Model rendering method and apparatus, computer device, and storage medium

Abstract

The present disclosure provides a model rendering method and device, computer equipment and a storage medium, wherein the method comprises: obtaining a three-dimensional model of a target face, and obtaining target rendering information corresponding to the three-dimensional model; the three-dimensional model comprises a plurality of vertices; the target rendering information is used to represent the display light intensity of each target vertex in the subsurface scattering range corresponding to the three-dimensional model; based on the target rendering information and a color tendency diagram of subsurface scattering, the color tendency corresponding to each target vertex is determined; the color tendency diagram is used to describe the mapping relationship between different display light intensities and color tendencies; based on the color tendency corresponding to each target vertex, the three-dimensional model is rendered to obtain a target rendering model of the three-dimensional model.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a model rendering method, apparatus, computer device, and storage medium. Background Technology

[0002] Subsurface scattering (3S) refers to the process by which light enters an object from its surface, is scattered internally, and then exits through other vertices on the object's surface. It is used to describe the lighting phenomenon of light scattering when passing through a transparent / semi-transparent surface, and can be specifically represented by the light and shadow effects on human skin under illumination in the real world.

[0003] When rendering the faces of hyper-realistic characters and other objects, displaying the subsurface scattering phenomenon under light can make the rendered lighting effects more realistic. However, subsurface scattering specifically involves the scattering of light after it enters the medium, and general computer equipment cannot provide the computing power to support this, resulting in the current problem of poor realism in the lighting effects of rendering two-dimensional objects. Summary of the Invention

[0004] This disclosure provides at least one model rendering method, apparatus, computer device, and storage medium.

[0005] In a first aspect, embodiments of this disclosure provide a model rendering method, comprising: acquiring a three-dimensional model of a target face, and acquiring target rendering information corresponding to the three-dimensional model; the three-dimensional model includes multiple vertices; the target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the three-dimensional model; based on the target rendering information and the color tendency map of the subsurface scattering, determining the color tendency corresponding to each of the target vertices; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies; and rendering the three-dimensional model based on the color tendency corresponding to each of the target vertices to obtain a target rendering model of the three-dimensional model.

[0006] In this way, by using the color tendency map of subsurface scattering to determine the color tendency of each target vertex in the subsurface scattering region, and using the color tendency to render the 3D model, the rendered target model can have a good subsurface scattering effect without simulating the scattering effect of light on the skin medium. Therefore, it requires less computing power and is suitable for general computer equipment. As a result, it is relatively easy to add subsurface scattering effects to hyper-realistic characters and other objects, making the lighting and shadow effects of the hyper-realistic characters and other objects closer to the real effect.

[0007] In one optional implementation, obtaining the target rendering information corresponding to the three-dimensional model includes: determining an initial thickness map for characterizing the thickness information of the target face and an initial curvature map for characterizing the curvature information of the target face based on the three-dimensional model; and determining the target rendering information based on the initial thickness map and the initial curvature map.

[0008] In this way, the initial thickness map and initial curvature map corresponding to the target face can be determined in advance, and the target rendering information used to characterize the subsurface scattering range of the target face can be determined based on the initial thickness map and the initial curvature map. Thus, the target rendering information calculated in advance can be used directly when subsurface scattering rendering is required, without the need to calculate the thickness and curvature information in real time, thereby improving the efficiency of subsurface scattering rendering of the terminal device.

[0009] In one optional implementation, determining the color tendency corresponding to each of the target vertices based on the target rendering information and the subsurface scattering color tendency map includes: for any target vertex, determining the target pixel corresponding to the target vertex from the color tendency map based on the display light intensity corresponding to the target vertex and the mapping relationship between different display light intensities and color tendencies described by the color tendency map; and determining the color tendency indicated by the target pixel as the color tendency corresponding to the target vertex.

[0010] In this way, the color tendency map can be used to determine the color tendency of the target vertex under the subsurface scattering effect, thereby determining the rendering color when rendering the subsurface scattering effect. This allows the rendered face to have the subsurface scattering effect under illumination without the need for complex calculations of the physical propagation of light in the skin medium through the pipeline. This improves the realism of the face while reducing the computational power of subsurface scattering effect processing.

[0011] In one optional implementation, rendering the 3D model based on the color tendency corresponding to each of the target vertices to obtain the target rendering model of the 3D model includes: for any target vertex, adjusting the base color of the target vertex based on the color tendency corresponding to the target vertex to obtain the rendering color of the target vertex; and rendering the 3D model based on the rendering colors corresponding to each of the target vertices to obtain the target rendering model of the 3D model.

[0012] In this way, by adjusting the base color through color bias, the basic display effect of the base color on human skin tone and lighting color can be preserved, while reflecting the light and shadow effects presented under the subsurface scattering effect.

[0013] In one optional implementation, the color tendency includes: adjusting the reference color by a ratio under a display light intensity corresponding to the color tendency; and adjusting the reference color of any target vertex based on the color tendency corresponding to the target vertex to obtain the rendered color of the target vertex includes: adjusting the pixel value of the reference color corresponding to the target vertex based on the adjustment ratio to obtain the rendered color of the target vertex.

[0014] In one optional implementation, the reference color corresponding to any vertex is determined by: obtaining the illumination color corresponding to the target light source illuminating the 3D model and obtaining the color map corresponding to the 3D model; determining the initial color corresponding to each vertex in the 3D model based on the color map; and superimposing the initial color corresponding to each vertex and the illumination color to obtain the reference color corresponding to each vertex.

