Three-dimensional image generation method and device, equipment and storage medium

Abstract

The invention discloses a three-dimensional image generation method and device, equipment and a storage medium, and relates to the technical field of computers.The method comprises the steps that description information of a user image is determined, and the description information comprises overall description information and detail description information; inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image by referring to the description information; and processing the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image. According to the technical scheme, three-dimensional image construction is performed on the user image based on the basic image corresponding to the user image, the three-dimensional image corresponding to the user image is obtained, automatic and rapid generation of the three-dimensional image corresponding to the user image is realized, the threshold of three-dimensional image generation is reduced, and the efficiency of three-dimensional image generation is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a three-dimensional image generation method, apparatus, device and storage medium. Background Art

[0002] With the rise of the Internet in recent years, live broadcast creation through three-dimensional images has also become a trend. More and more users want to have customized three-dimensional images. In order to meet user needs, it is necessary to generate corresponding three-dimensional images based on user data.

[0003] In the prior art, professionals are usually required to manually process user data using 3D software to generate a 3D image. This process is time-consuming and requires high professional skills.

[0004] Therefore, there is an urgent need for a three-dimensional image generation method that can quickly generate three-dimensional images, lower the threshold for three-dimensional image generation, and improve the efficiency of three-dimensional image generation. Summary of the Invention

[0005] The present invention provides a three-dimensional image generation method, device, equipment and storage medium to achieve rapid generation of a three-dimensional image.

[0006] In a first aspect, an embodiment of the present invention provides a method for generating a three-dimensional image, comprising:

[0007] Determining description information of the user image, wherein the description information includes overall description information and detailed description information;

[0008] Inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information;

[0009] The basic image is processed based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0010] The technical solution of an embodiment of the present invention provides a three-dimensional image generation method, including: determining description information of a user image, wherein the description information includes overall description information and detailed description information; inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; and processing the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image. The above technical solution can first determine the description information of the user image, specifically the overall description information and the detailed description information, and improve the matching degree between the description information and the user image by describing the user image with the overall description information and the detailed description information. Secondly, the user image and the description information corresponding to the user image can be input into the image redrawing model, so that the image redrawing model redraws the user image with reference to the description information corresponding to the user image, and obtains the basic image corresponding to the user image. The basic image for generating a three-dimensional image is obtained by redrawing the user image in two dimensions, and then the basic image can be processed based on the three-dimensional modeling application, so that the three-dimensional modeling application constructs a three-dimensional image of the user image based on the basic image corresponding to the user image, and obtains the three-dimensional image corresponding to the user image, thereby realizing the automatic and rapid generation of the three-dimensional image corresponding to the user image, lowering the threshold for generating three-dimensional images, and improving the efficiency of generating three-dimensional images.

[0011] Furthermore, the description information of the user image is determined, including:

[0012] By inputting the user image into a pre-trained image-to-prompt model, the image-to-prompt model determines the overall description information of the user image based on the feature information and logical relationship of the user image, and determines the detailed description information of the user image based on the feature information and detail requirements.

[0013] Furthermore, before processing the basic image based on the three-dimensional modeling application, the method further includes:

[0014] Obtaining an intermediate image by performing restoration processing and magnification processing on the basic image;

[0015] The image style of the intermediate image is adjusted based on the style requirement to obtain a target image.

[0016] Furthermore, the step of processing the basic image by the three-dimensional modeling application includes:

[0017] After generating a three-dimensional head model based on the facial information corresponding to the basic image, optimizing the three-dimensional head model based on the feature information corresponding to the basic image to obtain an initial image;

[0018] Performing geometric fine-tuning on the initial image according to the detailed description information to obtain an intermediate image;

[0019] Texture information is added to the intermediate image to obtain the three-dimensional image.

[0020] Furthermore, it also includes:

[0021] An identification file is generated according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image.

