Method for generating three-dimensional landscape character model

Abstract

The present invention relates to the field of digital art and discloses a method for generating a three-dimensional landscape word model. The method comprises the following steps: step 1, providing input text style information; step 2, parsing the text style information through an artificial intelligence algorithm and extracting text style features; step 3, automatically generating a three-dimensional base model based on the text style features; step 4, performing preliminary modeling of the three-dimensional base using polygon modeling technology; step 5, applying a surface modeling method to the polygon modeling result to generate a smooth surface; step 6, mapping and enhancing the detail texture of the three-dimensional base model through a deep neural network. By automatically parsing the input text style information and generating a three-dimensional word model through an artificial intelligence algorithm deep convolutional neural network and a generative adversarial network, the need for manual intervention is greatly reduced, the efficiency and accuracy of generating the three-dimensional word model are improved, and a large amount of time and cost are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital art, in particular to a method for generating a three-dimensional landscape character model. Background Art

[0002] With the continuous development of computer graphics and virtual reality technologies, 3D modeling has become an indispensable technology in numerous industries, such as advertising design, film and television special effects, game development, and virtual reality. In particular, in the fields of advertising and brand promotion, 3D landscape lettering models serve as a crucial visual presentation method, possessing a high degree of visual impact and communication effectiveness. Traditional 3D lettering model production often requires manual design and fine-tuning, which is not only time-consuming and labor-intensive, but also difficult to automate. Improving production efficiency and precision is particularly urgent when extensive customized content is required.

[0003] Currently, methods for generating three-dimensional letter models primarily rely on traditional computer graphics techniques and manual modeling processes. Traditional methods typically use 3D modeling software (such as Autodesk Maya and Blender) for manual modeling, with designers manually adjusting the shape, texture, and lighting effects of the letters based on the input text style. While these methods can generate relatively detailed three-dimensional letter models, they often suffer from shortcomings such as long production cycles, cumbersome design processes, and excessive manual intervention. In recent years, with advances in deep learning technology, 3D model generation methods based on artificial intelligence algorithms have gradually attracted attention. Some studies have attempted to use convolutional neural networks (CNNs) and generative adversarial networks (GANs) to automatically generate and optimize 3D images and models.

[0004] Although existing technologies have improved the accuracy and efficiency of 3D word model generation to a certain extent, the following problems still exist: existing methods lack effective technical support for the automated generation and detailed representation of 3D word models, and have obvious flaws in texture mapping, lighting adaptability, and environmental adaptation. For example, traditional texture mapping technology is prone to seams and flaws, and its performance is unstable under changing lighting conditions, making it difficult to meet the demand for high-quality visual effects in modern advertising and virtual environments. In addition, existing methods cannot guarantee visual consistency from different perspectives, especially when lighting changes or scene switching, and inconsistent effects often occur. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a method for generating a three-dimensional landscape font model, which solves the problem that traditional texture mapping technology is prone to seams and defects, and its performance is unstable under changing lighting conditions, making it difficult to meet the requirements of high-quality visual effects in modern advertising and virtual environments.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for generating a three-dimensional landscape character model, the method comprising the following steps:

[0007] Step 1: Provide input text style information;

[0008] Step 2: Analyze the text style information using an artificial intelligence algorithm to extract text style features;

[0009] Step 3: Automatically generate a three-dimensional matrix model based on the text style features;

[0010] Step 4: Using polygonal modeling technology to perform preliminary modeling on the three-dimensional matrix;

[0011] Step 5: Applying a surface modeling method to the polygonal modeling result to generate a smooth surface;

[0012] Step 6: Mapping and enhancing the detail texture of the three-dimensional base model through a deep neural network;

[0013] Step 7: Using ray tracing technology to simulate the light and shadow of the three-dimensional matrix model under different lighting conditions;

[0014] Step 8: Automatically adjust the color, material and reflection properties of the three-dimensional character model through environmental perception technology to make it blend with the lighting conditions and environment in the virtual scene.

[0015] Preferably, the text style information includes font, thickness, curve and appearance features, and the text style features are parsed by a deep convolutional neural network, and the obtained text style features are used to construct a three-dimensional matrix model.

[0016] Preferably, the three-dimensional matrix model is generated by polygonal modeling technology, specifically including meshing the text outline information and using surface fitting technology to smoothly optimize the generated polygonal model, and finally generating a three-dimensional font model.

[0017] Preferably, the three-dimensional matrix model is generated by polygonal modeling technology, specifically including meshing the text outline information and using surface fitting technology to smoothly optimize the generated polygonal model, and finally generating a three-dimensional font model.

