Model generation method and apparatus, storage medium, and electronic device

Abstract

A model generation method and device, a storage medium and an electronic device are disclosed. The method comprises: obtaining a plurality of initial models, wherein the plurality of initial models comprise a first model and a second model, the first model and the second model are models of different body shapes, and the wiring and texture coordinates of the plurality of initial models are the same; determining a target fusion degree, wherein the target fusion degree is used to represent the fusion degree of the first model and the second model; and fusing the first model and the second model based on the target fusion degree to generate a target model. The present application solves the technical problem of low model generation efficiency of different body shapes in related technologies.

Description

Technical Field

[0001] This invention relates to the field of computers, and more specifically, to a model generation method, apparatus, storage medium, and electronic device. Background Technology

[0002] Currently, 3D online games often feature a large number of character models with different body types, which are often due to differences in age, race, gender, and other factors. In related technologies, creating separate art assets for different body types requires 3D artists to use software, resulting in low work efficiency and high labor costs. Furthermore, it generates a large number of textures, increasing the game's file size and consequently increasing performance overhead.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] At least some embodiments of the present invention provide a model generation method, apparatus, storage medium, and electronic device to at least solve the technical problem of low generation efficiency of models of different sizes in the related art.

[0005] According to one embodiment of the present invention, a model generation method is provided, comprising: acquiring a plurality of initial models, wherein the plurality of initial models include: a first model and a second model, the first model and the second model being models of different sizes, and the plurality of initial models having the same topology and texture coordinates; determining a target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model; and fusing the first model and the second model based on the target fusion degree to generate a target model.

[0006] Optionally, the first model and the second model are fused based on the target fusion degree to generate a target model, including: determining the fusion requirements of the first model, wherein the fusion requirements are used to characterize the fusion parts of the first model that are fused with the second model, and the fusion parts include one of the following: all parts or local parts; and fusion of the first model and the second model based on the fusion requirements and the target fusion degree to generate the target model.

[0007] Optionally, the first model and the second model are fused based on the fusion requirements and the target fusion degree to generate a target model, including: in response to the fusion part being all parts, the first model and the second model are deformed based on the target fusion degree to obtain a first deformed model and a second deformed model; the first deformed model and the second deformed model are linearly combined to generate the target model.

[0008] Optionally, the first model and the second model are deformed based on the target fusion degree to obtain a first deformed model and a second deformed model, including: determining a first deformability of the first model and a second deformability of the second model based on the target fusion degree; deforming the first model based on the first deformability degree to obtain a first deformed model; and deforming the second model based on the second deformability degree to obtain a second deformed model.

[0009] Optionally, the first model and the second model are fused based on the fusion requirements and the target fusion degree to generate the target model, including: in response to the fusion part being a local part and in response to the target operation acting on the first model, determining the first part in the first model corresponding to the target operation; replacing the first part in the first model with the second part in the second model to obtain the fused model, wherein the second part and the first part are the same part; deforming the first model and the fused model respectively based on the target fusion degree to obtain a first deformed model and a deformed fused model; and linearly combining the first deformed model and the deformed fused model to generate the target model.

[0010] Optionally, deforming the first model and the fusion model based on the target fusion degree to obtain the second deformed model and the deformed fusion model includes: determining the model difference degree between the first model and the second model, wherein the model difference degree is used to characterize the degree of difference between the first model and the second model; in response to the model difference degree being less than or equal to a preset difference degree, deforming the first model and the fusion model based on the target fusion degree to obtain the first deformed model and the deformed fusion model.

[0011] Optionally, in response to the model difference degree being greater than a preset difference degree, deforming the first model and the fused model based on the target fusion degree to obtain the first deformed model and the deformed fused model further includes: repairing the first part of the fused model to obtain the first repaired model; and deforming the first model and the first repaired model based on the target fusion degree to obtain the first deformed model and the deformed fused model.

[0012] Optionally, repairing the first part of the fusion model to obtain the first repair model includes: cutting the first part of the fusion model to obtain the first cut model; adjusting the position of the first cut model to obtain the first adjusted model; and restoring the first part of the first adjusted model based on the first model to obtain the first repair model.

[0013] Optionally, linearly combining the first deformation model and the deformation fusion model to generate the target model includes: linearly combining the first deformation model and the deformation fusion model to generate the target deformation model; responding to the target operation acting on the target deformation model to determine the third part of the target deformation model; repairing the third part of the target deformation model to obtain the second repair model; and repairing the target parts in the second repair model that meet the preset conditions to generate the target model.

[0014] According to one embodiment of the present invention, a model generation apparatus is also provided, comprising: an acquisition module for acquiring a plurality of initial models, wherein the plurality of initial models include: a first model and a second model, the first model and the second model being models of different sizes, and the plurality of initial models having the same topology and texture coordinates; a determination module for determining a target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model; and a fusion module for fusing the first model and the second model based on the target fusion degree to generate a target model.

[0015] According to one embodiment of the present invention, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the model generation method described in any of the above claims when run by a processor.

[0016] According to one embodiment of the present invention, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the model generation method described in any of the preceding claims.

[0017] In at least some embodiments of the present invention, a method is adopted to automatically combine models of different body types by acquiring a first model and a second model, determining a target fusion degree, and then fusing the first model and the second model based on the target fusion degree to generate a target model. It is noteworthy that since the topology and texture coordinates of the first and second models are identical, the positions of the same parts in models of different body types are the same, eliminating the need for 3D artists to perform additional dragging and projection. Furthermore, the first model and the second model can be automatically fused based on the target fusion degree, eliminating the need for manual model fusion by 3D artists. This achieves the technical effects of reducing model generation time, improving model generation efficiency, and reducing the wear and tear on production personnel from mechanized labor. Simultaneously, all resources share one or more sets of basic resources, reducing the size of basic resources in the game, thereby reducing the game package size, improving game quality and running speed, and thus solving the technical problem of low generation efficiency for models of different body types in related technologies. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal for a model generation method according to an embodiment of the present invention.

