, the method can be applied to a virtual object generation device or a virtual object generation system, etc., the virtual object generation device can be a terminal device, a server or other processing equipment, etc. Wherein, the terminal device may be user equipment (User Equipment, UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (Personal Digital Assistant, PDA), handheld device, computing device, vehicle-mounted device, Wearable equipment etc. In an example, this can be applied to a cloud server or a local server, and the cloud server can be a public cloud server or a private cloud server, which can be flexibly selected according to actual conditions.

In some possible implementation manners, this may also be implemented by the processor calling computer-readable instructions stored in the memory.

As shown in Figure 1, in a possible implementation manner, the description may include:

Step S11, acquiring the target part to be processed in the original virtual object.

Among them, the original virtual object can be any virtual object that needs image change, for example, it can be a digital virtual object that is displayed on the screen of a smart device such as a computer and interacts with the user, such as a digital human, or displayed on the screen , and can be driven according to the actions of the user, a virtual class object that follows the actions of the user, such as network avatars such as Avatar (Avatar).

The target part can be any part of the original virtual object that needs image transformation. Which parts are included in the target part, the realization form can be flexibly determined according to the actual situation. For example, the target part can be the hair part, face part, lip part or eye part. Parts, etc., with different target parts, the way of processing the original virtual object can also be flexibly changed.

The implementation of step S11 can be flexibly determined according to the actual situation, see the following disclosed embodiments for details, and will not be expanded here.

Step S12, dividing the target part into a plurality of target regions according to the hue information of the target part.

Wherein, the hue information may reflect the relative lightness and darkness of the target part. Information contained in the hue information may be flexibly determined according to actual conditions. In a possible implementation manner, the hue information may include at least one of the following: highlight information, shadow information, and midtone information.

Among them, the highlight information can reflect the region with higher brightness in the target part, the shadow information can reflect the region with lower brightness in the target part, and the midtone information can reflect the region in the target part whose brightness is between the highlight and the shadow.

Different hue information can be determined from the target part through different hue methods. In some possible implementations, the above-mentioned hue information can be obtained directly according to the brightness of the pixel in the target part. In some possible implementations, it can also be The target part is processed in different ways to obtain different hue information. The manner of acquiring hue information can be referred to the following disclosed embodiments in detail, and will not be expanded here.

The area type and area position contained in the target area can be flexibly determined according to the actual situation of the tone information in the target area. There may be overlapping areas between multiple target areas, and they may also be independent of each other. In the embodiment of the present disclosure, no Do limit.

In some possible implementation manners, the target area may include at least one of the following: a highlight area, a shadow area, and a midtone area.

According to the hue information, the method of dividing the target part into multiple target areas can be flexibly changed with the different hue information. For example, according to the obtained highlight information, shadow information and midtone information, the pixels in the target part Divided into highlight area, shadow area and midtone area etc. For some possible implementation manners of step S12, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

Step S13 , according to preset color parameters, perform rendering processing on the multiple target areas to match the color tone of the target areas, to obtain multiple rendering results.

Wherein, the preset color parameter may be a relevant color for rendering the target part, and the format of the preset color parameter may be a color value or an RGB channel value. For multiple target areas, the preset color parameters corresponding to different target areas may be the same or different, and may be flexibly set according to actual conditions, and are not limited to the embodiments of the present disclosure.

The rendering result may be a result obtained after the target area is rendered. Depending on the target area, the rendering processing manner may also be different. Therefore, corresponding rendering processing may be performed on multiple target areas to obtain multiple rendering results. For some possible implementation manners of step S13, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

Step S14, generating a target virtual object according to multiple rendering results.

Among them, the target virtual object can be a virtual object obtained by changing or processing the target part of the original virtual object. The method of generating the target virtual object can be flexibly determined according to the actual situation. For example, multiple rendering results can be fused to obtain the target virtual object, or combine multiple rendering results with the original virtual object to obtain the target virtual object. In some possible implementation manners, multiple rendering results may also respectively belong to multiple layers. In this case, the target virtual object may be obtained by superimposing layers.

For some possible implementation manners of step S14, reference may be made to the following disclosed embodiments in detail, which will not be expanded here.

In the embodiment of the present disclosure, by responding to the acquisition of the target parts to be processed in the original virtual object, and according to the hue information of the target parts, the target parts are divided into multiple target areas, and according to the preset color parameters, the multiple target parts The areas are respectively subjected to rendering processing matching the tone of the target area to obtain multiple rendering results, and the target virtual object is generated according to the multiple rendering results. Through the above process, based on the hue of the target part of the virtual object, the target part can be divided into multiple target areas, and corresponding rendering processing is performed on the multiple target areas, so that in the process of changing the image of the virtual object, Using the original tone information of the original virtual object, the target virtual object with a more realistic and natural effect can still be obtained. For example, the target part can be divided into a highlight area, a shadow area, and a mid-tone area according to the tones such as highlights, shadows, and mid-tones. In the process of rendering the highlight area, increase the rendering brightness as much as possible, in the process of rendering the shadow area, reduce the rendering brightness as much as possible, and in the process of rendering the midtone area, keep the The brightness of the rendering enables the rendering effect of the target virtual object to match the original tone distribution of the original virtual object, improving the authenticity and naturalness of the target virtual object.

In a possible implementation manner, step S11 may include:

Obtaining an original virtual object, wherein the original virtual object is generated according to virtual information;

According to the virtual information, the target part to be processed is extracted from the original virtual object.

For the implementation form of the original virtual object, reference may be made to the above disclosed embodiments. In a possible implementation manner, the original virtual object may be generated according to virtual information.

