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

Abstract

The present disclosure provides a three-dimensional image generation method, device, storage medium and electronic equipment, and relates to the technical field of image processing. The three-dimensional image generation method comprises the following steps: extracting pixel data of each pixel point in a two-dimensional to-be-processed frame image; and projecting the to-be-processed frame image onto a specific three-dimensional model based on the pixel data of each pixel point in the to-be-processed frame image to obtain a three-dimensional image corresponding to the to-be-processed frame image. The present disclosure can not only improve the animation production efficiency, but also enable the three-dimensional animation to retain the pixel style characteristics by projecting the two-dimensional image onto the three-dimensional model.

Description

Technical Field

[0001] This disclosure relates to the field of image processing technology, and in particular to a three-dimensional image generation method, a three-dimensional image generation apparatus, a computer-readable storage medium, and an electronic device. Background Technology

[0002] 3D voxel-style animation differs from 2D pixel-style animation. 3D voxel-style animation typically uses skeletal animation to achieve the movement of virtual objects, where the vertices of the virtual object move linearly, resulting in continuous movement. In contrast, 2D pixel-style animation is abrupt and requires the smallest unit of movement to match the smallest unit displayed; the virtual object may deform during movement. Recreating 2D pixel-style effects in 3D animation can provide players with a novel visual experience.

[0003] In related technologies, when recreating a 2D pixel-style effect in 3D animation, vertex animation needs to be superimposed on 3D skeletal animation to produce pixel-style animation. Skeletal animation requires changing the orientation and position of the model object's bones, while vertex animation requires changing the texture vertices of the model object. For art production, superimposing vertex animation on skeletal animation to achieve pixel-style animation is a relatively cumbersome process and quite difficult to implement.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This disclosure provides a method for generating three-dimensional images, a device for generating three-dimensional images, a computer-readable storage medium, and an electronic device, thereby at least to some extent solving the problem of the cumbersome art production process in related technologies.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to a first aspect of this disclosure, a method for generating a three-dimensional image is provided, the method comprising: extracting pixel data of each pixel point in a two-dimensional frame image to be processed; and projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel point in the frame image to be processed, thereby obtaining a three-dimensional image corresponding to the frame image to be processed.

[0008] In one exemplary embodiment of this disclosure, the specific three-dimensional model is a three-dimensional model composed of multiple sub-models, and the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed.

[0009] In one exemplary embodiment of this disclosure, the step of projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed to obtain a three-dimensional image corresponding to the frame image to be processed includes: filling each sub-model in the specific three-dimensional model with color according to the pixel data of each pixel in the frame image to be processed to obtain a three-dimensional image corresponding to the frame image to be processed.

[0010] In one exemplary embodiment of this disclosure, the step of color-filling each sub-model in the specific 3D model according to the pixel data of each pixel in the frame image to be processed to obtain the 3D image corresponding to the frame image to be processed includes: mapping the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space, wherein the target UV space is the UV space corresponding to the specific 3D model, and the sub-UV space is the UV space corresponding to the sub-model; searching for the color information corresponding to each sub-model in the specific 3D model in the target UV space to determine the fill color corresponding to each sub-model in the specific 3D model; and color-filling each sub-model in the specific 3D model according to the fill color corresponding to each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

[0011] In an exemplary embodiment of this disclosure, mapping the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space includes: determining the color identifier corresponding to each pixel in the frame image to be processed on a color table based on the pixel data of each pixel in the frame image to be processed; and determining the color identifier corresponding to each sub-UV space of the target UV space on the color table based on the color identifier corresponding to each pixel in the frame image to be processed.

[0012] In one exemplary embodiment of this disclosure, before projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed to obtain a three-dimensional image corresponding to the frame image to be processed, the method further includes: creating the specific three-dimensional model according to the pixel arrangement of the frame image to be processed.

[0013] In one exemplary embodiment of this disclosure, the step of creating the specific three-dimensional model according to the pixel arrangement of the frame image to be processed includes: creating a planar grid corresponding to the pixel arrangement of the frame image to be processed; adding center points to the center positions of each primitive in the planar grid; deleting each primitive and its associated points; and placing the sub-model at each of the center points to obtain the specific three-dimensional model.

[0014] In one exemplary embodiment of this disclosure, the method further includes: overlapping the UV maps of each face of the sub-model and moving them to a sub-UV space in the target UV space corresponding to the position of the sub-model, wherein the arrangement of the sub-UV space in the target UV space is consistent with the arrangement of the sub-model in the specific three-dimensional model.

[0015] In one exemplary embodiment of this disclosure, the sub-model includes any one of the following: a box model or a patch model.

[0016] In an exemplary embodiment of this disclosure, the frame image to be processed is any frame image in a two-dimensional sequence frame set, and the method further includes: determining the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; and sequentially switching the three-dimensional images corresponding to each frame image according to the arrangement order of each frame image in the two-dimensional sequence frame set to obtain the target three-dimensional animation.