[0020] Figure 2 This is a flowchart of a model generation method according to one embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of five male body types according to one optional embodiment of the present invention;

[0022] Figure 4a This is a schematic diagram of the wiring of a standard body model according to one optional embodiment of the present invention;

[0023] Figure 4b This is a schematic diagram of the UV of a standard body model according to one optional embodiment of the present invention;

[0024] Figure 5a This is a schematic diagram illustrating the fusion of multiple body types throughout the body according to one optional embodiment of the present invention;

[0025] Figure 5b and Figure 5c This is a schematic diagram of various body types with relatively small differences in body size, according to one optional embodiment of the present invention;

[0026] Figure 5d and Figure 5e This is a schematic diagram of various body types with significant differences in body size, according to one optional embodiment of the present invention;

[0027] Figure 6 This is a schematic diagram of node connections in a model generation method according to an optional embodiment of the present invention;

[0028] Figure 7 This is a schematic diagram of an operation interface for setting the target fusion degree according to one optional embodiment of the present invention;

[0029] Figure 8 This is a structural block diagram of a model generation apparatus according to one embodiment of the present invention;

[0030] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] In 3D online games, when 3D artists create independent art assets for each body type, they often encounter situations where certain body parts of type A need to be retained and combined with certain parts of type B. Currently, the commonly used body type creation method is as follows: create a high-poly model that meets the requirements; use topology software to perform topology analysis to obtain a low-poly model; unpack the low-poly model's UVs (texture map coordinates) and bake them using baking software to obtain normal maps; create remaining texture assets for the model (color maps, metallic maps, roughness maps, subsurface reflection maps, etc.).

[0034] The combination scheme for assets of different body types is as follows: Use ZBrush software to modify the position and size of the high-poly models of the parts or the whole to be merged, so that the positions of the parts to be merged match each other; use the drag tool of ZBrush software to drag and bring the two parts to be merged closer together; use the projection tool of ZBrush software to project, or manually select key points for point-to-point projection; manually fix projection errors until the projection effect meets the requirements.

[0035] However, using the above method, creating low-poly models, UV mapping, and textures for different body types is labor-intensive and generates a large number of redundant textures, increasing the game's file size and thus increasing performance overhead. Furthermore, when the differences between two body types are small, the above combination method can be used to quickly blend parts of the two body types; for example, combining A's body with B's face. However, when the differences between the two body types are large, this combination method becomes difficult, requiring matching the positions of different parts and then repeatedly manually matching and projecting, resulting in a significant workload.

[0036] To address the aforementioned issues, this invention provides an efficient solution for creating, integrating, and reusing game notification resources. This solution can automatically combine assets of different sizes and reduce the burden on the game package.

[0037] According to one embodiment of the present invention, an embodiment of a model generation method is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0038] This method embodiment can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, the mobile terminal can be a smartphone (such as an Android phone, iOS phone, etc.), tablet computer, PDA, mobile Internet Device (MID), PAD, game console, and other terminal devices. Figure 1 This is a hardware structure block diagram of a computer terminal for a model generation method according to an embodiment of the present invention. For example... Figure 1 As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a central processing unit (CPU), graphics processing unit (GPU), digital signal processing (DSP) chip, microprocessor (MCU), programmable logic device (FPGA), neural network processor (NPU), tensor processor (TPU), artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data are also shown. Optionally, the computer terminal may further include a transmission device 106 for communication functions, an input / output device 108, and a display device 110. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0039] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the model generation method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby realizing the aforementioned model generation method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0040] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a routing device. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via the routing device to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0041] The inputs in input / output device 108 can come from multiple human interface devices (HIDs). Examples include keyboards and mice, gamepads, and other dedicated game controllers (such as steering wheels, fishing rods, dance mats, and remote controls). Some HIDs, in addition to providing input functions, can also provide output functions, such as force feedback and vibration from gamepads, and audio output from controllers.

[0042] Display device 110 may be, for example, a head-up display (HUD), a touchscreen liquid crystal display (LCD), or a touch display (also referred to as a "touchscreen" or "touch display"). The LCD allows a user to interact with the user interface of the computer terminal. In some embodiments, the computer terminal has a graphical user interface (GUI), through which the user can interact with the GUI using a device such as a mouse. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, a call interface, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0043] In one embodiment of this disclosure, the model generation method can run on a local terminal device or a server. When the model generation method runs on a server, it can be implemented and executed based on a cloud interaction system, which includes a server and client devices.

[0044] In an optional implementation, various cloud applications can run under the cloud interaction system. In the cloud application operation mode, the application's main running entity and the main entity presenting the operation screen are separated. The storage and execution of the model generation method are completed on the cloud application server. The client device is used for data reception, transmission, and operation screen presentation. For example, the client device can be a display device with data transmission capabilities located close to the user, such as a mobile terminal, television, computer, or PDA; however, information processing is performed by the cloud application server in the cloud. During model generation, the player operates the client device to send operation commands to the cloud application server. The cloud application server runs the game according to the operation commands, encodes and compresses the operation screen and other data, returns it to the client device via the network, and finally, the client device decodes and outputs the game screen.

[0045] In an alternative implementation, the local terminal device stores an application and is used to present an operation screen. The local terminal device is used to interact with the player through a graphical user interface (GUI), i.e., conventionally by downloading, installing, and running the application via an electronic device. The local terminal device can provide the GUI to the player in various ways, such as rendering it on the terminal's display screen or providing it to the player via holographic projection. For example, the local terminal device may include a display screen for presenting the GUI, which includes an operation screen, and a processor for running the application, generating the GUI, and controlling the display of the GUI on the display screen.