[0015] In this way, when rendering the target vertex of the subsurface scattering region, the base color for the facial color can be taken into account, including the lighting color and skin color. For non-target vertices, the base color can also be used to present the light and shadow information of the skin color under the influence of lighting in areas of the 3D model that do not present the subsurface scattering effect.

[0016] In one optional implementation, the method further includes generating the initial thickness map and the initial curvature map according to the following steps: obtaining the minimum occlusion distance and the maximum occlusion distance corresponding to the three-dimensional model; generating the initial thickness map corresponding to the three-dimensional model based on the minimum occlusion distance, the maximum occlusion distance and the three-dimensional model; and obtaining the sampling radius corresponding to the three-dimensional model; generating the initial curvature map corresponding to the three-dimensional model based on the sampling radius and the three-dimensional model.

[0017] Thus, by obtaining the minimum and maximum occlusion distances corresponding to the 3D model, an initial thickness map can be generated based on these distances, facilitating the subsequent generation of target rendering information based on the generated initial thickness map. Similarly, by obtaining the sampling radius, an initial curvature map can be generated based on this radius, further facilitating the subsequent generation of target rendering information based on the generated initial curvature map.

[0018] Secondly, embodiments of this disclosure also provide a model rendering apparatus, comprising: an acquisition module, configured to acquire a three-dimensional model of a target face and acquire target rendering information corresponding to the three-dimensional model; the three-dimensional model includes multiple vertices; the target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the three-dimensional model; a determination module, configured to determine the color tendency corresponding to each of the target vertices based on the target rendering information and a color tendency map of the subsurface scattering; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies; and a rendering module, configured to render the three-dimensional model based on the color tendency corresponding to each of the target vertices to obtain a target rendering model of the three-dimensional model.

[0019] In one optional implementation, when acquiring target rendering information corresponding to the 3D model, the acquisition module is configured to: determine an initial thickness map for characterizing the thickness information of the target face and an initial curvature map for characterizing the curvature information of the target face based on the 3D model; and determine the target rendering information based on the initial thickness map and the initial curvature map.

[0020] In one optional implementation, when the determining module determines the color tendency corresponding to each of the target vertices based on the target rendering information and the subsurface scattering color tendency map, it is configured to: for any target vertex, based on the display light intensity corresponding to the target vertex and the mapping relationship between different display light intensities and color tendencies described in the color tendency map, determine the target pixel corresponding to the target vertex from the color tendency map; and determine the color tendency indicated by the target pixel as the color tendency corresponding to the target vertex.

[0021] In one optional implementation, when the rendering module renders the 3D model based on the color tendency corresponding to each of the target vertices to obtain the target rendering model of the 3D model, it is configured to: for any target vertex, adjust the base color of the target vertex based on the color tendency corresponding to the target vertex to obtain the rendering color of the target vertex; and render the 3D model based on the rendering colors corresponding to each of the target vertices to obtain the target rendering model of the 3D model.

[0022] In one optional implementation, the color tendency includes: an adjustment ratio of the reference color under a display light intensity corresponding to the color tendency; when the rendering module adjusts the reference color of any target vertex based on the color tendency corresponding to the target vertex to obtain the rendered color of the target vertex, it is used to: adjust the pixel value of the reference color corresponding to the target vertex based on the adjustment ratio to obtain the rendered color of the target vertex.

[0023] In one optional implementation, the reference color corresponding to any vertex is determined by: obtaining the illumination color corresponding to the target light source illuminating the 3D model and obtaining the color map corresponding to the 3D model; determining the initial color corresponding to each vertex in the 3D model based on the color map; and superimposing the initial color corresponding to each vertex and the illumination color to obtain the reference color corresponding to each vertex.

[0024] In an optional implementation, the acquisition module is further configured to generate the initial thickness map and the initial curvature map according to the following steps: acquiring the minimum occlusion distance and the maximum occlusion distance corresponding to the 3D model; generating the initial thickness map corresponding to the 3D model based on the minimum occlusion distance, the maximum occlusion distance and the 3D model; and acquiring the sampling radius corresponding to the 3D model; generating the initial curvature map corresponding to the 3D model based on the sampling radius and the 3D model.

[0025] Thirdly, an optional implementation of this disclosure also provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the steps of the first aspect above, or any possible implementation of the first aspect, are performed.

[0026] Fourthly, an optional implementation of this disclosure also provides a computer-readable storage medium storing a computer program that, when run, performs the steps of the first aspect or any possible implementation of the first aspect.

[0027] For a description of the effects of the above-mentioned model rendering device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned model rendering method, which will not be repeated here.

[0028] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0030] Figure 1 A flowchart of a model rendering method provided by an embodiment of this disclosure is shown;

[0031] Figure 2 A schematic diagram of a three-dimensional model of a target human face provided in an embodiment of this disclosure is shown;

[0032] Figure 3a This diagram illustrates the initial thickness texture in the model rendering method provided in this embodiment of the present disclosure.

[0033] Figure 3b This diagram illustrates the initial curvature map in the model rendering method provided in this embodiment of the present disclosure.

[0034] Figure 3c This illustrates the initial thickness texture after color inversion processing in the model rendering method provided in this embodiment of the disclosure;

[0035] Figure 3d A schematic diagram of the target thickness texture in the model rendering method provided in this embodiment of the disclosure is shown;

[0036] Figure 3e A schematic diagram of the target curvature map is shown in the model rendering method provided in the embodiments of this disclosure;

[0037] Figure 3f This diagram illustrates the target texture obtained after overlay processing in the model rendering method provided in this embodiment of the present disclosure.