[0018] Preferably, the ray tracing technology is used to simulate reflection, refraction and diffuse reflection phenomena under lighting conditions.

[0019] Preferably, the environment perception technology automatically adjusts the color, reflectivity and glossiness of the three-dimensional character model to make it consistent with the surrounding environment by real-time perception of the lighting distribution, color distribution and material properties in the virtual scene.

[0020] Preferably, the detail enhancement of the three-dimensional character model is performed through a deep convolutional neural network, specifically including multi-scale learning of the surface texture of the letters, thereby enhancing the performance of the letter edges, surface gloss and material.

[0021] Preferably, the method further comprises performing multi-view rendering on the generated three-dimensional landscape font model, and verifying the consistency of the rendering results at different viewpoints using mean square error.

[0022] Preferably, the method is applicable to advertising design, virtual scene modeling, augmented reality and virtual reality application scenarios, in which the three-dimensional character model can be adaptively adjusted according to changes in different environments.

[0023] A computer-readable storage medium stores program codes, which, when executed, can implement the three-dimensional landscape character model generation method.

[0024] The present invention provides a method for generating a three-dimensional landscape character model. It has the following beneficial effects:

[0025] 1. The present invention uses artificial intelligence algorithms, deep convolutional neural networks, and generative adversarial networks to automatically parse input text style information and generate three-dimensional character models, significantly reducing the need for manual intervention and improving the efficiency and accuracy of three-dimensional character model generation. The automated process simplifies the design process and saves a lot of time and costs.

[0026] 2. This invention uses deep learning technology to accurately map the texture of 3D character models, combined with a generative adversarial network to optimize texture effects, effectively eliminating seams and artifacts common in traditional texture mapping. Furthermore, using a deep convolutional neural network for detail enhancement, the model's surface texture, letter edges, and gloss are refined, enhancing the realism and visual quality of the 3D model.

[0027] 3. This invention uses ray tracing technology to simulate reflection, refraction, and diffuse reflection under real-world lighting conditions, ensuring consistent rendering of the 3D character model in diverse lighting environments. Whether in strong or weak light, or in environments with dynamic light source fluctuations, the model can adapt to lighting changes and maintain visual stability.

[0028] 4. This invention uses environmental perception technology to detect the lighting, color, and material properties of the virtual scene in real time, and intelligently adjusts the color, reflectivity, and glossiness of the 3D character model based on environmental changes. This dynamic adjustment mechanism enables the 3D character model to blend harmoniously with its surroundings, enhancing its overall expressiveness and avoiding the poor environmental adaptation issues inherent in traditional 3D modeling techniques.

[0029] 5. The generation method of the present invention includes multi-perspective rendering and visual consistency verification steps. By using the mean square error to compare the rendering results of different perspectives, it is ensured that the generated three-dimensional character model always maintains a consistent visual effect under multiple perspectives, avoiding the problem of inconsistent effects caused by lighting changes or texture distortion under multiple perspectives. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a flow chart of the method of the present invention;

[0031] Figure 2 Schematic diagram of the storage medium structure of the present invention. DETAILED DESCRIPTION

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0033] Please see the attached Figure 1 ,An embodiment of the present invention provides a method for generating a three-dimensional landscape character model, the method comprising the following steps: step 1, providing input text style information;

[0034] Step 2: Analyze text style information through artificial intelligence algorithms and extract text style features;

[0035] Step 3: Automatically generate a 3D base model based on the text style features;

[0036] Step 4: Use polygonal modeling technology to perform preliminary modeling of the three-dimensional base;

[0037] Step 5: Apply surface modeling method to the polygon modeling result to generate a smooth surface;

[0038] Step 6: Map and enhance the detail texture of the 3D base model through a deep neural network;

[0039] Step 7: Use ray tracing technology to simulate the light and shadow of the three-dimensional matrix model under different lighting conditions;

[0040] Step 8: Automatically adjust the color, material, and reflection properties of the three-dimensional font model through environmental perception technology to make it blend with the lighting conditions and environment in the virtual scene.

[0041] Text style information includes font, thickness, curve and appearance features. The text style features are analyzed through a deep convolutional neural network, and the obtained text style features are used to construct a three-dimensional matrix model.

[0042] The three-dimensional matrix model is generated through polygonal modeling technology, which specifically includes meshing the text contour information and using surface fitting technology to smooth and optimize the generated polygonal model, ultimately generating a three-dimensional font model.

[0043] The three-dimensional matrix model is generated through polygonal modeling technology, which specifically includes meshing the text contour information and using surface fitting technology to smooth and optimize the generated polygonal model, ultimately generating a three-dimensional font model.