[0046] In one possible implementation, this invention provides a model generation method that provides a graphical user interface through a terminal device, wherein the terminal device may be the aforementioned local terminal device or a client device in the aforementioned cloud interaction system. Figure 2 This is a flowchart of a model generation method according to one embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0047] Step S202: Obtain multiple initial models, including a first model and a second model. The first model and the second model are models of different sizes, and the topology and texture coordinates of the multiple initial models are the same.

[0048] Multiple initial models can be various body types created by 3D artists using standard body models, including different heights, weights, genders, and even alien shapes. The specific creation process can utilize body type creation solutions provided in related technologies; this invention does not impose specific limitations on this. Since different models can be generated through fusion, to save on model creation costs, the multiple initial models can have significantly different body types, for example... Figure 3 As shown, taking the male body type as an example, five body types were created from left to right: normal (male), obese (male), alien 1 (male), child (male), and alien 2 (male). However, this is not the only possible model; more can be generated based on the specific project requirements. Furthermore, to avoid significant differences in the size and position of the same body parts across different body types, Zwrap can be used to unify the topology of different body types with that of the standard body model (e.g., ...). Figure 4a (as shown) and UV (as shown) Figure 4b (As shown) Same.

[0049] The first and second models in the above steps can be models that the 3D artist needs to merge partially or fully. Certain body parts of the first model are preserved and then merged with certain body parts of the second model. For example... Figure 5a As shown, the first model can be normal (male), and the second model can be a child (male); as Figure 5b As shown, the first model can be normal (male), and the second model can be obese (male); as Figure 5c As shown, the first model can be normal (male), and the second model can be alien 1 (male); as Figure 5d As shown, the first model can be normal (male), and the second model can be Alien 2 (male); as Figure 5e As shown, the first model can be normal (male), and the second model can be a child (male).

[0050] In one alternative embodiment, to improve the flexibility of model fusion, the model generation algorithm can be divided into different modules according to different functions, with each model acting as a node in the application, for example, such as... Figure 6 As shown, the model generation method provided in this embodiment of the invention can be divided into the following nodes: LoadGeom node (e.g., Figure 6 The LoadGeom01, LoadGeom02, LoadGeom03, LoadGeom04, and LoadGeom05 shown, and the Loadimage node (e.g.) Figure 6 The Loadimage01 and SelectPolygons nodes shown are as follows: Figure 6 The selectedPolygons01, SelectPolygons02, SelectPolygons03, SelectPolygons04, and SelectPolygons05 shown, and the Replace node (e.g.) Figure 6 The Replace01, Replace02, Replace03, and Replace04 shown), and the Blendshapes node (as shown) Figure 6 The diagram shows Blendshapes01, Blendshapes02, Blendshapes03, Blendshapes04, Blendshapes05, Blendshapes06, and Blendshapes07, and Subset nodes (such as...). Figure 6 Subset01 and Subset02 shown), Transform node (as shown) Figure 6 The Transform01 and ApplySubse nodes shown are shown in the image. Figure 6 The ApplySubse01 and ApplySubse02 shown), and the RepairGeom node (as shown) Figure 6 The RepairGeom01 and RemoveSpikes nodes shown are as follows: Figure 6 The example shows various nodes such as RemoveSpikes01. 3D artists can connect nodes with different functions according to the actual project requirements to achieve the goal of blending different body parts of different models, for example... Figure 6 As shown, textures can be imported through the Loadimage01 node, and imported through the five nodes LoadGeom01, LoadGeom02, LoadGeom03, LoadGeom04, and LoadGeom05 respectively. Figure 3 The five body types shown are designed to achieve the following: Figures 5a to 5eThe model fusion shown shows that LoadGeom01 can import normal (male) models.

[0051] Step S204: Determine the target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model.

[0052] The target blending degree in the above steps can be the degree of blending between the first model and the second model specified by the 3D artist. Specifically, it can be the blending degree required during the execution of the Blendshapes node.

[0053] In one alternative embodiment, a 3D artist may be provided with a... Figure 7 As shown in the interface, 3D artists can adjust the slider to set the target blending degree. The display box on the left side of the slider shows the specific value of the target blending degree corresponding to the current position of the slider.

[0054] Step S206: Based on the target fusion degree, the first model and the second model are fused to generate the target model.

[0055] It should be noted that the fusion here can be local or global, and can be determined according to the model fusion requirements in this embodiment of the invention. In an optional embodiment, regardless of the fusion method used, the degree of fusion between the two models needs to be controlled by a target fusion degree to ensure that the fusion of models of different body types is more coordinated, achieving the same effect as the combination scheme of different body type assets provided by related technologies. For example, Figures 5a to 5e The leftmost model is the target model.

[0056] To achieve differentiated and local fusion of the target model and thus customize the target model, in this embodiment of the invention, the first model and the second model can be fused to generate the target model in the following manner: determining the fusion requirements of the first model, wherein the fusion requirements are used to characterize the fusion parts of the first model that are fused with the second model, and the fusion parts include one of the following: all parts or local parts; fusion of the first model and the second model based on the fusion requirements and the target fusion degree to generate the target model.

[0057] The fusion requirement in the above steps can be a fusion method determined according to the model fusion needs. Different fusion methods fuse different parts of the model. For example, for the local fusion method, the fusion part can be a certain part of the model, and for the global fusion method, the fusion part can be the entire model.

[0058] In one alternative embodiment, the 3D artist can determine the blending requirements based on the actual project needs, and different nodes can be used to process the model for different blending requirements. Responding to the requirement that the blending area is all areas, i.e., for a global blending requirement, the Blendshapes node can be used to blend and deform the first and second models. The specific implementation process is as follows: Based on the target blending degree, the first and second models are deformed respectively to obtain a first deformed model and a second deformed model. Further, the first deformed model and the second deformed model are linearly combined to generate the target model.