Virtual information can be electronic data or information stored in various smart devices or servers, and the information content included in virtual information can also change with different types of virtual objects.

For example, for digital humans and other virtual objects that interact with users according to system control, the virtual information may include virtual object generation information preset in the system, and the preset virtual object generation information may be used to generate the original virtual object, including The information content is not limited in this embodiment of the present disclosure, for example, it may include an image of the target part in the original virtual object or a position of the target part in the original image of the original virtual object.

In an example, for virtual objects such as Avatars that can be driven according to user actions, the virtual information may include at least one of the following: preset virtual object generation information, virtual object control information generated in response to user actions, the The control information may respond to the user's action to control the action of the original virtual object and content such as sound, so as to realize the interaction between the original virtual object and the user. The information contained in the control information is not limited in this embodiment of the present disclosure. In an example, the control information may also include the image of the target part in the original virtual object or the image of the target part in the original image of the original virtual object. location etc.

As described in the above disclosed embodiments, the content of information contained in the virtual information may be different, so the manner of acquiring the target part according to the virtual information can also be flexibly selected. For example, images of target parts can be obtained directly from virtual information, such as hair textures, lip textures, or eye textures. Fig. 2 shows a schematic diagram of a target part according to an embodiment of the present disclosure. It can be seen from the figure that in an example, a hair texture can be obtained directly from virtual information to obtain a target part.

In some possible implementation manners, the image of the target part can also be obtained by intercepting or extracting from the original image of the original virtual object according to the position of the target part in the virtual information.

Through the embodiments of the present disclosure, the target part to be processed can be directly acquired according to the virtual information of the original virtual object, and the acquisition method is simple and fast, thereby improving the efficiency of the entire virtual object generation process.

In a possible implementation manner, step S12 may include at least one of the following:

Step S121 , based on the highlight information of the target part, a highlight region is extracted from the target part.

Step S122, based on the shadow information of the target part, the shadow area is extracted from the target part.

Step S123 , based on the midtone information of the target part, a midtone area is extracted from the target part.

Wherein, the numbers of step S121, step S122, and step S123 are only used to distinguish the above-mentioned different steps, and do not limit the implementation order of different steps. Different steps can be executed simultaneously or sequentially, and the order is in the embodiments of the present disclosure. No restrictions. Step S12 may include the above three steps at the same time, and may also selectively execute some of the steps.

Through the embodiments of the present disclosure, the target part can be flexibly divided into at least one of the highlight area, shadow area, and mid-tone area according to at least one of the highlight information, shadow information, and mid-tone information, thereby effectively improving the accuracy of the target. The flexibility of parts processing facilitates flexible and fast generation of virtual objects.

In a possible implementation, step S121 may include:

Based on the grayscale image of the target part, perform multiplication and bottom blending to obtain the first blending result;

determining the first transparency of the pixels in the target part according to the first mixing result;

According to the first preset transparency threshold and the first transparency, pixel points in the target part are extracted to obtain a highlight area.

Wherein, the grayscale image of the target part may be an image obtained by performing grayscale processing on the target part. Multiply blending based on the grayscale image of the target part may be to blend the grayscale image of the target part itself to obtain the first blending result. Specifically, it may be to combine the grayscale image of the target part After the image is copied, multiply and blend based on two identical grayscale images to obtain the first blending result. Fig. 3 shows a schematic diagram of a first blending result according to an embodiment of the present disclosure. As shown in the figure, in an example, the first blending result obtained by processing a grayscale image can reflect highlight information of a target part .

Therefore, based on the first mixing result, the highlight area in the target site can be further determined.

In some embodiments, the alpha channel value of each pixel in the first mixed result can be obtained, and the alpha channel value can be mapped to a transparency value through the mapping relationship between grayscale and transparency, so as to determine the value of each pixel in the target part The first transparency of the point. The specific mapping manner of the mapping relationship can be flexibly set according to the actual situation, and is not limited in this embodiment of the present disclosure.

The first preset threshold may be a preset threshold for filtering the pixel points belonging to the highlight area in the target part, and the specific value of the first preset threshold is not limited in this embodiment of the present disclosure.

According to the first preset threshold, it can be judged whether the first transparency of each pixel in the target part is within the range of the first preset threshold, and the first transparency of each pixel in the target part is within the range of the first preset threshold In the case of , it is determined that the pixel belongs to the highlight area. If the first transparency of each pixel in the target part is not within the range of the first preset threshold, the pixel is considered to belong to an area other than the highlight area. Through the above In the screening process, a plurality of pixel points belonging to the high-light area can be obtained from the target part by screening, and then the pixel points belonging to the high-light area in the target part are extracted to obtain the high-light area. FIG. 4 shows a schematic diagram of a highlight area according to an embodiment of the present disclosure. It can be seen from FIG. 4 that the highlight area can be effectively and accurately extracted from a target part through the method proposed by the embodiment of the present disclosure.

Through the embodiments of the present disclosure, the first blending result reflecting the highlight information can be obtained by multiplying and blending the grayscale image of the target part, so that the highlight region can be extracted from the target part according to the blending result. This method of obtaining highlight information The method is fast and convenient, and has high accuracy. While improving the processing efficiency of the target part, it can effectively improve the accuracy of the target part after processing, and then improve the real effect of the generated target virtual object.

In a possible implementation manner, step S122 may include:

Based on the reverse grayscale image of the target part, perform positive and bottom blending to obtain the second blending result;

determining the second transparency of the pixels in the target part according to the second mixing result;

According to the second preset transparency threshold and the second transparency, pixel points in the target part are extracted to obtain a shadow area.