[0038] Figure 4 A schematic diagram of a color tendency map provided in an embodiment of this disclosure is shown;

[0039] Figure 5 A schematic diagram of a model rendering apparatus provided in an embodiment of this disclosure is shown;

[0040] Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0042] Research has revealed that subsurface scattering can be manifested in the lighting effects on human skin under illumination in the real world, similar to the faint glow of light reflected from a lit candle near the flame due to diffuse reflection. Applying this real-world subsurface scattering effect to the rendering of hyper-realistic characters and other objects could enhance the realism of their lighting. However, due to the complexity of the physics behind subsurface scattering, rendering equipment requires real-time ray tracing and simulation of light scattering by the object's surface medium. Typical computers lack the computational power to support this, making it impossible to add subsurface scattering effects to hyper-realistic characters and similar objects, resulting in the current issue of poor realism in their rendering.

[0043] Based on the above research, this disclosure provides a model rendering method. For a 3D model of a target face, by obtaining the target rendering information corresponding to the 3D model, the display light intensity of each target vertex within the subsurface scattering range of the 3D model can be determined. Considering that the display light intensity varies at different positions of the face under the subsurface scattering effect in real-world scenes, the resulting color tendencies also differ. Therefore, by using the color tendency map under the subsurface scattering effect to determine the color tendency of the target vertex under the corresponding display light intensity, the rendered target model can be made closer to the lighting and shadow effects of subsurface scattering in real-world scenes. Since this method can achieve good subsurface scattering effects without simulating the scattering effect of light by the skin medium, the required computing power is relatively small, making it suitable for general computer equipment. Therefore, it is relatively easy to add subsurface scattering effects to hyper-realistic characters and other objects, making the lighting and shadow effects of the resulting hyper-realistic characters and other objects closer to real-world effects.

[0044] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0045] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0046] To facilitate understanding of this embodiment, a detailed description of the model rendering method disclosed in this disclosure is provided first. The execution entity of the model rendering method provided in this disclosure is generally a computer device with certain computing capabilities. This computer device may include, for example, a terminal device, a server, or other processing devices. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (PDA), handheld device, computing device, in-vehicle device, wearable device, etc. In some possible implementations, this model rendering method can be implemented by the processor calling computer-readable instructions stored in memory.

[0047] The model rendering method provided in this embodiment is described below. The model rendering method provided in this embodiment can be used to determine the target rendering model of a hyper-realistic character, and specifically can be applied to rendering the subsurface scattering effect on the face of a hyper-realistic character. The hyper-realistic character described here can specifically include a character image that simulates and closely resembles a real human face, a game character, etc. Therefore, the model rendering method provided in this embodiment can be specifically applied to different application fields such as game screen production or generation, animation and film production. After determining the target rendering model using the model rendering method provided in this embodiment, the determined target rendering model can be further used to render the hyper-realistic character, so as to make the hyper-realistic character more realistic and plausible through the subsurface scattering effect of different areas of the face displayed in the rendering.

[0048] See Figure 1 The diagram shows a flowchart of a model rendering method provided in an embodiment of this disclosure. The method includes steps S101 to S103, wherein:

[0049] S101: Obtain a 3D model of the target face and obtain target rendering information corresponding to the 3D model; the 3D model includes multiple vertices; the target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the 3D model;

[0050] S102: Based on the target rendering information and the subsurface scattering color tendency map, determine the color tendency corresponding to each of the target vertices; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies;

[0051] S103: Based on the color tendency corresponding to each of the target vertices, render the three-dimensional model to obtain the target rendering model of the three-dimensional model.

[0052] The above S101 to S103 are explained in detail below.

[0053] Regarding S101 above, the 3D model of the target face will first be explained. The target face may specifically include the face of a hyper-realistic character. Since the hyper-realistic character is a virtual object and does not actually exist, the facial features such as the position and size of the facial features of the hyper-realistic character can be determined by constructing a 3D model corresponding to the face of the hyper-realistic character. The determined 3D model is then used to simulate the facial image that the hyper-realistic character would ideally present in the real world. For example, see [link to example]. Figure 2 The diagram shown is a schematic representation of a three-dimensional model of a target face according to an embodiment of this disclosure. The three-dimensional model shown here is an artificially constructed virtual model. Furthermore, different three-dimensional models can be determined for different target faces.

[0054] A 3D model typically consists of multiple vertices located on the surface of the 3D model, and meshes formed by the interconnections between the vertices.

[0055] The target rendering information obtained from the 3D model can be used to characterize the subsurface scattering range of the 3D model and the display light intensity of each target vertex within the subsurface scattering range.

[0056] Specifically, when determining the subsurface scattering range corresponding to a 3D model, one can refer to the range of subsurface scattering effects produced by a real human face under illumination in a real-world scene. For example, in a real human face, because the skin is supported by bones and soft tissues, the curvature and thickness of the skin vary at different locations. The skin at locations with supporting structures, such as the nose wings and earlobes, is thinner and smoother due to the support of bones and soft tissues, resulting in subsurface scattering effects under illumination. Therefore, when determining the subsurface scattering range corresponding to a 3D model, one can identify the areas where the skin is thinner and smoother within the 3D model to determine the corresponding subsurface scattering range on the 3D model.

[0057] In specific implementation, when obtaining target rendering information corresponding to the 3D model, the following method can be adopted: based on the 3D model, determine an initial thickness map for representing the thickness information of the target face and an initial curvature map for representing the curvature information of the target face; based on the initial thickness map and the initial curvature map, determine the target rendering information.