[0059] Based on the implementation principle of Blendshapes nodes, the first and second deformed models can be generated as follows: Determine the first deformability of the first model and the second deformability of the second model based on the target fusion degree; deform the first model based on the first deformability to obtain the first deformed model; deform the second model based on the second deformability to obtain the second deformed model. Assuming the target fusion degree is 'a', then the first deformability is 1-a, the second deformability is 'a', and after fusing the first model A and the second model B, the generated target model C = (1-a)*A + a*B. For example, as... Figure 5a and Figure 7 As shown, 40% of a normal (male) sample can be combined with 60% of a child (male) sample.

[0060] In response to the fact that the fusion part is a local part, that is, for local fusion requirements, various node combinations such as SelectPolygons, Replac, and Blendshapes can be used to fuse and deform the first model and the second model. The specific implementation process is as follows: In response to the target operation applied to the first model, the first part corresponding to the target operation in the first model is determined; the first part in the first model is replaced with the second part in the second model to obtain the fused model, where the second part and the first part are the same part; the first model and the fused model are deformed based on the target fusion degree to obtain the first deformed model and the deformed fused model; the first deformed model and the deformed fused model are linearly combined to generate the target model.

[0061] The SelectPolygons node is used to manually select the area to be matched. 3D artists can select the part of the first model that needs to be replaced (i.e., the "first part" mentioned above) by performing target operations on the first model. This target operation can be a drag operation on the first model, which allows the artist to select the area containing the part to be replaced, thus defining the replacement area. Alternatively, the target operation can be other methods, such as clicking on the first model to directly select the part to be replaced. The remaining unselected parts of the first model need to be retained; therefore, these parts can be frozen to prevent blending and deformation. Figure 6 As shown, 3D artists can use the SelectPolygons node to select certain parts of the model input to the node, thereby determining the parts of the model that need to be replaced. In other words, the output of the SelectPolygons node is the selected parts of the first model. For example, as... Figure 5b As shown, when it's necessary to blend the limbs and height of a normal (male) figure with the belly of an obese (male) figure, the 3D artist can use the SelectPolygons node to select the normal (male) belly, as shown below. Figure 5b As shown in the box; Figure 5c As shown, when blending the height and build of the normal (male) creature with the arms of Alien 1 (male), the 3D artist can use the SelectPolygons node to select the two arms of the normal (male) creature, as shown below. Figure 5c As shown in the two boxes; Figure 5d As shown, when blending the normal (male) torso and height with the head of Alien 2 (male), the 3D artist can use the SelectPolygons node to select the normal (male) head, as shown below. Figure 5d As shown in the box; Figure 5e As shown, when blending a normal (male) torso and height with a child's (male) head, the 3D artist can use the SelectPolygons node to select the normal (male) head, as shown below. Figure 5e As shown in the box.

[0062] The Replace node is used to replace the selected region in the first model with the same region in the second model, achieving the purpose of local part fusion. For example... Figure 6 As shown, 3D artists can determine the specific area to be replaced through the third input of the Replace node, and replace the corresponding part of the model input from the first input with the same part of the model input from the second input. The output of the Replace node is a blended model. For example, as... Figure 5bAs shown, when it is necessary to blend the height of a normal (male) limbs and overall body shape with the belly of an obese (male), the 3D artist can use the Replace node to replace the normal (male) belly with the obese (male) belly, obtaining a preliminary blended model (i.e., the blended model); for example... Figure 5c As shown, when blending the height and build of the normal (male) character with the arm of Alien 1 (male), the 3D artist can use the Replace node to replace the normal (male) arm with the arm of Alien 1 (male) to obtain the preliminary blended model (i.e., the blended model); as... Figure 5d As shown, when blending the normal (male) torso and height with the head of Alien 2 (male), the 3D artist can use the Replace node to replace the normal (male) head with the head of Alien 2 (male) to obtain the preliminary blended model (i.e., the blended model); as... Figure 5e As shown, when blending the normal (male) body and height with the child (male) head, the 3D artist can use the Replace node to replace the normal (male) head with the child's (male) head to obtain the preliminary blended model (i.e., the blended model).

[0063] Because of the differences between models of different body shapes, directly replacing local parts may lead to inconsistencies in the fused model. Therefore, it is necessary to use the Blendshapes node to deform and fuse the first model and the fused model. That is, based on the target fusion degree, the first part of the first model and the first part of the fused model are deformed and fused to obtain the final target model. It should be noted that the implementation process of the Blendshapes node here is the same as that described above, and will not be repeated here. For example, as... Figure 5b As shown, when it is necessary to blend the height of the limbs and overall body shape of a normal (male) person with the belly of an obese (male) person, after replacing the belly of the normal (male) person with the belly of the obese (male) person using the Replace node to obtain the preliminary blended model (i.e., the blended model), the blending degree can be further modified using the Blendshapes node, so that the belly of the target model is different from both the belly of the normal (male) person and the belly of the obese (male) person, thus truly achieving the blending effect; for example... Figure 5c As shown, when fusing the height and weight of the normal (male) model with the arm of the alien 1 (male) model, after replacing the normal (male) arm with the alien 1 (male) model's arm using the Replace node to obtain the initial fused model (i.e., the fused model), the degree of fusion can be further modified using the Blendshapes node, so that the target model's arm is different from both the normal (male) and obese (male) arms, truly achieving the fusion effect.

[0064] Furthermore, since the differences between models of different body shapes vary, the smaller the difference, the simpler the model fusion; the larger the difference, the more complex the model fusion. To ensure the fusion effect after model fusion, the model difference between the first and second models is determined during the deformation process. The model difference is used to characterize the degree of difference between the first and second models. In response to a model difference less than or equal to a preset difference, the first model and the fused model are deformed based on the target fusion degree, resulting in a first deformed model and a deformed fused model. The preset difference here can be the maximum difference threshold representing the smallest difference between the two models. It can be set manually by the 3D artist or determined through experiments with different models; this invention does not specifically limit this. For example, as... Figure 5b and 5c As shown, for local fusion with small size differences, various node combinations such as SelectPolygons, Replac, Blendshapes, and Transform can be used to form an automated solution for combining local sizes with small differences. That is, the fusion degree can be directly modified through the Blendshapes node to obtain the target model.