[0022] Furthermore, generating an identification file according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image includes:

[0023] determining a file name according to the user identifier corresponding to the user image;

[0024] The identification file corresponding to the user image is obtained by storing the storage address of the three-dimensional image corresponding to the user image in a file corresponding to the file name.

[0025] Furthermore, it also includes:

[0026] After monitoring the generation of the identification file corresponding to the user image, sending update information to the user terminal corresponding to the user image;

[0027] In response to an acquisition request sent by the user terminal, the three-dimensional image is sent to the user terminal, wherein the acquisition request is determined by the user terminal in response to the update information.

[0028] In a second aspect, an embodiment of the present invention further provides a three-dimensional image generating device, comprising:

[0029] a determination module, configured to determine description information of the user image, wherein the description information includes overall description information and detailed description information;

[0030] an execution module, configured to input the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information;

[0031] A generation module is used to process the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising:

[0033] at least one processor; and a memory communicatively coupled to the at least one processor;

[0034] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the three-dimensional image generation method as described in any one of the first aspects.

[0035] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a computer processor, are used to execute the three-dimensional image generation method as described in any one of the first aspects.

[0036] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are run on a computer, the computer executes the three-dimensional image generation method provided in the first aspect.

[0037] It should be noted that the aforementioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the 3D image generation device, or may be packaged separately from the processor of the 3D image generation device, and this application does not limit this.

[0038] The descriptions of the second, third, fourth and fifth aspects of this application can refer to the detailed description of the first aspect; and the beneficial effects of the descriptions of the second, third, fourth and fifth aspects can refer to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0039] In this application, the name of the three-dimensional image generation device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they are within the scope of the claims of this application and their equivalents.

[0040] These and other aspects of the present application will become more readily apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A flowchart of a three-dimensional image generation method provided by an embodiment of the present invention;

[0043] Figure 2 A flowchart of another three-dimensional image generation method provided by an embodiment of the present invention;

[0044] Figure 3 A schematic structural diagram of a three-dimensional image generating device provided by an embodiment of the present invention;

[0045] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0047] The term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0048] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0049] Furthermore, the terms "including," "having," and any variations thereof, as used in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not limited to the listed steps or units but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to the process, method, product, or apparatus.

[0050] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. When its operation is completed, the process can be terminated, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the features in the embodiments of the present invention and the embodiments can be combined with each other without conflict.

[0051] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being more preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0052] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0053] Figure 1 This is a flow chart of a three-dimensional image generation method provided by an embodiment of the present invention. This embodiment is applicable to situations where a three-dimensional image needs to be generated quickly. The method can be executed by a three-dimensional image generation device, such as Figure 1 As shown, the specific steps include:

[0054] Step 110: Determine description information of the user image.

[0055] The description information includes overall description information and detailed description information.

[0056] In order to generate a 3D image that retains user features and integrates specified features, it is necessary to extract overall information and detail information from the user image.

[0057] Specifically, after obtaining a user image, a text description of the user image can be generated by determining the descriptive information of the user image. Of course, in order to improve the matching degree between the descriptive information and the user image, that is, to improve the accuracy of the description, a text description of the user image can be generated based on an overall description and a detailed description. For example, the user image can be input into a pre-trained image-to-prompt model, so that the image-to-prompt model describes the overall information of the user image based on the overall description to obtain overall description information, and describes specific details of the user image based on the detailed description to obtain detailed description information. Specific details can be set according to actual needs. For example, specific details can include gender, hairstyle, and clothing.

[0058] In the embodiment of the present invention, the user image is described by using overall description information and detailed description information to improve the matching degree between the description information and the user image.

[0059] Step 120: Input the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information.

[0060] In the process of redrawing the user's two-dimensional image based on the user image, in order to improve the accuracy of the redrawing, the description information can be used as reference information for the redrawing.

[0061] The image redrawing model is trained based on the image and the description information corresponding to the image as well as the two-dimensional image of the user corresponding to the image. It can be used to redraw the two-dimensional image based on the image and the description information corresponding to the image to obtain the two-dimensional image corresponding to the image.