[0058] Specifically, the thickness information of the target face includes the skin thickness at different locations on the face; for example, the skin around the eyes is thinner, resulting in a smaller thickness, while the skin on the cheeks is thicker, resulting in a larger thickness. The curvature information of the target face includes the skin curvature at different locations on the face, representing the smoothness of the face; for example, the edges of the face are more rounded, resulting in a larger skin curvature, while the inner curves of the cheeks are less pronounced, resulting in a smaller skin curvature.

[0059] When determining the initial thickness map and the initial curvature map based on the 3D model, the process of generating the initial thickness map and the initial curvature map can be completed by a 3D digital content creation (DDC) tool, such as Substance.

[0060] In one possible implementation, the initial thickness map can be generated using the following steps A1 to A2:

[0061] A1: Obtain the minimum occlusion distance and the maximum occlusion distance corresponding to the 3D model.

[0062] A2: Based on the minimum occlusion distance, the maximum occlusion distance, and the three-dimensional model, generate an initial thickness texture map corresponding to the three-dimensional model.

[0063] Here, the minimum occlusion distance and the maximum occlusion distance can be parameters preset for the target face. The occlusion distance range formed by the minimum occlusion distance and the maximum occlusion distance is used to characterize the thickness of the target face. The larger the occlusion distance range, the smaller the distance difference between vertices in the 3D model of the target face. The smaller the occlusion distance range, the larger the distance difference between vertices in the 3D model of the target face. The maximum occlusion distance and the minimum occlusion distance are related to the black and white contrast of the generated initial thickness map.

[0064] For example, taking the 3D DDC tool Substance as an example, the preset minimum occlusion distance can be 0.001, and the maximum occlusion distance can be 0.1. Based on Substance, the maximum occlusion distance, the minimum occlusion distance, and the 3D model, the initial thickness map corresponding to the 3D model can be baked.

[0065] For example, a schematic diagram of the initial thickness map can be as follows: Figure 3a As shown, Figure 3a In the diagram, brighter areas indicate greater thickness (i.e., thicker), while darker areas indicate less thickness (i.e., thinner).

[0066] In this way, by obtaining the minimum occlusion distance and the maximum occlusion distance corresponding to the 3D model, an initial thickness map can be generated based on the minimum occlusion distance and the maximum occlusion distance, which facilitates the subsequent generation of target rendering information based on the generated initial thickness map.

[0067] In one possible implementation, the initial curvature map can be generated using the following steps B1-B2:

[0068] B1: Obtain the sampling radius corresponding to the three-dimensional model.

[0069] B2: Based on the sampling radius and the three-dimensional model, generate an initial curvature map corresponding to the three-dimensional model.

[0070] Here, the sampling radius can be a parameter preset for the target face. The sampling radius is used to characterize the circumference radius of the curvature reference model. The larger the sampling radius, the larger the circumference radius of the model, and the greater the curvature difference between vertices in the three-dimensional model of the target face. The smaller the sampling radius, the smaller the circumference radius of the model, and the smaller the curvature difference between vertices in the three-dimensional model of the target face.

[0071] For example, taking the 3D DDC tool Substance as an example, the pre-set sampling radius can be 0.001. Based on the Substance, the maximum occlusion distance, the minimum occlusion distance, and the 3D model, the initial thickness map corresponding to the 3D model can be baked.

[0072] For example, a schematic diagram of the initial curvature map can be as follows: Figure 3b As shown, Figure 3b In the diagram, brighter areas indicate greater curvature, while darker areas indicate smaller curvature.

[0073] In this way, by obtaining the sampling radius, an initial curvature map can be generated based on the sampling radius, which facilitates the subsequent generation of target rendering information based on the generated initial curvature map.

[0074] When determining target rendering information to characterize the subsurface scattering range of the target face based on the initial thickness map and the initial curvature map, although the initial thickness map can be used to characterize the thickness information of the 3D model and the initial curvature map can be used to characterize the curvature information of the 3D model, the subsurface scattering effect of the target face is negatively correlated with the thickness of the target face surface and positively correlated with the curvature of the target face surface. If the initial curvature map and the initial thickness map are directly merged, the resulting merged map cannot be used to render the subsurface scattering effect of the target face. Therefore, it is necessary to process the initial thickness map and the initial curvature map separately first.

[0075] In one possible implementation, when determining the target rendering information used to characterize the subsurface scattering range of the target face, the following steps C1 to C2 can be used:

[0076] C1: Perform brightness adjustment processing on the initial thickness map to obtain the target thickness map; and update the brightness value of the initial curvature map based on a preset brightness value filtering range to obtain the target curvature map.

[0077] Here, the brightness adjustment process is used to adjust the brightness value corresponding to each pixel in the initial thickness map; the brightness value can be a normalized brightness value (ranging from 0 to 1), used to characterize the rendering attributes of the corresponding map, such as characterizing thickness in a thickness map and curvature in a curvature map.

[0078] In one possible implementation, the determination of the target thickness map can be achieved through the following steps C111 to C112:

[0079] C111: Invert the initial thickness map to obtain an inverted initial thickness map.

[0080] Here, the color inversion processing means inverting the brightness values ​​corresponding to each pixel in the initial thickness texture.

[0081] For example, taking the normalized brightness value in the initial thickness texture as being in the range of 0 to 1, and the brightness value of pixel A being 0.1, then the brightness value of pixel A after color inversion is 1 - 0.1 = 0.9.

[0082] For example, the initial thickness map after color inversion can be as follows: Figure 3c As shown, Figure 3c and Figure 3a The images have the same shape, but their brightness values ​​convey opposite meanings. Figure 3c Brighter areas indicate a smaller thickness (i.e., thinner), while darker areas indicate a larger thickness (i.e., thicker).