[0017] According to a second aspect of this disclosure, a three-dimensional image generation apparatus is provided, characterized in that the apparatus comprises: a pixel data extraction module for extracting pixel data of each pixel point in a two-dimensional frame image to be processed; and a three-dimensional image generation module for projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel point in the frame image to be processed, thereby obtaining a three-dimensional image corresponding to the frame image to be processed.

[0018] According to a third aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described three-dimensional image generation method.

[0019] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the above-described three-dimensional image generation method by executing the executable instructions.

[0020] The technical solution disclosed herein has the following beneficial effects:

[0021] In the aforementioned 3D image generation process, pixel data of each pixel in the 2D frame image to be processed is extracted. Based on the pixel data of each pixel in the frame image to be processed, the frame image is projected onto a specific 3D model to obtain the corresponding 3D image. This process, by projecting a 2D image onto a 3D model, allows the 3D animation to retain pixel-style characteristics. This not only provides users with a novel visual experience but also simplifies the production process, eliminating the need for manual modeling and skinning, thus improving animation production efficiency and reducing labor costs to some extent.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0023] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0024] Figure 1 This diagram illustrates a flowchart of a three-dimensional image generation method in this exemplary embodiment;

[0025] Figure 2 An example diagram of a two-dimensional sequence frame set is shown in this exemplary embodiment;

[0026] Figure 3A This diagram illustrates an example of a box model in this exemplary embodiment.

[0027] Figure 3B An example diagram of a patch model is shown in this exemplary embodiment;

[0028] Figure 3C This illustration shows a specific three-dimensional model example in this exemplary embodiment;

[0029] Figure 4 An example diagram illustrating a three-dimensional image rendering effect in this exemplary embodiment is shown;

[0030] Figure 5A An example diagram of a planar grid is shown in this exemplary embodiment;

[0031] Figure 5B This illustration shows an example of adding a center point to the center of a graphic element in this exemplary embodiment.

[0032] Figure 5C This illustration shows an example of a dot matrix pattern in this exemplary embodiment;

[0033] Figure 5D An example diagram illustrating the model structure of a three-dimensional model in this exemplary embodiment is shown.

[0034] Figure 5E This illustration shows an example of a three-dimensional model composed of assembled box models in this exemplary embodiment;

[0035] Figure 6 An example diagram showing UV map overlay of a box model in this exemplary embodiment is shown;

[0036] Figure 7 An example diagram illustrating UV mapping overlap of a patch model in this exemplary embodiment is shown.

[0037] Figure 8 This diagram illustrates a flowchart of generating a specific 3D model in this exemplary embodiment;

[0038] Figure 9 This diagram illustrates a flowchart of generating a target 3D animation in this exemplary embodiment;

[0039] Figure 10 This diagram illustrates a structural block diagram of a three-dimensional image generation apparatus according to this exemplary embodiment;

[0040] Figure 11 An electronic device for implementing the above-described three-dimensional image generation method is shown in this exemplary embodiment. Detailed Implementation

[0041] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0042] The terms “a,” “an,” “the,” and “the” are used in this specification to indicate the presence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended inclusion and to mean that there may be other elements / components / etc. in addition to the listed elements / components / etc.; the terms “first” and “second” are used only as markings and are not a limitation on the number of objects.

[0043] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0044] In related technologies, when creating 3D animation, it is usually necessary to first determine the original animation artwork, and then create corresponding motion resources for the skinned model based on the artwork. The animation production process itself is quite cumbersome. If pixel style is to be achieved on top of this, vertex animation is superimposed on the skeletal animation, which will greatly affect the production cost and efficiency. It should be noted that skinning is a technique that binds model objects to skeletons. In 3D animation software, model objects and skeletons are independent of each other. Model objects need to be bound to skeletons, and the skeletons drive the model objects to produce reasonable movements.

[0045] In view of one or more of the above-mentioned problems, an exemplary embodiment of this disclosure provides a three-dimensional image generation method, which can produce each frame of a three-dimensional animation, thereby realizing pixel-style three-dimensional animation.

[0046] Exemplary embodiments of this disclosure provide a method for generating three-dimensional images, such as... Figure 1 As shown, the three-dimensional image generation method may specifically include the following steps S110 to S120:

[0047] Step S110: Extract pixel data of each pixel in the two-dimensional frame image to be processed;

[0048] Step S120: Based on the pixel data of each pixel in the frame image to be processed, project the frame image to be processed onto a specific three-dimensional model to obtain the three-dimensional image corresponding to the frame image to be processed.

[0049] In the process of generating the above-mentioned 3D images, by projecting the 2D images onto the 3D model, the 3D animation can retain pixel style features. This not only brings users a novel visual experience, but also simplifies the production process. There is no need for manual modeling and skinning, which can improve the efficiency of animation production and reduce labor costs to a certain extent.

[0050] The following sections respectively address... Figure 1 Each step in the process will be explained in detail.

[0051] Step S110: Extract pixel data of each pixel in the two-dimensional frame image to be processed.

[0052] The frame image to be processed is a two-dimensional image, which can be any frame image from a two-dimensional sequence of frames. For example, such as... Figure 2 As shown in the two-dimensional sequence frame set, any frame image in the sequence frame set can be used as the frame image to be processed.