[0062] Specifically, the user image and description information can be input into the image redrawing model. The description information then serves as a prompt to guide the image redrawing model in drawing a 2D image corresponding to the user image. When drawing the 2D image, the image redrawing model references the overall and detailed description information contained in the description information corresponding to the user image to improve the matching degree between the drawn base image and the user image, thereby improving the accuracy of the base image.

[0063] In an embodiment of the present invention, by inputting a user image and description information corresponding to the user image into an image redrawing model, the image redrawing model can perform two-dimensional redrawing of the user image with reference to the description information corresponding to the user image to obtain a basic image corresponding to the user image.

[0064] Step 130: Process the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0065] Specifically, after redrawing the user image to obtain the base image required for 3D modeling, the base image can be processed using a 3D modeling application to generate a corresponding 3D image of the user image. Specifically, face detection and feature extraction can be performed on the base image to determine the corresponding facial information and feature information. Head modeling is then performed based on this facial and feature information to obtain an initial image. This initial image can then be fine-tuned geometrically and textured to create a 3D image.

[0066] In an embodiment of the present invention, a basic image corresponding to a user image is processed by a three-dimensional modeling application to establish a three-dimensional image of the user image based on the basic image, thereby obtaining a three-dimensional image corresponding to the user image.

[0067] The three-dimensional image generation method provided by an embodiment of the present invention includes: determining description information of a user image, wherein the description information includes overall description information and detailed description information; inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; and processing the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image. The above technical solution can first determine the description information of the user image, specifically the overall description information and the detailed description information, and improve the matching degree between the description information and the user image by describing the user image with the overall description information and the detailed description information. Secondly, the user image and the description information corresponding to the user image can be input into the image redrawing model, so that the image redrawing model redraws the user image with reference to the description information corresponding to the user image, and obtains the basic image corresponding to the user image. The basic image for generating a three-dimensional image is obtained by redrawing the user image in two dimensions, and then the basic image can be processed based on the three-dimensional modeling application, so that the three-dimensional modeling application constructs a three-dimensional image of the user image based on the basic image corresponding to the user image, and obtains the three-dimensional image corresponding to the user image, thereby realizing the automatic and rapid generation of the three-dimensional image corresponding to the user image, lowering the threshold for generating three-dimensional images, and improving the efficiency of generating three-dimensional images.

[0068] Figure 2 This is a flow chart of another three-dimensional image generation method provided by an embodiment of the present invention. This embodiment is a specific implementation based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:

[0069] Step 210: Determine description information of the user image.

[0070] The description information includes overall description information and detailed description information.

[0071] In one implementation, step 210 may specifically include:

[0072] By inputting the user image into a pre-trained image-to-prompt model, the image-to-prompt model determines the overall description information of the user image based on the feature information and logical relationship of the user image, and determines the detailed description information of the user image based on the feature information and detail requirements.

[0073] The image-to-prompt model is trained based on the image and the overall description information and detailed description information corresponding to the image. The detailed description information here is determined based on pre-set detail requirements.

[0074] Specifically, the user image can be input into the image-to-prompt model, which can perform image analysis on the user image and generate text based on the image analysis results to generate overall description information and detailed description information corresponding to the user image. Specifically, the image-to-prompt model can perform feature extraction on the user image during the image analysis phase to determine the feature information of the user image, such as objects, scenes, styles, colors, etc. It can also perform contextual understanding of the user image to determine the logical relationship between the objects in the user image. During the text generation phase, the image-to-prompt model can convert the feature information into description information suitable for two-dimensional image redrawing, that is, it can determine the description information. In addition, the length of the description information can be controlled within a preset range.

[0075] In actual applications, the description information includes overall description information and detailed description information. The detailed description information can be understood as the description information corresponding to the preset detail requirements. When the preset detail requirements include gender, hairstyle and clothing, the detailed description information may include gender information, hairstyle information and clothing information.