[0065] Furthermore, in response to a model difference greater than a preset difference, for models with large differences, in order to avoid large stretching caused by direct part replacement, after generating a fusion model, the fusion model can be further repaired in the following way: the first part of the fusion model is repaired to obtain a first repaired model; based on the target fusion degree, the first model and the first repaired model are deformed respectively to obtain a first deformed model and a deformed fusion model.

[0066] Optionally, a combination of nodes such as SelectPolygons, Replace, Subset, Transform, ApplySubse, Blendshapes, RepairGeom, and RemoveSpikes can be used to form an automated solution for combining significantly different body shapes. The specific repair process of the fused model is as follows: the first part of the fused model is cut to obtain a first cut model; the position of the first cut model is adjusted to obtain a first adjusted model; based on the first model, the first part of the first adjusted model is restored to obtain a first repaired model.

[0067] Subset nodes are used to segment the model, thereby ensuring differentiated body shapes. For example... Figure 6As shown, 3D artists can determine the specific area to be cut through the second input of the Subset node, and then cut the corresponding part of the model input from the first input. The output of the Subset node is the first cut model. For example, as... Figure 5d As shown, when the normal (male) torso and height are merged with the head of Alien 2 (male), after replacing the normal (male) head with the head of Alien 2 (male) using the Replace node to obtain the initial merged model (i.e., the merged model), the 3D artist can use the Subset node to cut the model to obtain the cut model (i.e., the first cut model); as... Figure 5e As shown, when the normal (male) body and height are blended with the child (male) head, after replacing the normal (male) head with the child's (male) head through the Replace node, the 3D artist can use the Subset node to cut the model and obtain the cut model (i.e., the first cut model).

[0068] The Transform node can be used in conjunction with the Subset node to modify the position of the cut model. For example... Figure 6 As shown, 3D artists can use the Transform node to change the deformation position of the input model to ensure that the differentiation blending achieves a better blending deformation effect. For example, as Figure 5d As shown, when the normal (male) torso and height are merged with the head of Alien 2 (male), after cutting the model using the Subset node to obtain the cut model (i.e., the first cut model), the model position can be further modified using the Transform node; for example... Figure 5e As shown, when the normal (male) body and height are merged with the child (male) head, after replacing the normal (male) head with the child's (male) head using the Replace node, and then cutting the model using the Subset node to obtain the cut model (i.e., the first cut model), the model position can be further modified using the Transform node.

[0069] The ApplySubse node is used to restore a cut model. As long as the topology remains consistent, this node will apply the cut and blended deformed model to another model with the same topology. For example... Figure 6 As shown, 3D artists can use the third input of the ApplySubse node to determine the specific area that needs repair, and then feed the model input from the second input onto the model input from the first input. For example, as... Figure 5dAs shown, when blending the torso and height of the normal (male) alien with the head of the alien 2 (male), after modifying the model position using the Transform node, the head of the modified model (i.e., the first adjusted model) can be given to the normal (male) alien using the ApplySubse node; as shown Figure 5e As shown, when the torso and height of a normal (male) child are merged with the head of a child (male), after modifying the model position through the Transform node, the head of the modified model (i.e., the first adjusted model) can be given to the normal (male) child through the ApplySubse node.

[0070] In the above scheme, due to the significant differences between the first model and the second model, the first part of the first repair model performs well, but other parts may have flaws, such as excessively sharp areas. In an optional embodiment, during the generation of the target model, the effect of the target model can be improved by manually selecting and repairing the parts to be repaired: The first deformed model and the deformed fusion model are linearly combined to generate the target deformed model; in response to the target operation applied to the target deformed model, the third part of the target deformed model is determined; the third part of the target deformed model is repaired to obtain the second repair model; the target parts in the second repair model that meet preset conditions are repaired to generate the target model. Here, the target parts that meet the preset conditions can be flawed parts, i.e., excessively sharp areas.

[0071] It should be noted that the Blendshapes node can be used to linearly combine the first deformable model and the deformable fusion model, the SelectPolygons node can be used to select the third part of the target deformable model, the Subset node and ApplySubse node can be used to repair the third part of the target deformable model, and the RepairGeom and RemoveSpikes nodes can be used to repair the target parts in the second repair model that meet the preset conditions. Specifically, the RepairGeom node stores the overly sharp parts in the second repair model, that is, it stores the target parts; the RemoveSpikes node processes the parts stored in the RepairGeom node.

[0072] Through the above embodiments of the present invention, by acquiring a first model and a second model, determining a target fusion degree, and then fusing the first model and the second model based on the target fusion degree to generate a target model, the purpose of automatically combining models of different body types is achieved. It is easy to note that since the topology and texture coordinates of the first model and the second model are the same, the positions of the same parts in models of different body types are the same, eliminating the need for 3D artists to perform additional dragging and projection. Furthermore, the first model and the second model can be automatically fused based on the target fusion degree, eliminating the need for manual model fusion by 3D artists. This achieves the technical effects of reducing model generation time, improving model generation efficiency, and reducing the wear and tear on production personnel caused by mechanized labor. Simultaneously, all resources share one or more sets of basic resources, reducing the size of basic resources in the game, thereby reducing the game package size, improving game quality and running speed, and thus solving the technical problem of low generation efficiency of models of different body types in related technologies.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0074] This embodiment also provides a model generation apparatus for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the terms "unit" and "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0075] Figure 8 This is a structural block diagram of a model generation apparatus according to one embodiment of the present invention, such as... Figure 8 As shown, the device includes:

[0076] The acquisition module 82 is used to acquire multiple initial models, including a first model and a second model. The first model and the second model are models of different sizes, and the topology and texture coordinates of the multiple initial models are the same.