[0053] The frame image to be processed can be divided into several small squares, each of which can be called a pixel. Pixel data refers to the color parameters corresponding to each pixel. For example, the (R, G, B, A) parameters of each pixel can be extracted. The (R, G, B, A) parameters can represent the color space parameters of red, green, blue, and alpha, where the alpha parameter can be used to characterize opacity.

[0054] Step S120: Based on the pixel data of each pixel in the frame image to be processed, project the frame image to be processed onto a specific three-dimensional model to obtain the three-dimensional image corresponding to the frame image to be processed.

[0055] By mapping the pixel data of each pixel in the frame image to the corresponding part of the 3D model, the color information of the specific 3D model can be obtained, and thus the 3D image corresponding to the frame image to be processed can be presented.

[0056] To facilitate projection mapping, a specific 3D model can be a 3D model composed of multiple sub-models, wherein the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed.

[0057] Sub-models include any of the following: box model, patch model.

[0058] For example, if the sub-model is a box model, its shape can be as follows: Figure 3A As shown in the box model.

[0059] For example, if the sub-model is a patch model, its shape can be as follows: Figure 3B The image shows a patch model. This patch model can be a multi-patch model that has undergone offset and overlay processing; or it can be a single-patch model that has been processed by a visual algorithm that produces a stereoscopic side view effect, such as parallax mapping algorithms like bump mapping offset and ray stepping.

[0060] It should be noted that the box model and patch model here are only illustrative examples of the sub-model shapes. In practical applications, other models capable of producing stereoscopic visual effects can also be used as sub-models. Regardless of the shape of the sub-model, it can be arranged according to the pixel arrangement of the frame image to be processed, thereby obtaining a specific 3D model, such as... Figure 3C As shown.

[0061] To facilitate mapping, the number of sub-models contained in a specific 3D model can be the same as the number of pixels in the frame image to be processed, that is, there is a one-to-one correspondence between sub-models and pixels.

[0062] In one optional implementation, in step S120, the frame image to be processed is projected onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed, thereby obtaining a three-dimensional image corresponding to the frame image to be processed. This can be achieved through the following steps: according to the pixel data of each pixel in the frame image to be processed, each sub-model in the specific three-dimensional model is filled with color to obtain a three-dimensional image corresponding to the frame image to be processed.

[0063] Specifically, based on the pixel data of each pixel in the frame image to be processed, the color to be filled in each sub-model of a specific 3D model can be determined, and each sub-model can be filled in according to the determined fill color to obtain the 3D image corresponding to the frame image to be processed.

[0064] It should be noted that there is a correspondence between the pixels of the frame image to be processed and the sub-models in a specific 3D model. Each sub-model can uniquely correspond to a pixel in the frame image to be processed, thus the pixel data of a pixel can be mapped to the sub-model. For example, the pixel data corresponding to the pixel in the upper left corner of the frame image to be processed can be mapped to the sub-model in the upper left corner of the specific model. In addition, since a pixel usually corresponds to a color, each sub-model can be filled with only one color.

[0065] In the above steps, a 3D image is constructed by filling in sub-models, eliminating the need to build animation resources through modeling, skinning, and other operations. This simplifies the animation production process to some extent and improves the efficiency of animation production.

[0066] In one optional implementation, the above-mentioned method of color-filling each sub-model in a specific 3D model based on the pixel data of each pixel in the frame image to be processed to obtain the 3D image corresponding to the frame image to be processed can be achieved through the following steps: mapping the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space, where the target UV space is the UV space corresponding to the specific 3D model and the sub-UV space is the UV space corresponding to the sub-model; searching for the color information corresponding to each sub-model in the specific 3D model in the target UV space to determine the fill color corresponding to each sub-model in the specific 3D model; and color-filling each sub-model in the specific 3D model according to the fill color corresponding to each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

[0067] For example, such as Figure 4As shown, after the frame image 401 to be processed is mapped to a specific three-dimensional model, the three-dimensional image presentation effect shown in the three-dimensional image 402 can be obtained by color filling, which to a certain extent enhances the three-dimensionality of the virtual object in the two-dimensional frame image.

[0068] The target UV space is the UV space corresponding to a specific 3D model, and the sub-UV space is the UV space corresponding to a sub-model. UV stands for texture coordinates, which defines the position information of each point on the model's surface.

[0069] The target UV space can be composed of multiple sub-UV spaces. Each sub-UV space corresponds one-to-one with a sub-model, and the UV maps of the sub-models can be placed there. The pixel data of each pixel in the frame image to be processed is mapped to the respective sub-UV spaces of the target UV space.

[0070] The pixel data of each pixel in the frame image to be processed is mapped to the respective sub-UV spaces of the target UV space. This process essentially tiles the frame image onto the target UV space. The fill color of each sub-model can be determined by finding its corresponding sub-UV space. Since the Alpha parameter in the (R, G, B, A) parameters of a pixel can be used to characterize opacity, mapping allows the sub-model to appear opaque, semi-transparent, or transparent, thus creating a three-dimensional virtual object.