[0076] Therefore, when the image-to-prompt model converts feature information into description information suitable for two-dimensional image redrawing, it first determines the overall description information of the user image based on the feature information of the user image and the logical relationship between objects in the user image. Secondly, it determines the detailed description information of the user image based on the feature information and detail requirements, thereby realizing the generation of overall description information and detailed description information.

[0077] In the embodiment of the present invention, the user image is described by using overall description information and detailed description information to improve the matching degree between the description information and the user image.

[0078] Step 220: Input the user image and description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information.

[0079] Specifically, the user image and description information are input into an image redrawing model trained based on the image, the description information corresponding to the image, and the two-dimensional image of the user corresponding to the image. The image redrawing model can draw the two-dimensional image corresponding to the user image with reference to the overall description information and detailed description information contained in the description information corresponding to the user image to obtain a basic image, thereby improving the matching degree between the drawn basic image and the user image, and thereby improving the accuracy of the basic image.

[0080] In an embodiment of the present invention, by inputting a user image and description information corresponding to the user image into an image redrawing model, the image redrawing model can perform two-dimensional redrawing of the user image with reference to the description information corresponding to the user image to obtain a basic image corresponding to the user image.

[0081] Step 230 : Obtain an intermediate image by performing restoration and magnification processing on the base image; and obtain a target image by adjusting the image style of the intermediate image based on the style requirement.

[0082] Among them, style requirements can be understood as style requirements for three-dimensional images, such as business, ancient style, art, etc.

[0083] Specifically, after determining the base image corresponding to the user image, the base image can be restored and amplified sequentially to obtain an intermediate image with richer details and greater clarity. The style image of the intermediate image can then be adjusted based on the desired style to obtain the target image. The target image can then serve as the modeling foundation for 3D modeling applications, constructing a 3D image of the corresponding style.

[0084] In the embodiment of the present invention, after the base image is restored and magnified, the image style is adjusted based on the style requirement to obtain a target image with improved clarity that better matches the style requirement.

[0085] Step 240: Process the target image based on the three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0086] In one implementation, step 240 may specifically include:

[0087] After generating a three-dimensional head model based on the facial information corresponding to the target image, the three-dimensional head model is optimized based on the feature information corresponding to the target image to obtain an initial image; the initial image is geometrically fine-tuned according to the detailed description information to obtain an intermediate image; and texture information is added to the intermediate image to obtain a three-dimensional image.

[0088] Specifically, the 3D modeling application first performs face detection and feature extraction based on the base image to determine the corresponding facial information and feature information. It then models the head based on the facial information to obtain a 3D head model. This 3D head model can then be optimized based on the feature information to obtain an initial image. This initial image can then be geometrically fine-tuned, meaning details can be sculpted to obtain an intermediate image. Textures can then be added to this intermediate image to complete the 3D image.

[0089] In the embodiment of the present invention, a target image that is clear and matches the style requirements is processed by a 3D modeling application, so as to establish a 3D image of the user image based on the target image and obtain a 3D image corresponding to the user image.

[0090] Step 250: Generate an identification file according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image.

[0091] In one implementation, step 250 may specifically include:

[0092] The file name is determined according to the user identification corresponding to the user image; and the identification file corresponding to the user image is obtained by storing the storage address of the three-dimensional image corresponding to the user image in the file corresponding to the file name.

[0093] After the three-dimensional image corresponding to the user image is generated, the three-dimensional image can be stored at the corresponding storage address. The file name of the identification file is composed of the user identifier corresponding to the user image and the task identifier of the three-dimensional image generation task that generated the three-dimensional image corresponding to the user image. The identification file is used to store the storage address of the three-dimensional image corresponding to the user image.