[0083] C112: Update the initial thickness map after color inversion processing according to the preset brightness value adjustment ratio to obtain the target thickness map.

[0084] Here, the brightness value adjustment ratio is used to reduce the brightness value of each pixel in the initial thickness texture.

[0085] For example, if the brightness value adjustment ratio is 25% and the brightness value of pixel B is 0.6, then the updated brightness value of pixel B is 0.6*(1-25%) = 0.45.

[0086] For example, the target thickness map shown can be as follows: Figure 3d As shown, Figure 3d and Figure 3a The images have the same shape, but the brightness values ​​are reduced. Figure 3d Brighter areas indicate a smaller thickness (i.e., thinner), while darker areas indicate a larger thickness (i.e., thicker).

[0087] Furthermore, when adjusting the brightness values ​​of each pixel in the initial thickness map, it can also respond to the brightness adjustment command for the initial thickness map, update the inverted initial thickness map according to the brightness adjustment command, and obtain the target thickness map.

[0088] In this way, by inverting the initial thickness map, the thickness parameter represented by the brightness value of each pixel in the inverted initial thickness map can be positively correlated with the subsurface scattering effect of the target face, thus facilitating merging with the curvature map. By updating the inverted initial thickness map according to a preset brightness value adjustment ratio, the range of brightness values ​​corresponding to each pixel in the final generated target thickness map can be reduced, thus facilitating subsequent merging with the curvature map.

[0089] In one possible implementation, the determination of the target curvature map can be achieved through the following steps C121 to C122:

[0090] C121: Based on the brightness value filtering range, filter the brightness values ​​of the initial curvature map to determine the target pixel point whose corresponding brightness value in the initial curvature map is within the brightness value filtering range.

[0091] C122: Set the brightness value of the target pixel to zero to obtain the target curvature map.

[0092] Here, in order to highlight the subsurface scattering effect of the target face, subsurface scattering rendering can be performed on the areas with larger curvature of the 3D model corresponding to the target face, while subsurface scattering rendering is not performed on the areas with smaller curvature.

[0093] For example, taking the normalized brightness value in the initial thickness texture as being in the range of 0 to 1, the brightness value filtering range as being 0 to 0.4, and the brightness value of pixel C as being 0.3, the brightness value corresponding to pixel C can be set to zero, that is, the brightness value corresponding to pixel C can be adjusted to 0.

[0094] For example, the target curvature map can be as follows: Figure 3e As shown, Figure 3e and Figure 3b The images have the same shape, but the brightness values ​​of pixels with smaller brightness values ​​are all set to zero (i.e., the black parts in the image).

[0095] In this way, by setting the brightness values ​​of target pixels whose corresponding brightness values ​​are within the brightness value selection range in the initial curvature map to zero, it is possible to achieve the effect of not performing subsurface rendering in areas with small curvature after subsequent merging with the thickness map.

[0096] C2: Based on the target thickness map and the target curvature map, generate an initial thickness map corresponding to the 3D model.

[0097] In one possible implementation, the target thickness map and the target curvature map can be overlaid to determine target rendering information used to characterize the subsurface scattering range of the target face.

[0098] Here, the overlay process can be, for example, a multiply blending mode.

[0099] Specifically, by superimposing the target thickness map and the target curvature map, a superimposed target map can be obtained. The brightness value corresponding to each pixel in the target map is used to characterize the target rendering information.

[0100] For example, the target texture obtained after overlay processing can be as follows: Figure 3f As shown, Figure 3f The brightness value of each pixel is used to characterize the intensity of subsurface scattering. Since there is a correspondence between each pixel and each vertex of the 3D model, the intensity of subsurface scattering expressed by the brightness value of a pixel can also characterize the display light intensity of the corresponding vertex.

[0101] In this process, vertices with non-zero brightness values, i.e., those that render subsurface scattering effects, are designated as target vertices. Therefore, the target rendering information can be used to characterize the display light intensity of each target vertex. Points with zero brightness values ​​are designated as non-target vertices, i.e., those that do not render subsurface scattering effects. During subsequent rendering of the 3D model, these non-target vertices are rendered using their preset base colors.

[0102] Since the brightness values ​​of each pixel in the target thickness map are positively correlated with subsurface scattering, and the brightness values ​​of each pixel in the target curvature map are also positively correlated with subsurface scattering, the target rendering information of the three-dimensional model can be obtained by superimposing the target thickness map and the target curvature map. Specifically, this information can be used to characterize the target rendering information corresponding to the three-dimensional model.

[0103] Regarding S102 above, after determining the target vertex used to render the subsurface scattering effect, the color rendered by that target vertex under the subsurface scattering effect can also be determined accordingly. Since the subsurface scattering effect involves light scattering in the skin medium to produce different colors, these colors are relatively specific and fixed, specifically including transitional colors from light yellow to red, and then to black. Therefore, the target rendering information can be used to determine the color tendency of the target vertex under the subsurface scattering effect from the transitional colors. This color tendency can specifically represent the tendency of the target vertex's rendered color under the subsurface scattering effect in multiple aspects such as hue, lightness, and chroma. For example, for a target vertex located at the edge of the cheek, under the subsurface scattering effect, the red hue channel will lean towards white, and the lightness will also lean towards brighter. In other words, the color tendency can be used to determine the rendered color of the target vertex under subsurface scattering.