[0077] Module 84 is used to determine the target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model;

[0078] The fusion module 86 is used to fuse the first model and the second model based on the target fusion degree to generate the target model.

[0079] In the above embodiments of the present invention, the fusion module includes: a determining unit, used to determine the fusion requirements of the first model, wherein the fusion requirements are used to characterize the fusion parts of the first model that are fused with the second model, and the fusion parts include one of the following: all parts or partial parts; and a fusion unit, used to fuse the first model and the second model based on the fusion requirements and the target fusion degree to generate a target model.

[0080] In the above embodiments of the present invention, the fusion unit is further configured to, in response to the fusion part being all parts, deform the first model and the second model respectively based on the target fusion degree to obtain the first deformed model and the second deformed model; and linearly combine the first deformed model and the second deformed model to generate the target model.

[0081] In the above embodiments of the present invention, the fusion unit is further configured to determine a first deformation degree of the first model and a second deformation degree of the second model based on the target fusion degree; deform the first model based on the first deformation degree to obtain a first deformed model; and deform the second model based on the second deformation degree to obtain a second deformed model.

[0082] In the above embodiments of the present invention, the fusion unit is further configured to, in response to the fusion part being a local part and in response to the target operation acting on the first model, determine a first part in the first model corresponding to the target operation; replace the first part in the first model with a second part in the second model to obtain a fusion model, wherein the second part and the first part are the same part; deform the first model and the fusion model based on the target fusion degree to obtain a first deformed model and a deformed fusion model; and linearly combine the first deformed model and the deformed fusion model to generate a target model.

[0083] In the above embodiments of the present invention, the fusion unit is further configured to determine the model difference degree between the first model and the second model, wherein the model difference degree is used to characterize the degree of difference between the first model and the second model; in response to the model difference degree being less than or equal to a preset difference degree, the first model and the fused model are deformed based on the target fusion degree to obtain a first deformed model and a deformed fused model.

[0084] In the above embodiments of the present invention, the fusion unit is further configured to, in response to the model difference degree being greater than a preset difference degree, repair the first part of the fusion model to obtain a first repaired model; and deform the first model and the first repaired model based on the target fusion degree to obtain a first deformed model and a deformed fusion model.

[0085] In the above embodiments of the present invention, the fusion unit is further configured to cut the first part of the fusion model to obtain a first cut model; adjust the position of the first cut model to obtain a first adjusted model; and restore the first part of the first adjusted model based on the first model to obtain a first repair model.

[0086] In the above embodiments of the present invention, the fusion unit is further configured to: linearly combine the first deformation model and the deformation fusion model to generate a target deformation model; respond to the target operation acting on the target deformation model to determine the third part of the target deformation model; repair the third part of the target deformation model to obtain a second repair model; and repair the target part in the second repair model that meets the preset conditions to generate the target model.

[0087] It should be noted that the above-mentioned units and modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but not limited to these: all the above-mentioned units and modules are located in the same processor; or, the above-mentioned units and modules are located in different processors in any combination.

[0088] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0089] Optionally, in this embodiment, the computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0090] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0091] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0092] Obtain multiple initial models, including a first model and a second model. The first model and the second model are models of different sizes, and the topology and texture coordinates of the multiple initial models are the same.

[0093] Determine the target fusion degree, which is used to characterize the degree of fusion between the first model and the second model;

[0094] The first model and the second model are fused based on the target fusion degree to generate the target model.

[0095] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining the fusion requirements of a first model, wherein the fusion requirements characterize the fusion parts in the first model that are fused with the second model, and the fusion parts include one of the following: all parts or partial parts; fusing the first model and the second model based on the fusion requirements and the target fusion degree to generate a target model.

[0096] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: in response to the fusion region being all regions, deforming the first model and the second model respectively based on the target fusion degree to obtain a first deformed model and a second deformed model; linearly combining the first deformed model and the second deformed model to generate a target model.

[0097] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining a first deformation degree of the first model and a second deformation degree of the second model based on the target fusion degree; deforming the first model based on the first deformation degree to obtain a first deformed model; and deforming the second model based on the second deformation degree to obtain a second deformed model.

[0098] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: in response to the fusion region being a local region, in response to a target operation acting on the first model, determining a first region in the first model corresponding to the target operation; replacing the first region in the first model with a second region in the second model to obtain a fusion model, wherein the second region and the first region are the same region; deforming the first model and the fusion model based on the target fusion degree to obtain a first deformed model and a deformed fusion model; and linearly combining the first deformed model and the deformed fusion model to generate a target model.

[0099] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: determining the model difference degree between the first model and the second model, wherein the model difference degree is used to characterize the degree of difference between the first model and the second model; in response to the model difference degree being less than or equal to a preset difference degree, deforming the first model and the fused model based on a target fusion degree to obtain a first deformed model and a deformed fused model.

[0100] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: in response to a model difference degree greater than a preset difference degree, repairing a first part of the fused model to obtain a first repaired model; deforming the first model and the first repaired model based on a target fusion degree to obtain a first deformed model and a deformed fused model.

[0101] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: cutting a first part of the fusion model to obtain a first cut model; adjusting the position of the first cut model; obtaining a first adjusted model; and restoring the first part of the first adjusted model based on the first model to obtain a first repair model.

[0102] Optionally, the aforementioned computer-readable storage medium is further configured to store program code for performing the following steps: linearly combining a first deformation model and a deformation fusion model to generate a target deformation model; determining a third part of the target deformation model in response to a target operation acting on the target deformation model; repairing the third part of the target deformation model to obtain a second repair model; and repairing the target parts in the second repair model that meet preset conditions to generate a target model.