[0044] Ray tracing technology is used to simulate reflection, refraction, and diffuse reflection under lighting conditions.

[0045] Environmental perception technology automatically adjusts the color, reflectivity and glossiness of the three-dimensional font model by real-time perception of the light distribution, color distribution and material properties in the virtual scene to make it consistent with the surrounding environment.

[0046] The details of the three-dimensional letter model are enhanced through a deep convolutional neural network, which specifically includes multi-scale learning of the surface texture of the letters, thereby enhancing the performance of the letter edges, surface gloss and material.

[0047] The method further includes performing multi-view rendering on the generated three-dimensional landscape font model, and using mean square error to verify the consistency of the rendering results from different viewpoints.

[0048] The method is applicable to advertising design, virtual scene modeling, augmented reality and virtual reality application scenarios, in which the three-dimensional character model can be adaptively adjusted according to changes in different environments.

[0049] In one embodiment, step 1: input text style information

[0050] The user enters the text content to be generated (such as a brand name, slogan, etc.) through the computer interface and selects the corresponding font style and design elements. For example, the user enters the text "BRAND" and selects the font ArialBold, bold style, and sets parameters such as font size and spacing.

[0051] The system obtains the input text and combines it with the style information set by the user to generate corresponding digitized text content, and passes this content to the subsequent processing module.

[0052] Step 2: Text style information analysis

[0053] The selected text style information (such as font, weight, curves, corners, etc.) is input into the text parsing module and processed using a deep convolutional neural network (CNN). The CNN network performs multi-level feature extraction on the text, identifies various geometric features of the text, and converts them into a digital text style feature vector F.s .

[0054] The input "B" letter is converted into a set of geometric features through convolutional layers and pooling layers. These features include information such as the edges, line thickness, angles, and curvatures of the letter.

[0055] Step 3: 3D base model construction

[0056] According to the parsed text style feature F s The system automatically uses polygonal modeling technology to mesh the text outline. Specifically, the Delaunay triangulation algorithm is used to convert the text outline into a preliminary three-dimensional polygon mesh. Then, a surface fitting algorithm is applied to smooth the mesh to generate a smooth three-dimensional font model.

[0057] Each edge of the letter is meshed. For example, the surface of the letter "B" is processed to generate a smooth rounded curve boundary, removing the corners and edges that may appear in the traditional modeling process.

[0058] Step 4: Texture mapping and detail enhancement

[0059] A deep convolutional neural network (CNN) is used to perform texture mapping on the generated 3D font model. The system first generates a preliminary texture using preset textures from the texture library and maps it to the surface of the 3D font model. Then, a generative adversarial network (GAN) is used to optimize the generated texture, automatically repairing texture seams and fine details. Assuming the user requires the generated "B" to have a metallic sheen, the system uses a GAN network to optimize the metal texture, automatically repairing the seams in the texture map, and making the texture fit the 3D font more naturally.

[0060] Step 5: Ray tracing and lighting effect simulation

[0061] Ray tracing technology is applied to the generated 3D letter model to simulate real-world lighting effects, including reflection, refraction, and diffuse reflection. By calculating the interaction between light and the surface of the object, the system can adjust the surface lighting and shadow effects of the 3D letter model in real time, ensuring the model's realism under different lighting conditions.

[0062] Assuming the model is in a virtual scene, the light source consists of a fixed point light source and a variable directional light source. The ray tracing algorithm simulates the details of the metal surface reflection and the shadow effect of the letters by calculating the interaction between the light source and the surface of the object.

[0063] Step 6: Environmental Perception and Adaptive Adjustment

[0064] Environmental awareness technology automatically detects the current scene's environmental characteristics by analyzing the lighting distribution, color distribution, and material properties in real time. Based on these perceived environmental characteristics, the system dynamically adjusts the color, material, and glossiness of the 3D font model to ensure the model blends naturally into the scene.

[0065] Assuming that the background of the virtual environment is a dark city night scene with weak lighting, the system will automatically adjust the color of the model based on the environmental perception results to make it brighter to ensure that the text maintains high visibility in the virtual scene.

[0066] Step 7: Multi-view rendering and consistency verification

[0067] After generating the 3D font model, the system performs multi-view rendering. Specifically, the model is rendered from multiple viewpoints (such as top, side, and oblique side). The consistency of the rendering results from different viewpoints is then verified using a mean square error algorithm to ensure consistent lighting and texture effects for the 3D font model across all viewpoints.

[0068] Users can adjust the viewing angle in the virtual environment, and the system will automatically verify the rendering effects under multiple perspectives and ensure that there are no lighting inconsistencies or texture damage.