[0104] Specifically, regarding the transitional colors exhibited under the subsurface scattering effect described above, a color tendency map, i.e., a look-up table (LUT), can be created. For example, see [link to example]. Figure 4 The diagram shown is a schematic representation of a color tendency map provided in an embodiment of this disclosure. In the color tendency map, colors on the left are more yellowish and lighter, while colors on the right are more blackish and darker. Below the color tendency map, coordinate axes with arrows are used to indicate the display light intensity. Corresponding to the mapping relationship in the color tendency map, for target vertices with higher display light intensity, the corresponding subsurface scattering color is more yellowish and lighter; for target vertices with lower display light intensity, the corresponding subsurface scattering color is more blackish and darker.

[0105] In specific implementation, when determining the color tendency corresponding to each of the target vertices based on the target rendering information and the subsurface scattering color tendency map, the following method can be adopted: For any target vertex, based on the display light intensity corresponding to the target vertex and the mapping relationship between different display light intensities and color tendencies described in the color tendency map, the target pixel corresponding to the target vertex is determined from the color tendency map; the color tendency indicated by the target pixel is determined as the color tendency corresponding to the target vertex.

[0106] For any target vertex, the corresponding display light intensity can be determined using the target rendering information in the steps described above. In the color tendency map, the display light intensity at each value corresponds to a pixel at a different location, and each pixel corresponds to a different color tendency. Thus, using the display light intensity of the target vertex, the corresponding target pixel can be determined in the color tendency map; the color tendency indicated by the target pixel is then used as the color tendency corresponding to the target vertex.

[0107] In one possible scenario, since the color tendency map reflects the color of light when it exhibits subsurface scattering in the skin medium of a human face, after determining the pixel value corresponding to the display light intensity of the target vertex in the color tendency map, the color tendency of the target vertex can be used as the color tendency of the target vertex, and further, the color tendency can be used as the rendering color of the target vertex when rendering the subsurface scattering effect.

[0108] In another possible scenario, the pixel values ​​corresponding to each pixel in the color tendency map are used only to reflect the color tendency. For example, using the median of the pixel values ​​as a benchmark, if the pixel value of a pixel determined by the display light intensity as the target vertex is lower than the median, then the color tendency is considered to include a darker, more blackish color appearing at that target vertex under the subsurface scattering effect; conversely, if the pixel value of a pixel determined by the display light intensity as the target vertex is higher than the median, then the color tendency is considered to include a lighter, more yellowish color appearing at that target vertex under the subsurface scattering effect.

[0109] Regarding S103 above, after determining the color tendency corresponding to each target vertex, the 3D model can be rendered to obtain the target rendering model of the 3D model.

[0110] In one possible scenario, if the color tendency (i.e., pixel value) of the target vertex in the color tendency map is directly used to determine the rendering color for rendering the subsurface scattering effect, then in this step, for the target vertex in the 3D model, the rendering color corresponding to the determined pixel value can be used to render the subsurface scattering effect for the target vertex. For non-target vertices, as can be seen from the above steps, they do not have a subsurface scattering effect under light; therefore, they can be rendered using only a preset initial color, which may include, for example, a preset skin tone.

[0111] In another possible scenario, if the color tendency of the target vertex is used to influence and adjust the pixel values ​​when rendering the subsurface scattering effect, then specifically for any of the target vertexes, the base color of the target vertex can be adjusted based on the color tendency corresponding to the target vertex to obtain the rendering color of the target vertex; the 3D model can be rendered based on the rendering colors corresponding to each of the target vertices to obtain the target rendering model of the 3D model.

[0112] Here, the reference color can specifically include the color of each vertex in the 3D model under illumination without exhibiting subsurface scattering effects. Specifically, the reference color can be determined based on two colors: a preset skin color and a lighting color. Specifically, the reference color for any vertex can be determined as follows: obtain the lighting color corresponding to the target light source illuminating the 3D model, and obtain a color map corresponding to the 3D model; determine the initial color corresponding to each vertex in the 3D model based on the color map; superimpose the initial color corresponding to each vertex and the lighting color to obtain the reference color corresponding to each vertex.

[0113] The lighting color corresponding to the target light source in the 3D model can be determined based on the actual situation. For example, the lighting color may include white or yellow light that mimics natural light, or light with a specific color that mimics other artificial light sources, such as red, green, or blue. In reality, lighting color also has a certain impact on the color of the face. For example, in real-world scenes, the color of a face under different lighting conditions will be affected by the different colors of the lighting.

[0114] Color maps for 3D models can be used to represent the skin tone of each vertex. Since facial skin tone is typically uneven—for example, the skin tone around the nose and jawline may be darker than other areas due to pigment deposition—color maps can effectively determine the skin tone of each area. Correspondingly, color maps can also be used to determine the skin tone, or initial color, of each vertex in a 3D model.

[0115] In this way, by superimposing the initial color corresponding to each vertex in the 3D model determined by the color map and the lighting color described above, the base color corresponding to each vertex can be obtained.

[0116] Furthermore, regarding the color bias described above, the color bias specifically includes the adjustment ratio of the base color under the corresponding display light intensity. For example, for any target vertex, if the pixel value of the target pixel in the color bias map is much lower than the median, for example, appearing black, then the adjustment ratio of the base color is correspondingly larger, and the pixel value of the adjusted base color is reduced, so that when rendering the subsurface scattering effect, the target vertex appears darker and blacker than the original base color. Therefore, the adjustment ratio can be determined based on the pixel value of the target pixel in the color bias map. The adjustment ratio is used, on the one hand, to adjust the base color towards darker or lighter colors, and also includes adjusting the base color towards yellow or black; on the other hand, it also determines the adjustment magnitude. For example, if the target pixel in the color bias map appears yellow, meaning the corresponding pixel value is large, then the adjustment magnitude when adjusting the base color is also larger.