[0071] In the above process, by using the target UV space corresponding to a specific 3D model, the frame image to be processed is mapped to the specific 3D model, eliminating the need for modeling, skinning, and other processing, which simplifies the production steps of 3D images to a certain extent.

[0072] In an optional implementation, the above-mentioned mapping of pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space can be achieved by the following steps: determining the color identifier corresponding to each pixel in the frame image to be processed on the color table based on the pixel data of each pixel in the frame image to be processed; determining the color identifier corresponding to each sub-UV space of the target UV space on the color table based on the color identifier corresponding to each pixel in the frame image to be processed.

[0073] The color table contains multiple colors, each with a corresponding color identifier. These identifiers allow for the identification of different colors within the color table, mapping the pixel data of each pixel in the frame image to the respective sub-UV spaces of the target UV space. The entire process is simple and easy to implement.

[0074] It should be noted that when searching for the color information of each sub-model in a specific 3D model in the target UV space, and then determining the corresponding fill color of each sub-model in the specific 3D model, the fill color of each sub-model in the specific 3D model can be determined by searching for the color identifiers corresponding to each sub-UV space in the target UV space.

[0075] In addition, a specific 3D model can be a pre-created 3D model or a model dynamically created during the animation production process.

[0076] In one alternative implementation, before projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to obtain the three-dimensional image corresponding to the frame image to be processed, the specific three-dimensional model can be created by the following steps: creating a specific three-dimensional model according to the pixel arrangement of the frame image to be processed.

[0077] Specifically, the pixel arrangement can be represented by the number of pixels contained in the horizontal and vertical directions of the frame image to be processed. For example, if the frame image to be processed has x pixels horizontally and y pixels vertically, then a specific 3D model can have x sub-models placed horizontally and y sub-models placed vertically.

[0078] In the above steps, the arrangement of the sub-models in the specific 3D model is kept consistent with the arrangement of the pixels in the frame image to be processed, so that a one-to-one correspondence is formed between the sub-models and the pixels, so that the frame image to be processed can be quickly projected onto the specific 3D model.

[0079] In one optional implementation, the creation of a specific three-dimensional model based on the pixel arrangement of the frame image to be processed can be achieved through the following steps: creating a planar mesh corresponding to the pixel arrangement of the frame image to be processed; adding center points to the center positions of each primitive in the planar mesh; deleting each primitive and its associated points; and placing sub-models at each center point to obtain the specific three-dimensional model.

[0080] When creating a planar grid corresponding to the pixel arrangement of the frame image to be processed, the row and column values ​​of the planar grid can depend on the number of pixels in the horizontal and vertical directions of the frame image to be processed. For example, such as... Figure 5A As shown, if the frame image to be processed has x pixels horizontally and y pixels vertically, then the row and column values ​​of the planar grid can be set to X*Y. It should be noted that the size ratio of each small square in the planar grid can also be set with reference to the size ratio of the pixels in the frame image to avoid disproportionate virtual object proportions in the generated 3D image.

[0081] A primitive refers to a small square composed of vertices in a planar mesh. When adding center points to the center positions of each primitive in the planar mesh, the number of primitives in the planar mesh can be used as the number of iterations. Within each iteration, a center point is added to each primitive sequentially, as exemplified by... Figure 5B As shown. After adding a center point to each graphic element, you can delete each graphic element and its associated points, retaining only the added center points, resulting in the following: Figure 5C The dot matrix shown. A sub-model structure of the same size can be copied at each center point. Taking the box model structure as an example, the following can be obtained: Figure 5D The model structure shown is a 3D model. After UV mapping of this 3D model structure, the following can be obtained: Figure 5E The model shown is a 3D model assembled from box models.

[0082] It should be noted that in practical applications, the size of the sub-models and the spacing between them can be set according to actual needs, and no specific limitations are made here.

[0083] In the above steps, by constructing a specific three-dimensional model, a projection model is provided for converting two-dimensional images into three-dimensional images, realizing the conversion of virtual objects from two-dimensional to three-dimensional and improving the production efficiency of three-dimensional images.

[0084] In one alternative implementation, the UV maps of each face of the sub-model can be overlapped and then moved to the sub-UV space in the target UV space corresponding to the position of the sub-model. The arrangement of the sub-UV spaces in the target UV space is consistent with the arrangement of the sub-model in the specific 3D model.

[0085] The arrangement of sub-UV spaces in the target UV space is consistent with the arrangement of sub-models in a specific 3D model, ensuring a one-to-one correspondence between the sub-UV spaces and the sub-models. The UV maps of each face of the sub-model can be tiled, overlapped, and then moved to their corresponding positions in the target UV space to complete the creation of the specific 3D model. Specifically, when overlapping UV maps, the four vertices of the UV map corresponding to each face of the sub-model can be located and overlapped one-to-one.

[0086] Taking the box model as an example, such as Figure 6 As shown, the UV maps of each face in the box model 602 in the upper right corner of the specific 3D model 601 can be overlapped and placed in the upper right corner of the target UV space 603.