[0094] Specifically, after generating a three-dimensional image corresponding to the user image, the file name can be determined based on the task identifier of the three-dimensional image generation task for generating the three-dimensional image corresponding to the user image and the user identifier corresponding to the user image. The storage address of the three-dimensional image corresponding to the user image can also be stored in the file corresponding to the file name to obtain the identification file corresponding to the user image.

[0095] In the embodiment of the present invention, after determining to generate a 3D image corresponding to the user image, an identification file is generated indicating that the 3D image corresponding to the user image has been generated, thereby achieving timely and automatic identification of the 3D image generation.

[0096] Step 260: After monitoring the generation of the identification file corresponding to the user image, send the update information to the user terminal corresponding to the user image; and in response to the acquisition request sent by the user terminal, send the three-dimensional image to the user terminal.

[0097] The acquisition request is determined by the user terminal in response to the update information.

[0098] In order to promptly notify the user after the three-dimensional image corresponding to the user image is generated, it is possible to monitor whether the identification file is generated to monitor whether the three-dimensional image corresponding to the user image is generated.

[0099] Specifically, upon detecting the presence of an identification file whose file name consists of a user identifier corresponding to a user image and a task identifier for a 3D image generation task for generating a 3D image corresponding to the user image, it is determined that a 3D image corresponding to the user image has been generated. At this point, update information can be sent to the user terminal corresponding to the user image to remind the user that the latest 3D image has been generated. Of course, the user terminal can display a reminder message based on the download interface, and after determining that the download page has received a trigger request, it can send a retrieval request to the server to download the latest 3D image based on the retrieval request. Correspondingly, after receiving the retrieval request, the server can send the 3D image to the user terminal in response to the retrieval request. In this case, the user terminal can automatically change the identification information of the 3D image and display the latest 3D image after the user terminal is restarted.

[0100] In an embodiment of the present invention, after determining to generate an identification file corresponding to a user image, timely reminders for generating a three-dimensional image corresponding to the user image are achieved by sending update information to the user terminal corresponding to the user image, and in response to an acquisition request sent by the user terminal, the three-dimensional image is sent to the user terminal, thereby achieving timely distribution of the three-dimensional image corresponding to the user image.

[0101] The three-dimensional image generation method provided by an embodiment of the present invention includes: determining the description information of a user image; inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; obtaining an intermediate image by repairing and amplifying the basic image; adjusting the image style of the intermediate image based on style requirements to obtain a target image; processing the target image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image; generating an identification file based on the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image; after monitoring the generation of the identification file corresponding to the user image, sending update information to the user terminal corresponding to the user image; and sending the three-dimensional image to the user terminal in response to a get request sent by the user terminal. The above technical solution can first determine the description information of the user image, specifically the overall description information and the detailed description information, and improve the matching degree between the description information and the user image through the description of the user image by the overall description information and the detailed description information. Secondly, the user image and the description information corresponding to the user image can be input into the image redrawing model, so that the image redrawing model redraws the user image with reference to the description information corresponding to the user image to obtain the basic image corresponding to the user image. The basic image for generating a three-dimensional image can be obtained by two-dimensionally redrawing the user image, and then the basic image can be repaired and enlarged, and the image style can be adjusted based on the style requirements to obtain a target image with improved clarity and more matching the style requirements. The target image that is clearer and more matching the style requirements is processed through the three-dimensional modeling application, and the three-dimensional image of the user image is established based on the target image to obtain the three-dimensional image corresponding to the user image, and the three-dimensional image corresponding to the user image is automatically and quickly generated, thereby lowering the threshold for three-dimensional image generation and improving the efficiency of three-dimensional image generation.

[0102] Furthermore, after determining that a three-dimensional image corresponding to the user image has been generated, an identification file is generated indicating that a three-dimensional image corresponding to the user image has been generated, thereby realizing timely and automatic identification of the generation of the three-dimensional image. After determining that an identification file corresponding to the user image has been generated, an update information is sent to the user terminal corresponding to the user image, thereby realizing timely reminder of the generation of the three-dimensional image corresponding to the user image. Furthermore, in response to an acquisition request sent by the user terminal, the three-dimensional image is sent to the user terminal, thereby realizing timely distribution of the three-dimensional image corresponding to the user image.