[0117] Therefore, in practice, once a color tendency is determined for the target vertex, the pixel value of the base color corresponding to the target vertex can be numerically adjusted based on the adjustment ratio corresponding to the color tendency to obtain the rendering color of the target vertex.

[0118] Thus, given a determined rendering color for the target vertex, the target vertex can be rendered using that color to represent the subsurface scattering effect at that vertex. Conversely, non-target vertices can be rendered using their corresponding base colors to represent skin color under lighting, thus obtaining the target rendering model of the 3D model.

[0119] The present invention discloses a model rendering method, apparatus, computer device, and storage medium that utilizes a subsurface scattering color tendency map to determine the color tendency corresponding to each target vertex in the subsurface scattering region, and uses the color tendency to render the three-dimensional model. This method can achieve a good subsurface scattering effect on the rendered target model without simulating the scattering effect of skin medium on light. Therefore, it requires less computing power and is suitable for general computer devices. Consequently, it can more easily add subsurface scattering effects to objects such as hyper-realistic characters, making the lighting and shadow effects of the hyper-realistic characters and other objects closer to the real effect.

[0120] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0121] Based on the same inventive concept, this disclosure also provides a model rendering device corresponding to the model rendering method. Since the principle of the device in this disclosure for solving the problem is similar to the model rendering method described above in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0122] Reference Figure 5 The diagram shown is a schematic of a model rendering apparatus provided in an embodiment of this disclosure. The apparatus includes: an acquisition module 51, a determination module 52, and a rendering module 53; wherein,

[0123] The acquisition module 51 is used to acquire a three-dimensional model of the target face and to acquire target rendering information corresponding to the three-dimensional model; the three-dimensional model includes multiple vertices; the target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the three-dimensional model;

[0124] The determining module 52 is used to determine the color tendency corresponding to each of the target vertices based on the target rendering information and the color tendency map of subsurface scattering; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies;

[0125] The rendering module 53 is used to render the three-dimensional model based on the color tendency corresponding to each of the target vertices to obtain the target rendering model of the three-dimensional model.

[0126] In one optional implementation, when acquiring target rendering information corresponding to the three-dimensional model, the acquisition module 51 is configured to: determine an initial thickness map for characterizing the thickness information of the target face and an initial curvature map for characterizing the curvature information of the target face based on the three-dimensional model; and determine the target rendering information based on the initial thickness map and the initial curvature map.

[0127] In one optional implementation, when determining the color tendency corresponding to each of the target vertices based on the target rendering information and the subsurface scattering color tendency map, the determining module 52 is configured to: for any target vertex, based on the display light intensity corresponding to the target vertex and the mapping relationship between different display light intensities and color tendencies described in the color tendency map, determine the target pixel corresponding to the target vertex from the color tendency map; and determine the color tendency indicated by the target pixel as the color tendency corresponding to the target vertex.

[0128] In one optional implementation, when the rendering module 53 renders the three-dimensional model based on the color tendency corresponding to each of the target vertices to obtain the target rendering model of the three-dimensional model, it is configured to: for any target vertex, adjust the base color of the target vertex based on the color tendency corresponding to the target vertex to obtain the rendering color of the target vertex; and render the three-dimensional model based on the rendering colors corresponding to each of the target vertices to obtain the target rendering model of the three-dimensional model.

[0129] In one optional implementation, the color tendency includes: an adjustment ratio of the reference color under a display light intensity corresponding to the color tendency; when the rendering module 53 adjusts the reference color of any target vertex based on the color tendency corresponding to the target vertex to obtain the rendering color of the target vertex, it is used to: adjust the pixel value of the reference color corresponding to the target vertex based on the adjustment ratio to obtain the rendering color of the target vertex.

[0130] In one optional implementation, the reference color corresponding to any vertex is determined by: obtaining the illumination color corresponding to the target light source illuminating the 3D model and obtaining the color map corresponding to the 3D model; determining the initial color corresponding to each vertex in the 3D model based on the color map; and superimposing the initial color corresponding to each vertex and the illumination color to obtain the reference color corresponding to each vertex.

[0131] In an optional implementation, the acquisition module 51 is further configured to generate the initial thickness map and the initial curvature map according to the following steps: acquiring the minimum occlusion distance and the maximum occlusion distance corresponding to the three-dimensional model; generating the initial thickness map corresponding to the three-dimensional model based on the minimum occlusion distance, the maximum occlusion distance and the three-dimensional model; and acquiring the sampling radius corresponding to the three-dimensional model; generating the initial curvature map corresponding to the three-dimensional model based on the sampling radius and the three-dimensional model.

[0132] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0133] This disclosure also provides a computer device, such as... Figure 6 The diagram shown is a schematic representation of a computer device structure provided in an embodiment of this disclosure, including:

[0134] Processor 10 and memory 20; the memory 20 stores machine-readable instructions executable by processor 10, and processor 10 executes the machine-readable instructions stored in memory 20. When the machine-readable instructions are executed by processor 10, processor 10 performs the following steps:

[0135] A 3D model of the target face is obtained, along with target rendering information corresponding to the 3D model. The 3D model includes multiple vertices. The target rendering information characterizes the display light intensity of each target vertex within the subsurface scattering range corresponding to the 3D model. Based on the target rendering information and the color tendency map of the subsurface scattering, the color tendency corresponding to each target vertex is determined. The color tendency map describes the mapping relationship between different display light intensities and color tendencies. Based on the color tendency corresponding to each target vertex, the 3D model is rendered to obtain the target rendering model of the 3D model.

[0136] The aforementioned memory 20 includes a main memory 210 and an external memory 220; the main memory 210, also known as internal memory, is used to temporarily store the computational data in the processor 10, as well as the data exchanged with external memory 220 such as a hard disk. The processor 10 exchanges data with the external memory 220 through the main memory 210.