Wherein, the reverse grayscale image of the target part can be an image obtained by performing reverse grayscale processing on each pixel in the target part, and the reverse grayscale can perform linear or non-linear processing on the image grayscale range of the target part. Invert to get the image opposite to the grayscale image of the target site. Multiply blending based on the reverse grayscale image of the target part, which can be mixed in the form of multiplying the reverse grayscale image of the target part itself to obtain the second blending result. The implementation form can refer to Based on the target part The way the grayscale image is multiplied and blended to get the first blended result. Fig. 5 shows a schematic diagram of a second blending result according to an embodiment of the present disclosure. As shown in the figure, in an example, the second blending result obtained by processing the grayscale image can reflect the shadow information of the target part .

Therefore, based on the second mixing result, the shadow area in the target site can be further determined.

In some embodiments, the alpha channel value of each pixel in the second mixed result can be obtained, and the alpha channel value can be mapped to a transparency value through the mapping relationship between grayscale and transparency, so as to determine the value of each pixel in the target part Secondary transparency of the point. For the mapping relationship, reference may be made to the above disclosed embodiments.

The second preset threshold may be a preset threshold used to filter the pixels belonging to the shaded area in the target part, and the specific value of the second preset threshold is not limited in this embodiment of the present disclosure. In a possible implementation manner, the second preset threshold is different from the first preset threshold.

According to the second preset threshold, it can be judged whether the second transparency of each pixel in the target part is within the range of the second preset threshold, and the second transparency of each pixel in the target part is within the range of the second preset threshold In the case of , it is determined that the pixel belongs to the shaded area. If the second transparency of each pixel in the target part is not within the range of the second preset threshold, the pixel is considered to belong to an area other than the shaded area. Through the above In the screening process, a plurality of pixel points belonging to the shadow area may be screened from the target part, and then the pixel points belonging to the shadow area in the target part are extracted to obtain the shadow area. FIG. 6 shows a schematic diagram of a shadow area according to an embodiment of the present disclosure. It can be seen from FIG. 6 that the shadow area can be effectively and accurately extracted from the target part through the method proposed by the embodiment of the present disclosure.

Through the embodiments of the present disclosure, the second blending result reflecting the shadow information can be obtained by multiplying and blending the reverse grayscale image of the target part, so as to extract the shadow area from the target part according to the blending result. This acquisition The method of shadow information is fast and convenient, and it is convenient to perform batch processing at the same time as the method of obtaining highlight information, with high accuracy, which further improves the determination efficiency and processing accuracy of the target part, and then improves the display effect of the target virtual object.

In a possible implementation manner, step S123 may include:

Based on the grayscale image of the target part, performing exclusion mixing to obtain a third mixing result;

determining the third transparency of the pixels in the target part according to the third mixing result;

According to the third preset transparency threshold and the third transparency, the pixels in the target part are extracted to obtain a midtone area.

For the implementation form of the grayscale image of the target part, reference may be made to the above disclosed embodiments. Excluding and mixing based on the grayscale image of the target part may be to mix the grayscale image of the target part itself in a form of exclusion to obtain a third mixed result, and its implementation form may refer to the above-mentioned disclosed embodiments. Wherein, the exclusion mixing can be an image mixing mode in PS (Photoshop) editing software, which can change the brightness and gray scale of the image, and based on the result of the exclusion mixing, the middle tone information of the target part can be obtained. Fig. 7 shows a schematic diagram of a third blending result according to an embodiment of the present disclosure. As shown in Fig. 7, in an example, the third blending result obtained by processing the grayscale image can reflect the middle of the target part call information.

Therefore, based on the third mixing result, the midtone region in the target site can be further determined.

In some embodiments, the alpha channel value of each pixel in the third mixed result can be obtained, and the alpha channel value can be mapped to a transparency value through the mapping relationship between grayscale and transparency, so as to determine the value of each pixel in the target part The third transparency of the point. For the mapping relationship, reference may be made to the above disclosed embodiments.

The third preset threshold may be a preset threshold used to filter the pixels belonging to the midtone area in the target part, and the specific value of the third preset threshold is not limited in this embodiment of the present disclosure. In a possible implementation manner, the third preset threshold is different from the second preset threshold and the first preset threshold.

According to the third preset threshold, it can be judged whether the third transparency of each pixel in the target part is within the range of the third preset threshold, and the third transparency of each pixel in the target part is within the range of the third preset threshold In the case of , it is determined that the pixel belongs to the midtone area, and if the third transparency of each pixel in the target part is not within the range of the third preset threshold, the pixel is considered to belong to an area other than the midtone area, Through the above screening process, a plurality of pixel points belonging to the midtone region can be obtained from the target part by screening, and then the pixel points belonging to the midtone region in the target part are extracted to obtain the midtone region. Fig. 8 shows a schematic diagram of a midtone region according to an embodiment of the present disclosure. It can be seen from the figure that the midtone region can be effectively and accurately extracted from the target part through the method proposed by the embodiment of the present disclosure.

Through the embodiments of the present disclosure, the grayscale image of the target part can be excluded and mixed to obtain the third mixed result reflecting the midtone information, so that the midtone area can be extracted from the target part according to the mixed result. This method of obtaining the midtone The information method is fast and convenient, and it is convenient to perform batch processing at the same time as the method of obtaining highlight information and shadow information, thereby improving the overall efficiency of virtual object generation and the display effect of virtual objects.

In a possible implementation, step S13 may include:

In step S131 , according to the preset color parameters, the multiple target regions are respectively rendered to obtain multiple intermediate rendering results.