[0087] Taking the sub-model as a patch model as an example, such as Figure 7As shown, the UV maps of each face in any patch model in a specific 3D model 701 can be overlaid, and based on the position of any patch model in the specific 3D model 701, the overlaid UV maps are placed at the corresponding positions in the target UV space 703.

[0088] It should be noted that this specific 3D model can be generated automatically by a program or manually created by the user using 3D computer graphics software; no specific limitations are made here.

[0089] In the above process, a target UV space for a specific 3D model is constructed so that each sub-model in the specific 3D model can be filled with color based on the target UV space, so that the sub-model presents an appearance corresponding to the sub-UV space.

[0090] Taking the box model as an example, such as Figure 8 As shown, a flowchart for generating a specific 3D model is provided, which may include the following steps:

[0091] Step S801: Create a planar grid corresponding to the pixel arrangement of the frame image to be processed;

[0092] Step S802: Based on the number of elements in the planar grid, create a loop and add a center point to each element sequentially within the loop;

[0093] Step S803: Delete each graphic element and its associated points;

[0094] Step S804: Place the box model at each center point;

[0095] Step S805: Overlay the UV maps of each face of each box model and move them to the sub-UV space in the target UV space corresponding to the position of each box model.

[0096] Step S806: Complete the creation of the specific 3D model.

[0097] Figure 8 In the steps shown, the target UV space can be the UV space corresponding to a specific 3D model, and the sub-UV space can be the UV space corresponding to a box model. The created specific 3D model resembles a wall with thickness, and can convert virtual objects in a 2D image into 3D virtual objects.

[0098] In one optional implementation, the above-mentioned frame image to be processed can be any frame image in a two-dimensional sequence frame set. Specifically, the target three-dimensional animation can be obtained through the following steps: determining the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; and switching the three-dimensional images corresponding to each frame image in turn according to the arrangement order of each frame image in the two-dimensional sequence frame set to obtain the target three-dimensional animation.

[0099] Specifically, based on the steps described above for generating the 3D image corresponding to the frame image to be processed, the 3D image corresponding to each frame image in the 2D sequence frame can be determined. Then, according to the arrangement order of each frame image in the 2D sequence frame set, the 3D images corresponding to each frame image are switched sequentially, so that the virtual objects in the image can move, thereby obtaining the target 3D animation.

[0100] like Figure 9 As shown, a flowchart for generating a target 3D animation is provided, which may include the following steps:

[0101] Step S901: Determine the frame image to be processed in the two-dimensional sequence frame set;

[0102] Step S902: Extract the pixel data of each pixel in the frame image to be processed;

[0103] Step S903: Determine the color identifier corresponding to each pixel in the color table based on the pixel data of each pixel in the frame image to be processed.

[0104] Step S904: Determine the color identifier of each sub-UV space in the target UV space on the color table according to the color identifier of each pixel on the color table.

[0105] Step S905: Determine the fill color corresponding to each sub-model in the specific 3D model based on the color identifier of each sub-UV space in the target UV space on the color table.

[0106] Step S906: According to the fill color corresponding to each sub-model in the specific 3D model, fill each sub-model in the specific 3D model with color to obtain the 3D image corresponding to the frame image to be processed.

[0107] Step S907: After determining the three-dimensional images corresponding to each frame in the two-dimensional sequence frame set, the three-dimensional images corresponding to each frame are switched sequentially to obtain the target three-dimensional animation.

[0108] Figure 9 In the steps shown, the specific 3D model can be a 3D model composed of multiple sub-models, and the arrangement of the sub-models can be consistent with the pixel arrangement of the frame image to be processed. Furthermore, the target UV space can be the UV space corresponding to the specific 3D model, and the sub-UV spaces can be the UV spaces corresponding to the sub-models. By converting a 2D sequence of frames into a 3D animation, not only is the stereoscopic effect of the animation improved, but the pixel style characteristics of the 2D animation are also preserved, providing a novel visual presentation effect.

[0109] Exemplary embodiments of this disclosure also provide a three-dimensional image generation apparatus, such as... Figure 10As shown, the three-dimensional image generation device 1000 may include:

[0110] The pixel data extraction module 1010 is used to extract pixel data of each pixel in the two-dimensional frame image to be processed;

[0111] The 3D image generation module 1020 is used to project the frame image to be processed onto a specific 3D model based on the pixel data of each pixel in the frame image to be processed, so as to obtain the 3D image corresponding to the frame image to be processed.

[0112] In one optional implementation, a specific three-dimensional model in the three-dimensional image generation apparatus 1000 can be a three-dimensional model composed of multiple sub-models, wherein the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed.

[0113] In one optional implementation, the three-dimensional image generation module 1020 may include a color filling module, which can be configured to fill each sub-model in a specific three-dimensional model with color according to the pixel data of each pixel in the frame image to be processed, so as to obtain a three-dimensional image corresponding to the frame image to be processed.