[0137] The specific execution process of the above instructions can be referred to the steps of the model rendering method described in the embodiments of this disclosure, and will not be repeated here.

[0138] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the model rendering method described in the above method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0139] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the model rendering method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0140] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0141] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0142] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] In addition, the functional units in the various embodiments of this disclosure 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.

[0144] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion 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 this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0145] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A model rendering method, characterized in that, include: Obtain a 3D model of the target face and obtain target rendering information corresponding to the 3D model; The three-dimensional model includes multiple vertices; The target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the three-dimensional model; Based on the target rendering information and the subsurface scattering color tendency map, the color tendency corresponding to each of the target vertices is determined; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies. Based on the color tendency corresponding to each of the target vertices, the three-dimensional model is rendered to obtain the target rendering model of the three-dimensional model. The process of obtaining target rendering information corresponding to the 3D model includes: Based on the three-dimensional model, an initial thickness map for characterizing the thickness information of the target face and an initial curvature map for characterizing the curvature information of the target face are determined. The initial thickness map is inverted to obtain an inverted initial thickness map; the inverted initial thickness map is updated according to a preset brightness value adjustment ratio to obtain the target thickness map. The brightness values ​​of the initial curvature map are filtered based on the brightness value filtering range to determine the target pixel points whose corresponding brightness values ​​in the initial curvature map are within the brightness value filtering range; the brightness values ​​of the target pixel points are set to zero to obtain the target curvature map. The target thickness map and the target curvature map are superimposed to generate target rendering information that characterizes the subsurface scattering range corresponding to the three-dimensional model.

2. The method according to claim 1, characterized in that, The step of determining the color tendency corresponding to each of the target vertices based on the target rendering information and the subsurface scattering color tendency map includes: For any target vertex, based on the display light intensity corresponding to the target vertex and the mapping relationship between different display light intensities and color tendencies described in the color tendency map, the target pixel point corresponding to the target vertex is determined from the color tendency map; The color tendency indicated by the target pixel is determined as the color tendency corresponding to the target vertex.

3. The method according to any one of claims 1-2, characterized in that, The process of rendering the 3D model based on the color tendency corresponding to each of the target vertices to obtain the target rendering model of the 3D model includes: For any of the target vertices, the base color of the target vertex is adjusted based on the color tendency corresponding to the target vertex to obtain the rendered color of the target vertex; The 3D model is rendered based on the rendering color corresponding to each of the target vertices to obtain the target rendering model of the 3D model.

4. The method according to claim 3, characterized in that, The color tendency includes: the adjustment ratio of the reference color under the display light intensity corresponding to the color tendency; The step of adjusting the base color of any target vertex based on its corresponding color tendency to obtain its rendered color includes: For any target vertex, based on the adjustment ratio of the reference color, the pixel value of the reference color corresponding to the target vertex is numerically adjusted to obtain the rendering color of the target vertex.

5. The method according to claim 4, characterized in that, The base color corresponding to any of the target vertices is determined in the following manner: Obtain the illumination color corresponding to the target light source illuminating the 3D model, and obtain the color texture corresponding to the 3D model; The initial color corresponding to each vertex in the 3D model is determined based on the color map. The initial color corresponding to each vertex and the lighting color are superimposed to obtain the base color corresponding to each vertex.

6. The method according to claim 1, characterized in that, The method further includes: generating the initial thickness map and the initial curvature map according to the following steps: Obtain the minimum occlusion distance and maximum occlusion distance corresponding to the 3D model; based on the minimum occlusion distance, maximum occlusion distance, and the 3D model, generate an initial thickness texture map corresponding to the 3D model; and, Obtain the sampling radius corresponding to the three-dimensional model; based on the sampling radius and the three-dimensional model, generate an initial curvature map corresponding to the three-dimensional model.

7. A model rendering apparatus, characterized in that, include: The acquisition module is used to acquire a 3D model of the target face and acquire target rendering information corresponding to the 3D model; The three-dimensional model includes multiple vertices; the target rendering information is used to characterize the display light intensity of each target vertex within the subsurface scattering range corresponding to the three-dimensional model; wherein, obtaining the target rendering information corresponding to the three-dimensional model includes: determining an initial thickness map for characterizing the thickness information of the target face and an initial curvature map for characterizing the curvature information of the target face based on the three-dimensional model; inverting the initial thickness map to obtain an inverted initial thickness map; updating the inverted initial thickness map according to a preset brightness value adjustment ratio to obtain a target thickness map; filtering the brightness values ​​of the initial curvature map based on a brightness value filtering range to determine target pixels whose corresponding brightness values ​​in the initial curvature map are within the brightness value filtering range; setting the brightness values ​​of the target pixels to zero to obtain a target curvature map; and superimposing the target thickness map and the target curvature map to generate target rendering information characterizing the subsurface scattering range corresponding to the three-dimensional model; The determination module is used to determine the color tendency corresponding to each of the target vertices based on the target rendering information and the color tendency map of subsurface scattering; the color tendency map is used to describe the mapping relationship between different display light intensities and color tendencies; The rendering module is used to render the three-dimensional model based on the color tendency corresponding to each of the target vertices, so as to obtain the target rendering model of the three-dimensional model.

8. A computer device, characterized in that, include: A processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor executing the machine-readable instructions stored in the memory, wherein when the machine-readable instructions are executed by the processor, the processor performs the steps of the model rendering method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a computer device, performs the steps of the model rendering method as described in any one of claims 1 to 6.

Images