Step S132, according to the hues of the multiple target areas, determine the processing modes corresponding to the multiple target areas.

In step S133 , according to the corresponding processing methods of the multiple target regions, the grayscale image of the target part is mixed with multiple intermediate rendering results to obtain multiple rendering results.

Wherein, the intermediate rendering result may be a rendering result obtained after rendering preset color parameters to the target area. For the implementation form of the preset color parameters, reference may be made to the above disclosed embodiments. The preset color parameters can be flexibly set according to requirements.

Among the multiple target areas, different target areas may correspond to the same preset color parameters, or may correspond to different preset color parameters, which can be flexibly selected according to the actual situation. In a possible implementation manner, each target area may be mixed with a corresponding preset color parameter to obtain an intermediate rendering result corresponding to each target area.

Since different target areas can be divided based on different tone information, different target areas can correspond to different tones, as mentioned in the above disclosed embodiments, the highlight area corresponds to the highlight, the shadow area corresponds to the shadow, and the midtone area corresponds to the midtone wait.

Target areas with different hues can be processed in different ways, and the corresponding relationship between hues and processing methods can be found in the following disclosed embodiments in detail, and will not be expanded here.

After the processing method of each target area is determined, the target part can be mixed with each intermediate rendering result according to the processing method, so as to obtain multiple rendering results.

Through the embodiments of the present disclosure, according to the hues corresponding to different target areas, the corresponding processing methods can be mixed for each target area to obtain the rendering results of each target area, so that different target areas can have colors corresponding to the hue. The rendering effect effectively improves the accuracy and richness of the overall virtual object generation effect, and also improves the flexibility of the virtual object generation process.

In a possible implementation manner, step S132 may include:

In the case where the target area includes a highlight area, determine that the processing method includes color filter blending;

Where the target area includes shaded areas, determine that the processing includes multiply blending;

Where the target area includes the midtone area, it is determined that the processing includes normal mixing.

It can be seen from the above disclosed embodiments that, when the target area is a high-light area, the intermediate rendering result of the high-light area and the target part may be mixed in a color-filtering manner to obtain a rendering result of the high-light area. FIG. 9 shows a schematic diagram of a rendering result of a highlight region according to an embodiment of the present disclosure. It can be seen from the figure that color filter blending can make the blending result brighter, thereby fully retaining the tonal properties of the highlight region and improving the processing effect.

In the case that the target area is a shadow area, the intermediate rendering effect of the shadow area and the target part may be mixed in a multiply blending manner to obtain a rendering result of the shadow area. FIG. 10 shows a schematic diagram of the rendering result of the shadow area according to an embodiment of the present disclosure. It can be seen from the figure that multiply blending can darken the blending result, thereby fully retaining the tonal properties of the shadow area and improving the processing effect.

In the case that the target area is a midtone area, the intermediate rendering effect of the midtone area and the target part may be mixed in a normal mixing manner to obtain a rendering result of the midtone area. Fig. 11 shows a schematic diagram of the rendering result of the midtone region according to an embodiment of the present disclosure. It can be seen from the figure that normal blending has little influence on the brightness of the blending result, thereby fully retaining the tonal properties of the midtone region and improving processing Effect.

It can be seen from the above-mentioned disclosed embodiments that, for the hues of different target areas, different mixing methods are used for mixing, which can make the obtained rendering results consistent with the original hue properties of the target parts, thereby greatly improving the quality of the generated target virtual objects. authenticity.

In a possible implementation, step S14 may include:

Step S141, superimposing multiple rendering results to obtain a target rendering result;

Step S142, according to the preset rendering, render the target lip makeup result and the target part in the original virtual object to obtain the target user image.

In a possible implementation manner, the above-mentioned multiple target areas can be determined in multiple layers respectively. In this case, the multiple rendering results obtained can also belong to multiple layers respectively. Therefore, in a In the example, the rendering results in multiple layers can be superimposed to obtain the target rendering result.

The way of overlay can be flexibly decided according to the actual situation, for example, it can be direct overlay between layers, and in some possible implementations, overlay can also be realized through some or some mixed methods, for example, multiple layers can be passed through Multiply the way to mix and overlay.

In a possible implementation manner, multiple rendering results may also be directly fused or mixed to obtain a target rendering result.

After the target rendering result is obtained, the target rendering result and the target part in the original virtual object can be rendered according to the preset rendering parameters to obtain the target virtual object. The rendering method is also not limited in this embodiment of the disclosure, for example, The pixel values of the same position pixels are added or multiplied to achieve rendering, or the pixel values of the same position pixels are weighted and fused.

The fusion weight of the target rendering result in the weighted fusion may be determined according to preset rendering parameters, and the preset rendering parameter may be a preset parameter value used to indicate the weight of the target rendering result in the rendering process.

In a possible implementation, the preset rendering parameter can be transparency. The target rendering result can be multiplied by the transparency and then added to the target part of the original virtual object to obtain the target virtual object. By changing the preset rendering The transparency in the parameter can change the transparency effect of the entire target virtual object.

FIG. 12 shows a schematic diagram of a target virtual object according to an embodiment of the present disclosure. It can be seen from the figure that a target virtual object with a more realistic and natural effect can be obtained through the method for generating a virtual object proposed by each embodiment of the present disclosure.

Through the embodiments of the present disclosure, the target part in the original virtual object can be rendered by using the target rendering result according to the preset rendering parameters to obtain the target virtual object. By changing the preset rendering parameters, the effect of the target virtual object can be easily Adjustment, so as to improve the flexibility and autonomy of the whole target virtual object generation process.