[0103] Figure 3 This is a schematic diagram of the structure of a 3D image generation device provided in an embodiment of the present invention. This device can be used to improve the efficiency of 3D image generation when rapid 3D image generation is required. The device can be implemented using software and / or hardware and is typically integrated into an electronic device, such as a computer.

[0104] like Figure 3 As shown, the device includes:

[0105] A determination module 310 is configured to determine description information of the user image, wherein the description information includes overall description information and detailed description information;

[0106] An execution module 320 is configured to input the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information;

[0107] The generation module 330 is configured to process the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0108] The three-dimensional image generation device provided in this embodiment determines description information of a user image, wherein the description information includes overall description information and detailed description information; inputs the user image and the description information into a pre-trained image redrawing model so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; and processes the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image. The above technical solution can first determine the description information of the user image, specifically the overall description information and the detailed description information, and improve the matching degree between the description information and the user image by describing the user image with the overall description information and the detailed description information. Secondly, the user image and the description information corresponding to the user image can be input into the image redrawing model, so that the image redrawing model redraws the user image with reference to the description information corresponding to the user image, and obtains the basic image corresponding to the user image. The basic image for generating a three-dimensional image is obtained by redrawing the user image in two dimensions, and then the basic image can be processed based on the three-dimensional modeling application, so that the three-dimensional modeling application constructs a three-dimensional image of the user image based on the basic image corresponding to the user image, and obtains the three-dimensional image corresponding to the user image, thereby realizing the automatic and rapid generation of the three-dimensional image corresponding to the user image, lowering the threshold for generating three-dimensional images, and improving the efficiency of generating three-dimensional images.

[0109] Based on the above embodiment, the determination module 310 is specifically configured to:

[0110] By inputting the user image into a pre-trained image-to-prompt model, the image-to-prompt model determines the overall description information of the user image based on the feature information and logical relationship of the user image, and determines the detailed description information of the user image based on the feature information and detail requirements.

[0111] Based on the above embodiment, the device further includes:

[0112] The processing module is used to obtain an intermediate image by performing restoration processing and enlargement processing on the basic image; and to adjust the image style of the intermediate image based on style requirements to obtain a target image.

[0113] Based on the above embodiment, the generation module 330 is specifically configured to:

[0114] After the three-dimensional modeling application generates a three-dimensional head model based on the facial information corresponding to the basic image, the three-dimensional head model is optimized based on the feature information corresponding to the basic image to obtain an initial image; the initial image is geometrically fine-tuned according to the detailed description information to obtain an intermediate image; and texture information is added to the intermediate image to obtain the three-dimensional image.

[0115] Based on the above embodiment, the device further includes:

[0116] The identification module is used to generate an identification file according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image.

[0117] Based on the above embodiment, the identification module is specifically used to:

[0118] The file name is determined according to the user identification corresponding to the user image; and the identification file corresponding to the user image is obtained by storing the storage address of the three-dimensional image corresponding to the user image in the file corresponding to the file name.

[0119] Based on the above embodiment, the device further includes:

[0120] A sending module is used to send update information to the user terminal corresponding to the user image after monitoring the generation of the identification file corresponding to the user image; and send the three-dimensional image to the user terminal in response to the acquisition request sent by the user terminal, wherein the acquisition request is determined by the user terminal in response to the update information.

[0121] The three-dimensional image generation device provided in the embodiment of the present invention can execute the three-dimensional image generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the three-dimensional image generation method.

[0122] It is worth noting that in the embodiment of the above-mentioned three-dimensional image generation device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the various functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0123] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0124] like Figure 4 As shown, electronic device 4 is in the form of a general-purpose computing electronic device. Components of electronic device 4 may include, but are not limited to, one or more processors or processing units 16, system memory 28, and a bus 18 connecting various system components (including system memory 28 and processing unit 16).