[0114] In an optional implementation, the color filling module described above can be configured to: map the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space, wherein the target UV space is the UV space corresponding to a specific 3D model, and the sub-UV space is the UV space corresponding to a sub-model; search for the color information corresponding to each sub-model in the specific 3D model in the target UV space to determine the fill color corresponding to each sub-model in the specific 3D model; and fill each sub-model in the specific 3D model with color according to the fill color corresponding to each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

[0115] In one optional implementation, the color filling module maps the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space. This can be configured to: determine the color identifier corresponding to each pixel in the frame image to be processed on the color table based on the pixel data of each pixel in the frame image to be processed; and determine the color identifier corresponding to each sub-UV space of the target UV space on the color table based on the color identifier corresponding to each pixel in the frame image to be processed on the color table.

[0116] In one optional implementation, before the three-dimensional image generation apparatus 1000 projects the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed, and obtains the three-dimensional image corresponding to the frame image to be processed, a specific three-dimensional module creation module may be executed to create a specific three-dimensional model according to the pixel arrangement of the frame image to be processed.

[0117] In one alternative implementation, the specific 3D module creation module can be configured to: create a planar mesh corresponding to the pixel arrangement of the frame image to be processed; add center points to the center positions of each primitive in the planar mesh; delete each primitive and its associated points; and place sub-models at each center point to obtain the specific 3D model.

[0118] In one optional embodiment, the three-dimensional image generation device 1000 further includes: a UV space construction module, which is used to overlap the UV maps of each face of the sub-model and move them to the sub-UV space in the target UV space corresponding to the position of the sub-model, wherein the arrangement of the sub-UV space in the target UV space is consistent with the arrangement of the sub-model in the specific three-dimensional model.

[0119] In one alternative implementation, the sub-model of the 3D image generation device 1000 may include any one of the following: a box model or a patch model.

[0120] In one optional implementation, the frame image to be processed in the three-dimensional image generation device 1000 is any frame image in a two-dimensional sequence frame set, and may further include an animation generation module, which can be configured to: determine the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; and sequentially switch the three-dimensional images corresponding to each frame image according to the arrangement order of each frame image in the two-dimensional sequence frame set to obtain the target three-dimensional animation.

[0121] The specific details of each part of the above-mentioned three-dimensional image generation apparatus 1000 have been described in detail in the method section of the embodiments. For any undisclosed details, please refer to the method section of the embodiments, and therefore will not be repeated here.

[0122] Exemplary embodiments of this disclosure also provide a computer-readable storage medium storing a program product capable of implementing the three-dimensional image generation method described above. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when run on an electronic device, causes the electronic device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0123] Specifically, a program product stored on a computer-readable storage medium enables an electronic device to perform the following steps:

[0124] Extract pixel data of each pixel in the two-dimensional image to be processed;

[0125] Based on the pixel data of each pixel in the frame image to be processed, the frame image to be processed is projected onto a specific three-dimensional model to obtain the three-dimensional image corresponding to the frame image to be processed.

[0126] In one optional implementation, the specific 3D model is a 3D model composed of multiple sub-models, and the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed.

[0127] In one optional implementation, the above-mentioned projection of the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed to obtain the three-dimensional image corresponding to the frame image to be processed can be achieved by the following steps: according to the pixel data of each pixel in the frame image to be processed, each sub-model in the specific three-dimensional model is filled with color to obtain the three-dimensional image corresponding to the frame image to be processed.

[0128] In one optional implementation, the above-mentioned method of color-filling each sub-model in a specific 3D model based on the pixel data of each pixel in the frame image to be processed to obtain the 3D image corresponding to the frame image to be processed can be achieved through the following steps: mapping the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space, where the target UV space is the UV space corresponding to the specific 3D model and the sub-UV space is the UV space corresponding to the sub-model; searching for the color information corresponding to each sub-model in the specific 3D model in the target UV space to determine the fill color corresponding to each sub-model in the specific 3D model; and color-filling each sub-model in the specific 3D model according to the fill color corresponding to each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

[0129] In one optional implementation, the above-mentioned mapping of pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space can be achieved by the following steps: determining the color identifier corresponding to each pixel in the frame image to be processed on the color table based on the pixel data of each pixel in the frame image to be processed; determining the color identifier corresponding to each sub-UV space of the target UV space on the color table based on the color identifier corresponding to each pixel in the frame image to be processed.

[0130] In one alternative implementation, before projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to obtain the three-dimensional image corresponding to the frame image to be processed, the following steps may be performed: creating a specific three-dimensional model according to the pixel arrangement of the frame image to be processed.

[0131] In one optional implementation, the creation of a specific three-dimensional model based on the pixel arrangement of the frame image to be processed can be achieved through the following steps: creating a planar mesh corresponding to the pixel arrangement of the frame image to be processed; adding center points to the center positions of each primitive in the planar mesh; deleting each primitive and its associated points; and placing sub-models at each center point to obtain the specific three-dimensional model.

[0132] In an alternative implementation, the following steps may also be performed: after overlapping the UV maps of each face of the sub-model, move them to the sub-UV space in the target UV space corresponding to the position of the sub-model, wherein the arrangement of the sub-UV space in the target UV space is consistent with the arrangement of the sub-model in the specific 3D model.