In a possible implementation manner, the method proposed in the embodiment of the present disclosure may further include:

In response to the interactive operation on the target virtual object, according to the interaction information in the interactive operation, the target virtual object is controlled to perform a virtual action matching the interaction information.

Wherein, the interactive operation may be an interactive instruction issued by the user to the target virtual object, such as controlling the target virtual object to change an action or speak, or to transmit information to the target virtual object.

The interaction information may be related information input by the user during the interaction operation, such as text instruction information, voice instruction information, or touch instruction information.

According to the interaction information, the target virtual object can be controlled to perform virtual actions that match the interaction information. For example, the interaction information can instruct the target virtual object to perform actions such as dancing or directing, and the target virtual object can be controlled to perform such actions according to the interaction information.

Through the embodiments of the present disclosure, the interaction between the target virtual object and the user can be realized, and the application range and practicability of the generated target virtual object can be improved.

Fig. 13 shows a block diagram of an apparatus for generating a virtual object according to an embodiment of the present disclosure. As shown in the figure, the virtual object generation device 20 may include:

The acquiring part 21 is configured to acquire the target part to be processed in the original virtual object.

The division part 22 is configured to divide the target site into a plurality of target areas according to the tone information of the target site.

The rendering part 23 is configured to, according to preset color parameters, respectively perform rendering processing on the multiple target areas to match the color tone of the target areas, and obtain multiple rendering results.

The generation part 24 is configured to generate the target virtual object based on the plurality of rendering results.

In a possible implementation manner, the obtaining part is configured to: obtain an original virtual object, wherein the original virtual object is generated according to virtual information; and extract a target part to be processed from the original virtual object according to the virtual information.

In a possible implementation manner, the virtual information includes at least one of the following: preset virtual object generation information, and virtual object control information generated in response to user actions.

In a possible implementation manner, the tone information includes at least one of the following: highlight information, shadow information, and midtone information; the division part is configured as at least one of the following: based on the highlight information of the target part, the A highlight area; based on the shadow information of the target part, a shadow area is extracted from the target part; based on the midtone information of the target part, a midtone area is extracted from the target part.

In a possible implementation manner, the dividing part is further configured to: perform multiply and bottom blending based on the grayscale image of the target part to obtain a first blending result; determine the first blending result of the pixel in the target part according to the first blending result - Transparency: according to the first preset transparency threshold and the first transparency, the pixel points in the target part are extracted to obtain a highlight area.

In a possible implementation manner, the division part is further configured to: perform multiply and bottom blending based on the reverse grayscale image of the target part to obtain a second blending result; determine the pixel points in the target part according to the second blending result the second transparency; according to the second preset transparency threshold and the second transparency, pixel points in the target part are extracted to obtain a shadow area.

In a possible implementation, the dividing part is further configured to: perform exclusion mixing based on the grayscale image of the target part to obtain a third mixing result; determine the third transparency of the pixels in the target part according to the third mixing result ; According to the third preset transparency threshold and the third transparency, extract the pixels in the target part to obtain the midtone area.

In a possible implementation manner, the rendering part is configured to: respectively render multiple target areas according to preset color parameters to obtain multiple intermediate rendering results; determine multiple target areas according to the hues of multiple target areas Respectively corresponding processing methods; according to the corresponding processing methods of multiple target areas, the grayscale image of the target part is mixed with multiple intermediate rendering results to obtain multiple rendering results.

In a possible implementation manner, the target area includes at least one of the following: a highlight area, a shadow area, and a midtone area; the rendering part is further configured to: when the target area includes a highlight area, determine that the processing method includes color filtering blending; in a case where the target area includes a shadow area, determining the processing method includes multiply blending; in a case where the target area includes a midtone area, determining a processing method includes normal blending.

In a possible implementation, the generation part is configured to: superimpose multiple rendering results to obtain a target rendering result; based on preset rendering parameters, use the target rendering result to render the target part in the original virtual object to obtain The target dummy.

In a possible implementation manner, the device is further configured to: in response to an interaction operation on the target virtual object, according to interaction information in the interaction operation, control the target virtual object to perform a virtual action that matches the interaction information.

This disclosure relates to the field of augmented reality. By acquiring the image information of the target object in the real environment, and then using various visual correlation algorithms to detect or identify the relevant features, states and attributes of the target object, and thus obtain the image information that matches the specific application. AR effect combining virtual and reality. Exemplarily, the target object may involve faces, limbs, gestures, actions, etc. related to the human body, or markers and markers related to objects, or sand tables, display areas or display items related to venues or places. Vision-related algorithms can involve visual positioning, SLAM, 3D reconstruction, image registration, background segmentation, object key point extraction and tracking, object pose or depth detection, etc. Specific applications can not only involve interactive scenes such as guided tours, navigation, explanations, reconstructions, virtual effect overlays and display related to real scenes or objects, but also special effects processing related to people, such as makeup beautification, body beautification, special effect display, virtual Interactive scenarios such as model display. The relevant features, states and attributes of the target object can be detected or identified through the convolutional neural network. The above-mentioned convolutional neural network is a network model obtained by performing model training based on a deep learning framework.

Application Scenario Example

In the field of computer vision, how to change the hair color of the original virtual object to generate a target virtual object with a more realistic and natural hair effect has become an urgent problem to be solved.

The disclosed application example proposes a method for generating a virtual object, including the following process:

Obtain the hair texture of the original virtual object, and perform grayscale processing on the hair texture to obtain a grayscale image x.