[0103] This embodiment of the computer-readable storage medium provides a technical solution for automated model generation. It employs a method of acquiring a first model and a second model, determining a target fusion degree, and then fusing the first model and the second model based on the target fusion degree to generate a target model, thereby achieving the goal of automatically combining models of different body types. It is noteworthy that, since the topology and texture coordinates of the first and second models are identical, the positions of identical parts in models of different body types are the same, eliminating the need for 3D artists to perform additional dragging and casting. Furthermore, the first model and the second model can be automatically fused based on the target fusion degree, eliminating the need for manual model fusion by 3D artists. This achieves the technical effects of reducing model generation time, improving model generation efficiency, and reducing the wear and tear on production personnel from mechanized labor. Simultaneously, all resources share one or more sets of basic resources, reducing the size of basic resources in the game, thereby reducing the game package size, improving game quality and running speed, and thus solving the technical problem of low generation efficiency for models of different body types in related technologies.

[0104] 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 the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, portable 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 embodiments of the present invention.

[0105] In exemplary embodiments of this application, a computer-readable storage medium stores a program product capable of implementing the methods described above in this embodiment. In some possible implementations, various aspects of the embodiments of the present invention can also be implemented as a program product comprising program code, which, when run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this embodiment according to various exemplary embodiments of the present invention.

[0106] According to embodiments of the present invention, a program product for implementing the above-described method may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In the embodiments of the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0107] The aforementioned program product may take the form of any combination of one or more computer-readable media. Such computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (not exhaustive) of computer-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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0108] It should be noted that the program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0109] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0110] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0111] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0112] Obtain multiple initial models, including a first model and a second model. The first model and the second model are models of different sizes, and the topology and texture coordinates of the multiple initial models are the same.

[0113] Determine the target fusion degree, which is used to characterize the degree of fusion between the first model and the second model;

[0114] The first model and the second model are fused based on the target fusion degree to generate the target model.

[0115] Optionally, the processor may also be configured to perform the following steps via a computer program: determining the fusion requirements of the first model, wherein the fusion requirements are used to characterize the fusion parts in the first model that are fused with the second model, and the fusion parts include one of the following: all parts or partial parts; fusing the first model and the second model based on the fusion requirements and the target fusion degree to generate a target model.

[0116] Optionally, the processor may also be configured to perform the following steps via a computer program: in response to the fusion region being all regions, deforming the first model and the second model respectively based on the target fusion degree to obtain a first deformed model and a second deformed model; and linearly combining the first deformed model and the second deformed model to generate the target model.

[0117] Optionally, the processor may also be configured to perform the following steps via a computer program: determining a first deformation degree of the first model and a second deformation degree of the second model based on the target fusion degree; deforming the first model based on the first deformation degree to obtain a first deformed model; and deforming the second model based on the second deformation degree to obtain a second deformed model.

[0118] Optionally, the processor may also be configured to perform the following steps via a computer program: in response to the fusion region being a local region, in response to a target operation acting on the first model, determine a first region in the first model corresponding to the target operation; replace the first region in the first model with a second region in the second model to obtain a fusion model, wherein the second region and the first region are the same region; deform the first model and the fusion model based on the target fusion degree to obtain a first deformed model and a deformed fusion model; and linearly combine the first deformed model and the deformed fusion model to generate a target model.

[0119] Optionally, the processor may also be configured to perform the following steps via a computer program: determining the model difference degree between the first model and the second model, wherein the model difference degree is used to characterize the degree of difference between the first model and the second model; in response to the model difference degree being less than or equal to a preset difference degree, deforming the first model and the fused model based on a target fusion degree to obtain a first deformed model and a deformed fused model.

[0120] Optionally, the processor may also be configured to perform the following steps via a computer program: in response to a model difference degree greater than a preset difference degree, repairing a first part of the fused model to obtain a first repaired model; deforming the first model and the first repaired model based on a target fusion degree to obtain a first deformed model and a deformed fused model.

[0121] Optionally, the processor may also be configured to perform the following steps via a computer program: cutting a first part of the fusion model to obtain a first cut model; adjusting the position of the first cut model; obtaining a first adjusted model; and restoring the first part of the first adjusted model based on the first model to obtain a first repair model.

[0122] Optionally, the processor may also be configured to perform the following steps via a computer program: linearly combining the first deformation model and the deformation fusion model to generate a target deformation model; responding to a target operation applied to the target deformation model to determine a third part of the target deformation model; repairing the third part of the target deformation model to obtain a second repair model; and repairing the target parts in the second repair model that meet preset conditions to generate a target model.

[0123] In this embodiment of the electronic device, an automated model generation technical solution is provided. It employs a method of acquiring a first model and a second model, determining a target fusion degree, and then fusing the first model and the second model based on the target fusion degree to generate a target model, thereby achieving the purpose of automatically combining models of different body types. It is noteworthy that, since the topology and texture coordinates of the first and second models are identical, the positions of identical parts in models of different body types are the same, eliminating the need for 3D artists to perform additional dragging and projection. Furthermore, the first model and the second model can be automatically fused based on the target fusion degree, eliminating the need for manual model fusion by 3D artists. This achieves the technical effects of reducing model generation time, improving model generation efficiency, and reducing the wear and tear on production personnel from mechanized labor. Simultaneously, all resources share one or more sets of basic resources, reducing the size of basic resources in the game, thereby achieving the technical effects of reducing the game package size, improving game quality and running speed, and thus solving the technical problem of low generation efficiency for models of different body types in related technologies.

[0124] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Figure 9 As shown, the electronic device 900 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0125] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processor 910, at least one memory 920, a bus 930 connecting different system components (including memory 920 and processor 910), and a display 940.

[0126] The memory 920 stores program code that can be executed by the processor 910, causing the processor 910 to perform the steps described in the method section of the embodiments of this application according to various exemplary implementations of the present invention.