[0133] In one alternative implementation, the sub-model includes any one of the following: a box model or a patch model.

[0134] In one optional implementation, the above-mentioned frame image to be processed is any frame image in a two-dimensional sequence frame set, and the following steps can also be performed: determine the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; according to the arrangement order of each frame image in the two-dimensional sequence frame set, switch the three-dimensional images corresponding to each frame image in turn to obtain the target three-dimensional animation.

[0135] In the above steps, by projecting the two-dimensional image onto the three-dimensional model, the three-dimensional animation can retain pixel style features. This not only brings users a novel visual experience but also simplifies the production process. It eliminates the need for manual modeling and skinning, thereby improving animation production efficiency and reducing labor costs to a certain extent.

[0136] The program product may be a portable compact disc read-only memory (CD-ROM) and include program code, and may run on an electronic device, such as a personal computer. However, the program product disclosed herein is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0137] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0138] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying 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 readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0139] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0140] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0141] Exemplary embodiments of this disclosure also provide an electronic device capable of implementing the above-described three-dimensional image generation method. Referring below... Figure 11 To describe an electronic device 1100 according to such an exemplary embodiment of the present disclosure. Figure 11 The electronic device 1100 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0142] like Figure 11 As shown, the electronic device 1100 can be represented as a general-purpose computing device. The components of the electronic device 1100 may include, but are not limited to: at least one processing unit 1110, at least one storage unit 1120, a bus 1130 connecting different system components (including storage unit 1120 and processing unit 1110), and a display unit 1140.

[0143] The storage unit 1120 stores program code that can be executed by the processing unit 1110, causing the processing unit 1110 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0144] Specifically, the processing unit 1110 may perform the following steps:

[0145] Extract pixel data of each pixel in the two-dimensional image to be processed;

[0146] Based on the pixel data of each pixel in the frame image to be processed, the frame image to be processed is projected onto a specific three-dimensional model to obtain the three-dimensional image corresponding to the frame image to be processed.

[0147] In one optional implementation, the specific 3D model is a 3D model composed of multiple sub-models, and the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed.

[0148] In one optional implementation, the above-mentioned projection of the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to be processed to obtain the three-dimensional image corresponding to the frame image to be processed can be achieved by the following steps: according to the pixel data of each pixel in the frame image to be processed, each sub-model in the specific three-dimensional model is filled with color to obtain the three-dimensional image corresponding to the frame image to be processed.

[0149] In one optional implementation, the above-mentioned method of color-filling each sub-model in a specific 3D model based on the pixel data of each pixel in the frame image to be processed to obtain the 3D image corresponding to the frame image to be processed can be achieved through the following steps: mapping the pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space, where the target UV space is the UV space corresponding to the specific 3D model and the sub-UV space is the UV space corresponding to the sub-model; searching for the color information corresponding to each sub-model in the specific 3D model in the target UV space to determine the fill color corresponding to each sub-model in the specific 3D model; and color-filling each sub-model in the specific 3D model according to the fill color corresponding to each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

[0150] In one optional implementation, the above-mentioned mapping of pixel data of each pixel in the frame image to be processed to each sub-UV space of the target UV space can be achieved by the following steps: determining the color identifier corresponding to each pixel in the frame image to be processed on the color table based on the pixel data of each pixel in the frame image to be processed; determining the color identifier corresponding to each sub-UV space of the target UV space on the color table based on the color identifier corresponding to each pixel in the frame image to be processed.

[0151] In one alternative implementation, before projecting the frame image to be processed onto a specific three-dimensional model based on the pixel data of each pixel in the frame image to obtain the three-dimensional image corresponding to the frame image to be processed, the following steps may be performed: creating a specific three-dimensional model according to the pixel arrangement of the frame image to be processed.

[0152] In one optional implementation, the creation of a specific three-dimensional model based on the pixel arrangement of the frame image to be processed can be achieved through the following steps: creating a planar mesh corresponding to the pixel arrangement of the frame image to be processed; adding center points to the center positions of each primitive in the planar mesh; deleting each primitive and its associated points; and placing sub-models at each center point to obtain the specific three-dimensional model.

[0153] In an alternative implementation, the following steps may also be performed: after overlapping the UV maps of each face of the sub-model, move them to the sub-UV space in the target UV space corresponding to the position of the sub-model, wherein the arrangement of the sub-UV space in the target UV space is consistent with the arrangement of the sub-model in the specific 3D model.

[0154] In one alternative implementation, the sub-model includes any one of the following: a box model or a patch model.

[0155] In one optional implementation, the above-mentioned frame image to be processed is any frame image in a two-dimensional sequence frame set, and the following steps can also be performed: determine the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; according to the arrangement order of each frame image in the two-dimensional sequence frame set, switch the three-dimensional images corresponding to each frame image in turn to obtain the target three-dimensional animation.