Based on the grayscale image x, the highlight, shadow and midtone regions are separated for the hair part, and three target regions are obtained, including the highlight region, shadow region and midtone region, among which,

The process of highlight separation can include:

Multiply blend x and x itself to get the first blend result. Obtain the alpha channel value in the first blending result, and map the alpha channel value to transparency according to the black-and-white relationship of the alpha channel value, so as to obtain the first transparency of each pixel in the target part, based on the first transparency, filter from the hair part The pixels belonging to the highlight area get the highlight area.

The process of shadow separation can include:

Reverse grayscale processing is performed on x to obtain a reverse grayscale image, and the reverse grayscale image and the reverse grayscale image itself are multiplied and mixed to obtain a second mixed result. Obtain the alpha channel value in the second blending result, and map the alpha channel value to transparency according to the black-and-white relationship of the alpha channel value, so as to obtain the second transparency of each pixel in the target part, based on the second transparency, filter from the hair part Pixels belonging to the shaded area get the shaded area.

The process of separating midtones can include:

Perform exclusion mixing of x and x itself to obtain a third mixing result. Obtain the alpha channel value in the third blending result, and map the alpha channel value to transparency according to the black-and-white relationship of the alpha channel value, so as to obtain the third transparency of each pixel in the target part, based on the third transparency, filter from the hair part The pixels belonging to the midtone area are obtained from the midtone area.

After obtaining the highlight area, shadow area, and midtone area, the preset color parameters can be mixed with the highlight area, shadow area, and midtone area to obtain intermediate rendering results a, b, and c, respectively.

Filter and mix the obtained intermediate rendering result a with x to obtain the rendering result d;

Multiply and mix the obtained intermediate rendering result b with x to obtain the rendering result e;

The obtained intermediate rendering result c is normally mixed with x to obtain the rendering result f.

Superimpose the three layers where the rendering results d, e, and f are located, that is, pack them into a group to obtain the target rendering result g. The target rendering result g can render the hair part of the original virtual object to obtain the target virtual object. Change g The transparency of the target virtual object can change the transparency effect, wherein the target rendering result g can be mixed with the original virtual object through normal mixing.

As proposed in the application example of the present disclosure, the hair dyeing effect can be made more natural and a WYSIWYG processing effect can be realized by processing target areas of different tones. Moreover, the method proposed in the embodiment of the present disclosure can achieve more parameter definitions, such as the change of the preset color parameters of different target areas, the change of the target rendering result and the preset rendering parameters of the original virtual object, etc., so that the generation of virtual objects The effect is more controllable, and it is convenient to customize related parameters. Compared with saving the hair texture as a PSD file in the PS operation process in the related method, and changing the rendering effect of the hair in the virtual object by changing the result of the PSD, the unity designer can use the method proposed in the application example of this disclosure to make a virtual The hair color of the object can be manually changed, and the target virtual object will be displayed directly after the change. Unity developers can also set the bottom layer based on the method of this disclosed application example, and retain the interface for modifying the hair color, so as to facilitate related use The user can directly realize the color change to obtain the target virtual object and so on.

It can be understood that the above-mentioned method embodiments mentioned in this disclosure can all be combined with each other to form a combined embodiment without violating the principle and logic. Due to space limitations, this disclosure will not repeat them.

Those skilled in the art can understand that in the above-mentioned method of specific implementation, the writing order of each step does not imply a strict execution order and constitutes any limitation on the implementation process, and the execution order of each step should be based on its function and possible internal Logically OK.

Embodiments of the present disclosure also provide a computer-readable storage medium, on which computer program instructions are stored, and the above-mentioned method is implemented when the computer program instructions are executed by a processor. The computer readable storage medium may be a volatile computer readable storage medium or a nonvolatile computer readable storage medium.

An embodiment of the present disclosure also proposes an electronic device, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured as the above method.

The embodiment of the present disclosure also proposes a computer program product, the computer program product includes a computer program or an instruction, and when the computer program or instruction is run on a computer, the computer implements the method for generating a virtual object described above when executed.

In practical applications, the above-mentioned memory can be volatile memory (volatile memory), random access memory (Random Access Memory, RAM); or non-volatile memory (non-volatile memory), such as read-only memory (Read Only Memory, ROM), Erasable Programmable Read Only Memory (Erasable Programmable Read Only Memory, EPROM or flash memory), Static Random-Access Memory (Static Random-Access Memory, SRAM), Portable Compact Disk Read-Only Memory (Compact Disk Read Only Memory, CD-ROM), Digital versatile disc (Digital versatile Disc, DVD), memory sticks, floppy disks, mechanical encoding devices, such as punched cards or raised structures in grooves on which instructions are stored, and the aforementioned any suitable combination. As used herein, computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light through fiber optic cables), or transmitted electrical signals. .

The above-mentioned processor can be an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processing, DSP), a digital signal processing device (Digital signal processing device, DSPD), a programmable logic device (programmable logic device) , PLD), Field Programmable Gate Array (Field Programmable Gate Array, FPGA), controller, microcontroller at least one. It can be understood that, for different devices, the electronic device used to implement the above processor function may also be other, which is not specifically limited in this embodiment of the present disclosure.

Electronic devices may be provided as terminals, servers, or other forms of devices.

Based on the same technical idea as the foregoing embodiments, the embodiments of the present disclosure further provide a computer program, which implements the above method when the computer program is executed by a processor.

FIG. 14 is a block diagram of an electronic device 800 according to an embodiment of the present disclosure. For example, the electronic device 800 may be a terminal such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, or a personal digital assistant.

14, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input/output (Input/Output, I/O) interface 812 , sensor component 814 , and communication component 816 .