[0127] The memory 920 may include a readable medium in the form of volatile memory cells, such as random access memory (RAM) 9201 and / or cache memory 9202, and may further include read-only memory (ROM) 9203, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0128] In some instances, memory 920 may also include a program / utility 9204 having a set (at least one) of program modules 9205, including but not limited to: an 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. Memory 920 may further include memory remotely located relative to processor 910, which can be connected to electronic device 900 via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0129] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, peripheral bus, graphics acceleration port, processor 910, or a local bus using any of the various bus structures.

[0130] The display 940 may be, for example, a touchscreen liquid crystal display (LCD) that allows a user to interact with the user interface of the electronic device 900.

[0131] Optionally, the electronic device 900 can also communicate with one or more external devices 1000 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 900, and / or any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via the input / output (I / O) interface 950. Furthermore, the electronic device 900 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 the network adapter 960. Figure 9 As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although... Figure 9 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0132] The aforementioned electronic device 900 may also include: a keyboard, a cursor control device (such as a mouse), an input / output interface (I / O interface), a network interface, a power supply, and / or a camera.

[0133] Those skilled in the art will understand that Figure 9 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, the electronic device 900 may also include components that are more... Figure 9 The more or fewer components shown, or having the same Figure 1 Different configurations are shown. The memory 920 can be used to store computer programs and corresponding data, such as the computer program and corresponding data for model generation in this embodiment. The processor 910 executes various functional applications and data processing by running the computer program stored in the memory 920, thereby implementing the aforementioned model generation method.

[0134] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0135] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0136] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0137] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0139] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A model generation method, characterized in that, include: Multiple initial models are obtained, including a first model and a second model, wherein the first model and the second model are models of different sizes, and the multiple initial models have the same topology and texture coordinates; Determine the target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model; Based on the target fusion degree, the first model and the second model are fused to generate the target model; The process of fusing the first model and the second model based on the target fusion degree to generate a target model includes: In response to the fact that the fusion part of the first model and the second model is a local fusion, and a target operation acting on the first model is detected, a first part corresponding to the target operation in the first model is determined; the first part in the first model is replaced with a second part in the second model to obtain a fusion model, wherein the second part and the first part are the same part; the first model and the fusion model are deformed based on the target fusion degree to obtain a first deformed model and a deformed fusion model; the first deformed model and the deformed fusion model are linearly combined to generate the target model.

2. The method according to claim 1, characterized in that, Based on the target fusion degree, the first model and the second model are fused to generate the target model, including: Determine the fusion requirements of the first model, wherein the fusion requirements are used to characterize the fusion parts of the first model that are fused with the second model; Based on the fusion requirements and the target fusion degree, the first model and the second model are fused to generate the target model.

3. The method according to claim 2, characterized in that, Based on the fusion requirements and the target fusion degree, the first model and the second model are fused to generate the target model, including: In response to the fact that the fusion region is all regions, the first model and the second model are deformed based on the target fusion degree to obtain a first deformed model and a second deformed model; The first deformation model and the second deformation model are linearly combined to generate the target model.

4. The method according to claim 3, characterized in that, Based on the target fusion degree, the first model and the second model are deformed respectively to obtain the first deformed model and the second deformed model, including: Based on the target fusion degree, the first deformation degree of the first model and the second deformation degree of the second model are determined; The first model is deformed based on the first degree of deformation to obtain the first deformed model; The second model is deformed based on the second deformation degree to obtain the second deformed model.

5. The method according to claim 1, characterized in that, Based on the target fusion degree, the first model and the fusion model are deformed to obtain the first deformed model and the deformed fusion model, respectively, including: Determine the model difference degree between the first model and the second model, wherein the model difference degree is used to characterize the degree of difference between the first model and the second model; In response to the model difference degree being less than or equal to a preset difference degree, the first model and the fused model are deformed based on the target fusion degree to obtain the first deformed model and the deformed fused model.

6. The method according to claim 5, characterized in that, In response to the model difference degree being greater than the preset difference degree, the first model and the fused model are deformed based on the target fusion degree to obtain the first deformed model and the deformed fused model, which further includes: The first part of the fusion model is repaired to obtain a first repaired model; Based on the target fusion degree, the first model and the first repair model are deformed to obtain the first deformed model and the deformed fusion model.

7. The method according to claim 6, characterized in that, Repairing the first part of the fusion model to obtain the first repaired model includes: The first part of the fusion model is cut to obtain a first cut model; The position of the first cutting model is adjusted to obtain the first adjusted model; The first part of the first adjustment model is restored based on the first model to obtain the first repair model.

8. The method according to claim 5, characterized in that, The target model is generated by linearly combining the first deformation model and the deformation fusion model. The first deformation model and the deformation fusion model are linearly combined to generate the target deformation model; In response to a target operation applied to the target deformable model, a third part of the target deformable model is determined; The third part of the target deformed model is repaired to obtain a second repaired model; The target parts that meet the preset conditions in the second repair model are repaired to generate the target model.

9. A model generation device, characterized in that, include: The acquisition module is used to acquire multiple initial models, including: a first model and a second model, wherein the first model and the second model are models of different sizes, and the multiple initial models have the same topology and texture coordinates; A determination module is used to determine the target fusion degree, wherein the target fusion degree is used to characterize the degree of fusion between the first model and the second model; The fusion module is used to fuse the first model and the second model based on the target fusion degree to generate a target model; The fusion module is further configured to: respond to the fact that the fusion part of the first model and the second model is a local fusion, and a target operation acting on the first model is detected, determine a first part corresponding to the target operation in the first model; replace the first part in the first model with a second part in the second model to obtain a fusion model, wherein the second part and the first part are the same part; deform the first model and the fusion model based on the target fusion degree to obtain a first deformed model and a deformed fusion model; and linearly combine the first deformed model and the deformed fusion model to generate the target model.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the model generation method according to any one of claims 1 to 8 when run by a processor.

11. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the model generation method according to any one of claims 1 to 8.

Images