[0156] In the above steps, by projecting the two-dimensional image onto the three-dimensional model, the three-dimensional animation can retain pixel style features. This not only brings users a novel visual experience but also simplifies the production process. It eliminates the need for manual modeling and skinning, thereby improving animation production efficiency and reducing labor costs to a certain extent.

[0157] Storage unit 1120 may include readable media in the form of volatile storage units, such as random access memory (RAM) 1121 and / or cache memory 1122, and may further include read-only memory (ROM) 1123.

[0158] Storage unit 1120 may also include a program / utility 1124 having a set (at least one) program module 1125, such program module 1125 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0159] Bus 1130 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0160] Electronic device 1100 can also communicate with one or more external devices 1200 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 1100, and / or with any device that enables the electronic device 1100 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1150. Furthermore, electronic device 1100 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1160. Figure 11 As shown, network adapter 1160 communicates with other modules of electronic device 1100 via bus 1130. It should be understood that, although... Figure 11 As not shown, other hardware and / or software modules can be used in conjunction with electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0161] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the exemplary embodiments of this disclosure.

[0162] Furthermore, the above figures are merely illustrative representations of the processes included in the methods according to exemplary embodiments of this disclosure, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0163] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0164] Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be embodied in entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.” Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0165] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is defined only by the appended claims.

Claims

1. A method for generating a three-dimensional image, characterized in that, The method includes: Extract pixel data of each pixel in the two-dimensional image to be processed; Based on the pixel data of each pixel in the frame image to be processed, the frame image to be processed is projected onto a specific three-dimensional model to obtain a three-dimensional image corresponding to the frame image to be processed; the specific three-dimensional model is a three-dimensional model composed of multiple sub-models, and the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed. The specific 3D model is created through the following steps: Create a planar grid corresponding to the pixel arrangement of the frame image to be processed; Add a center point to the center position of each graphic element in the planar grid; Delete each of the graphic elements and the associated points of each of the graphic elements; The sub-models are placed at each of the stated center points to obtain the specific three-dimensional model.

2. The method according to claim 1, characterized in that, The step of projecting the frame image to be processed onto a specific 3D model based on the pixel data of each pixel in the frame image to be processed, to obtain the 3D image corresponding to the frame image to be processed, includes: Based on the pixel data of each pixel in the frame image to be processed, the sub-models in the specific 3D model are filled with color to obtain the 3D image corresponding to the frame image to be processed.

3. The method according to claim 2, characterized in that, The step of filling each sub-model in the specific 3D model with color based on the pixel data of each pixel in the frame image to be processed, to obtain the 3D image corresponding to the frame image to be processed, includes: The pixel data of each pixel in the frame image to be processed is mapped to each sub-UV space of the target UV space, wherein the target UV space is the UV space corresponding to the specific 3D model, and the sub-UV space is the UV space corresponding to the sub-model. Find the color information corresponding to each sub-model in the specific 3D model in the target UV space, and determine the fill color corresponding to each sub-model in the specific 3D model; Based on the fill color corresponding to each sub-model in the specific 3D model, the color is filled into each sub-model in the specific 3D model to obtain the 3D image corresponding to the frame image to be processed.

4. The method according to claim 3, characterized in that, The step of mapping the pixel data of each pixel in the frame image to each sub-UV space of the target UV space includes: Based on the pixel data of each pixel in the frame image to be processed, determine the color identifier corresponding to each pixel in the frame image to be processed on the color table; Based on the color identifier of each pixel in the frame image to be processed on the color table, determine the color identifier of each sub-UV space in the target UV space on the color table.

5. The method according to claim 1, characterized in that, The method further includes: After overlapping the UV maps of each face of the sub-model, they are moved to the sub-UV space in the target UV space corresponding to the position of the sub-model. The arrangement of the sub-UV space in the target UV space is consistent with the arrangement of the sub-model in the specific 3D model.

6. The method according to claim 1, characterized in that, The sub-model includes any of the following: Box model, facet model.

7. The method according to claim 1, characterized in that, The frame image to be processed is any frame image in a two-dimensional sequence frame set, and the method further includes: Determine the three-dimensional image corresponding to each frame image in the two-dimensional sequence frame set; According to the arrangement order of each frame image in the two-dimensional sequence frame set, the three-dimensional images corresponding to each frame image are switched sequentially to obtain the target three-dimensional animation.

8. A three-dimensional image generation device, characterized in that, The device includes: The pixel data extraction module is used to extract pixel data of each pixel in the two-dimensional image to be processed. A 3D image generation module is used to project the frame image to be processed onto a specific 3D model based on the pixel data of each pixel in the frame image to be processed, so as to obtain a 3D image corresponding to the frame image to be processed; the specific 3D model is a 3D model composed of multiple sub-models, and the arrangement of the sub-models is consistent with the pixel arrangement of the frame image to be processed. The specific 3D model is created through the following steps: Create a planar grid corresponding to the pixel arrangement of the frame image to be processed; Add a center point to the center position of each graphic element in the planar grid; Delete each of the graphic elements and the associated points of each of the graphic elements; The sub-models are placed at each of the stated center points to obtain the specific three-dimensional model.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 7 by executing the executable instructions.

Images