The processing component 802 generally controls the overall operations of the electronic device 800, such as those associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above method. Additionally, processing component 802 may include one or more components that facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia unit to facilitate interaction between multimedia component 808 and processing component 802 .

The memory 804 is configured to store various types of data to support operations at the electronic device 800 . Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 can be realized by any type of volatile or non-volatile storage device or their combination, such as Static Random-Access Memory (Static Random-Access Memory, SRAM), Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable read only memory, EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, EPROM), programmable read-only memory (Programmable Read-Only Memory, PROM), read-only memory (Read-Only Memory, ROM), magnetic memory, flash memory, magnetic disk or optical disk.

The power supply component 806 provides power to various components of the electronic device 800 . Power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 800 .

The multimedia component 808 includes a screen providing an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (Liquid Crystal Display, LCD) and a touch panel (Touch panel, TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may not only sense a boundary of a touch or swipe action, but also detect duration and pressure associated with the touch or swipe action. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a microphone (microphone, MIC), and when the electronic device 800 is in an operation mode, such as a calling mode, a recording mode and a voice recognition mode, the microphone is configured to receive an external audio signal. Received audio signals may be further stored in memory 804 or sent via communication component 816 . In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module, which may be a keyboard, a click wheel, a button, and the like. These buttons may include, but are not limited to: a home button, volume buttons, start button, and lock button.

Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of electronic device 800 . For example, the sensor component 814 can detect the open/closed state of the electronic device 800, the relative positioning of components, such as the display and the keypad of the electronic device 800, the sensor component 814 can also detect the electronic device 800 or a Changes in position of components, presence or absence of user contact with electronic device 800 , electronic device 800 orientation or acceleration/deceleration and temperature changes in electronic device 800 . Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor component 814 may also include an optical sensor, such as a (Complementary Metal Oxide Semiconductor, Complementary Metal Oxide Semiconductor) or a CCD (Charge-coupled Device, Charge-Coupled Device) image sensor, for use in imaging applications. In some embodiments, the sensor component 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access wireless networks based on communication standards, such as WiFi, 2G (2-Generation wireless telephone technology, second-generation mobile communication technology) or 3G (3-Generation wireless telephone technology, third-generation mobile communication technology), or a combination of them. In an exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a Near Field Communication (NFC) portion to facilitate short-range communication. For example, the NFC part can be based on Radio Frequency Identification (RFID) technology, Infrared Data Association (Infrared Data Association, IrDA) technology, Ultra Wide Band (Ultra Wide Band, UWB) technology, Bluetooth (Bluetooth, BT) technology and other technology to achieve.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (Digital signal processing device , DSPD), programmable logic device (programmable logic device, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), controller, microcontroller, microprocessor or other electronic components to implement, used to perform the above method.

In an exemplary embodiment, there is also provided a non-volatile computer-readable storage medium, such as the memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to implement the above method.

FIG. 15 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, electronic device 1900 may be provided as a server. Referring to FIG. 15 , electronic device 1900 includes processing component 1922 , which further includes one or more processors, and a memory resource represented by memory 1932 for storing instructions executable by processing component 1922 , such as application programs. An application program stored in memory 1932 may include one or more portions each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input-output (I/O) interface 1958 . The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

In an exemplary embodiment, there is also provided a non-transitory computer-readable storage medium, such as the memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to implement the above method.

The present disclosure may be a system, method, computer program product. A computer program product may include a computer readable storage medium having computer readable program instructions thereon for causing a processor to implement various aspects of the present disclosure.

A computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer-readable storage media include: portable computer disk, hard disk, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), erasable Electrical Programmable Read Only Memory (EPROM or flash memory), Static Random Access Memory (Static Random Access Memory, SRAM), Portable Compact Disc Read-Only Memory (CD-ROM) , Digital Video Disc (DVD), memory sticks, floppy disks, mechanically encoded devices such as punched cards or raised structures in grooves with instructions stored thereon, and any suitable combination of the foregoing. As used herein, computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light through fiber optic cables), or transmitted electrical signals.

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

Computer program instructions for performing operations of embodiments of the present disclosure may be assembly instructions, instruction set architecture (Industry Standard Architecture, ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in a or any combination of programming languages, including object-oriented programming languages—such as Smalltalk, C++, etc., and conventional procedural programming languages—such as “C” or similar programming languages language. Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In cases involving a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer such as use an Internet service provider to connect via the Internet). In some embodiments, electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (programmable logic arrays, PLAs), are personalized by utilizing state information of computer-readable program instructions, The electronic circuit can execute computer readable program instructions, thereby implementing various aspects of the embodiments of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowcharts and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that when executed by the processor of the computer or other programmable data processing apparatus , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart and/or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause computers, programmable data processing devices and/or other devices to work in a specific way, so that the computer-readable medium storing instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks in flowcharts and/or block diagrams.

It is also possible to load computer-readable program instructions into a computer, other programmable data processing device, or other equipment, so that a series of operational steps are performed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , so that instructions executed on computers, other programmable data processing devices, or other devices implement the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a portion, a program segment, or a portion of an instruction that includes one or more Executable instructions. In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

Having described various embodiments of the present disclosure above, the foregoing description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and alterations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principle of each embodiment, practical application or technical improvement in the market, or to enable other ordinary skilled in the art to understand each embodiment disclosed herein.