[0125] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0126] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0127] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be configured to read and write non-removable, non-volatile magnetic media ( Figure 4 Not shown, often called a "hard drive"). Although Figure 4 Not shown, a magnetic disk drive for reading and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of various embodiments of the present invention.

[0128] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0129] The electronic device 4 may also communicate with one or more external devices 14 (e.g., a keyboard, a pointing device, a display 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0130] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing a three-dimensional image generation method provided in an embodiment of the present invention, which includes:

[0131] Determining description information of the user image, wherein the description information includes overall description information and detailed description information;

[0132] Inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information;

[0133] The basic image is processed based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0134] Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the three-dimensional image generation method provided by any embodiment of the present invention.

[0135] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for generating a three-dimensional image provided in an embodiment of the present invention is implemented. The method includes:

[0136] Determining description information of the user image, wherein the description information includes overall description information and detailed description information;

[0137] Inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information;

[0138] The basic image is processed based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

[0139] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0140] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0141] Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0142] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0143] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computing device. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Alternatively, they can be implemented using program code executable by a computer device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

[0144] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention comply with relevant provisions of laws and regulations.

[0145] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A three-dimensional image generation method, characterized in that: include: Determining description information of the user image, wherein the description information includes overall description information and detailed description information; Inputting the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; The basic image is processed based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

2. The three-dimensional image generation method according to claim 1, characterized in that: Determine the description information of the user image, including: By inputting the user image into a pre-trained image-to-prompt model, the image-to-prompt model determines the overall description information of the user image based on the feature information and logical relationship of the user image, and determines the detailed description information of the user image based on the feature information and detail requirements.

3. The three-dimensional image generation method according to claim 1, characterized in that: Before processing the basic image based on the three-dimensional modeling application, the method further includes: Obtaining an intermediate image by performing restoration processing and magnification processing on the basic image; The image style of the intermediate image is adjusted based on the style requirement to obtain a target image.

4. The three-dimensional image generation method according to claim 1, characterized in that: The step of processing the basic image by the three-dimensional modeling application comprises: After generating a three-dimensional head model based on the facial information corresponding to the basic image, optimizing the three-dimensional head model based on the feature information corresponding to the basic image to obtain an initial image; Performing geometric fine-tuning on the initial image according to the detailed description information to obtain an intermediate image; Texture information is added to the intermediate image to obtain the three-dimensional image.

5. The three-dimensional image generation method according to claim 1, characterized in that: Also includes: An identification file is generated according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image.

6. The three-dimensional image generation method according to claim 5, characterized in that: Generating an identification file according to the storage address of the three-dimensional image corresponding to the user image and the user identification corresponding to the user image includes: determining a file name according to the user identifier corresponding to the user image; The identification file corresponding to the user image is obtained by storing the storage address of the three-dimensional image corresponding to the user image in a file corresponding to the file name.

7. The three-dimensional image generation method according to claim 6, characterized in that: Also includes: After monitoring the generation of the identification file corresponding to the user image, sending update information to the user terminal corresponding to the user image; In response to an acquisition request sent by the user terminal, the three-dimensional image is sent to the user terminal, wherein the acquisition request is determined by the user terminal in response to the update information.

8. A three-dimensional image generating device, characterized in that: include: a determination module, configured to determine description information of the user image, wherein the description information includes overall description information and detailed description information; an execution module, configured to input the user image and the description information into a pre-trained image redrawing model, so that the image redrawing model generates a basic image corresponding to the user image with reference to the description information; A generation module is used to process the basic image based on a three-dimensional modeling application to obtain a three-dimensional image corresponding to the user image.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the three-dimensional image generation method according to any one of claims 1 to 7.

10. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the three-dimensional image generation method according to any one of claims 1 to 7.

Images