Industrial Applicability

The disclosure relates to a method and device for generating a virtual object, electronic equipment and a storage medium. The method includes: acquiring target parts to be processed in the original virtual object; dividing the target parts into multiple target areas according to the hue information of the target parts; Performing rendering processing that matches the color tone of the target area respectively to obtain multiple rendering results; based on the multiple rendering results, a target virtual object is generated. Through the above process, based on the hue of the target part of the virtual object, the target part can be divided into multiple target areas, and corresponding rendering processing is performed on the multiple target areas, so that in the process of changing the image of the virtual object, Using the original tone information of the original virtual object, the target virtual object with a more realistic and natural effect can still be obtained. For example, the target part can be divided into a highlight area, a shadow area, and a mid-tone area according to the tones such as highlights, shadows, and mid-tones. In the process of rendering the highlight area, increase the rendering brightness as much as possible, in the process of rendering the shadow area, reduce the rendering brightness as much as possible, and in the process of rendering the midtone area, keep the The brightness of the rendering enables the rendering effect of the target virtual object to match the original tone distribution of the original virtual object, improving the authenticity and naturalness of the target virtual object.

Claims (15)

1. A method for generating a virtual object, comprising:

   Obtain the target part to be processed in the original virtual object;

   dividing the target site into a plurality of target areas according to the hue information of the target site;

   performing rendering processing on the plurality of target areas according to the preset color parameters to match the color tone of the target areas, to obtain multiple rendering results;

   Based on the plurality of rendering results, a target virtual object is generated.
2. The method according to claim 1, wherein said obtaining the target part to be processed in the original virtual object comprises:

   acquiring the original virtual object, wherein the original virtual object is generated according to virtual information;

   According to the virtual information, the target part to be processed is extracted from the original virtual object.
3. The method according to claim 2, wherein the virtual information includes at least one of the following: preset virtual object generation information, virtual object control information generated in response to user actions.
4. The method according to any one of claims 1 to 3, wherein the tone information includes at least one of the following: highlight information, shadow information, and midtone information;

   The said target part is divided into a plurality of target areas according to the hue information of the target part, including at least one of the following:

   Based on the highlight information of the target part, extracting a highlight region from the target part;

   Extracting a shadow area from the target part based on the shadow information of the target part;

   Based on the midtone information of the target part, a midtone area is extracted from the target part.
5. The method according to claim 4, wherein said extracting a highlight region from the target part based on the highlight information of the target part comprises:

   Based on the grayscale image of the target part, perform multi-layer blending to obtain a first blending result;

   determining a first transparency of pixels in the target part according to the first mixing result;

   According to the first preset transparency threshold and the first transparency, pixel points in the target part are extracted to obtain the highlight area.
6. The method according to claim 4 or 5, wherein said extracting a shadow area from said target part based on the shadow information of said target part comprises:

   Based on the reverse grayscale image of the target part, perform multi-fold blending to obtain a second blending result;

   determining a second transparency of pixels in the target part according to the second mixing result;

   According to the second preset transparency threshold and the second transparency, pixel points in the target part are extracted to obtain the shadow area.
7. The method according to any one of claims 4 to 6, wherein said midtone region extracted from said target part based on the midtone information of said target part comprises:

   Based on the grayscale image of the target part, performing exclusion mixing to obtain a third mixing result;

   determining a third transparency of pixels in the target part according to the third mixing result;

   According to the third preset transparency threshold and the third transparency, pixel points in the target part are extracted to obtain the midtone area.
8. The method according to any one of claims 1 to 7, wherein, according to the preset color parameters, the plurality of target areas are respectively subjected to rendering processing that matches the color tone of the target areas to obtain a plurality of rendered Results, including:

   Rendering the plurality of target areas respectively according to the preset color parameters to obtain a plurality of intermediate rendering results;

   According to the hues of the multiple target areas, determine processing modes corresponding to the multiple target areas;

   According to the processing manners respectively corresponding to the multiple target regions, the grayscale image of the target part is mixed with the multiple intermediate rendering results respectively to obtain multiple rendering results.
9. The method according to claim 8, wherein the target area comprises at least one of the following: a highlight area, a shadow area, and a midtone area;

   The determining the processing methods respectively corresponding to the multiple target areas according to the hues of the multiple target areas includes:

   In the case that the target area includes a highlight area, determining that the processing method includes color filter mixing;

   In the case where the target area includes a shaded area, determining that the processing method includes multiplying and blending;

   In a case where the target area includes a midtone area, it is determined that the processing manner includes normal mixing.
10. The method according to any one of claims 1 to 9, wherein said generating a target virtual object based on said plurality of rendering results comprises:

    superimposing the plurality of rendering results to obtain a target rendering result;

    Based on preset rendering parameters, the target part in the original virtual object is rendered by using the target rendering result to obtain the target virtual object.
11. The method according to any one of claims 1 to 10, wherein the method further comprises:

    In response to an interactive operation on the target virtual object, according to interaction information in the interactive operation, the target virtual object is controlled to perform a virtual action that matches the interaction information.
12. A device for generating a virtual object, comprising:

    an acquisition part configured to acquire a target part to be processed in the original virtual object;

    a dividing part configured to divide the target part into a plurality of target regions according to the tone information of the target part;

    The rendering part is configured to, according to preset color parameters, respectively perform rendering processing on the plurality of target areas matching the color tone of the target areas to obtain multiple rendering results;

    The generation part is configured to generate a target virtual object based on the plurality of rendering results.
13. An electronic device comprising:

    processor;

    memory for storing processor-executable instructions;

    Wherein, the processor is configured to invoke instructions stored in the memory to execute the method according to any one of claims 1-11.
14. A computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.
15. A computer program, comprising computer readable code, when the computer readable code is run in the electronic device, the processor in the electronic device executes the method for implementing any one of claims 1 to 11 .

Images