[0069] Step 8: Export the 3D font model

[0070] Finally, the generated 3D font model can be rendered and displayed in real time through a computer graphics engine (such as OpenGL or DirectX), or exported to OBJ, FBX standard 3D file formats for use in other design software or virtual environments.

[0071] Please see the attached Figure 2 , the present invention also provides a computer-readable storage medium, wherein:

[0072] The program code includes a text style information parsing module for receiving input text style information and parsing the text style information through an artificial intelligence algorithm to extract text style features;

[0073] The program code also includes a three-dimensional matrix generation module for generating a three-dimensional matrix model based on text style features using polygon modeling technology and optimizing the three-dimensional matrix model using a surface modeling method;

[0074] The program code further includes a texture mapping and detail enhancement module for performing high-precision texture mapping on a three-dimensional base model using a deep convolutional neural network (CNN), optimizing the texture effect using a generative adversarial network (GAN), and further performing detail enhancement using a deep convolutional neural network (DCNN);

[0075] The program code further includes a ray tracing and lighting simulation module for applying ray tracing technology to simulate lighting effects, including reflection, refraction, and diffuse reflection, based on the geometric shape of the three-dimensional character model and the position of the light source;

[0076] The program code also includes an environment perception and adaptive adjustment module for real-time perception of the lighting, color distribution, and material properties in the virtual scene, and automatically adjusting the color, material, and reflectivity of the three-dimensional character model to make it consistent with the lighting and background characteristics of the virtual environment;

[0077] The program code also includes a multi-view rendering and consistency verification module, which is used to render the three-dimensional font model from different angles and use the mean square error (MSE) to verify the consistency of the rendering results under different perspectives, ensuring that the visual effect of the three-dimensional font model remains consistent under all perspectives.

[0078] Computer-readable storage media include, but are not limited to, hard disks, solid-state drives, optical disks, USB flash drives, SD cards, cloud storage, or other media with storage capabilities.

[0079] The program code may also be executed by a programmable logic device, an integrated circuit (IC), or a processor (eg, a CPU, a GPU, an FPGA, etc.) to implement the method of the present invention.

[0080] The program code may include an application programming interface (API) and interface code for interacting with other program components to facilitate collaboration with other software and hardware devices.

[0081] The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (READ-ONLY MEMORY), magnetic memory, flash memory, magnetic disk or optical disk.

[0082] Experimental setup

[0083] 1. Experimental Environment

[0084] Hardware configuration:

[0085] Processor: Intel Core i9-11900K 8 cores 16 threads

[0086] GPU: NVIDIA RTX3080

[0087] Memory: 64GB RAM

[0088] Storage: 1TB SSD

[0089] Operating system: Windows 10 Pro 64-bit

[0090] Software Configuration:

[0091] Programming language: Python 3.8

[0092] Deep learning framework: TensorFlow 2.6

[0093] Computer graphics engine: Blender 2.93 (for 3D rendering)

[0094] Image processing library: OpenCV 4.5

[0095] Generative Adversarial Networks (GANs): Implementation with TensorFlow and Keras

[0096] Experimental platform:

[0097] A three-dimensional landscape character model generation system is adopted based on the technical solution of the present invention.

[0098] The comparison system uses traditional 3D modeling tools (such as Autodesk Maya or Blender) and a 3D font model generation method based on manually set texture and lighting parameters.

[0099] 2. Experimental content and steps

[0100] Experiment 1: Comparison of visual effects of generative models

[0101] Experimental purpose: To compare the visual effects of the three-dimensional character model between the method of the present invention and the traditional method.

[0102] Experimental steps:

[0103] Sample selection: Select multiple glyph samples (such as "BRAND", "PRODUCT") for testing.

[0104] Method 1 (traditional method): Use traditional 3D modeling tools to manually set the font shape and texture, and generate a 3D font model by setting static lighting and simple texture mapping.

[0105] Method 2 (method of the present invention): Use the method of the present invention to automatically parse the text style and generate a three-dimensional character model through deep learning, and apply ray tracing and environmental perception to automatically adjust the lighting, color and material.

[0106] Comparison content: Compare the visual effects, detail performance (such as gloss, texture clarity) and consistency of the generated models under different lighting conditions (strong light, weak light, dynamic light source).

[0107] Evaluation indicators:

[0108] Detail: Compare each model's gloss, surface texture, and reflections using a visual scoring criteria.

[0109] Consistency: Compare the consistency of models rendered from multiple perspectives, especially under different lighting conditions.

[0110] Experimental results:

[0111] Traditional methods: When the lighting conditions change, the generated 3D font model loses surface texture details, the reflection effect is relatively stiff, and the display effect is inconsistent under strong and weak light conditions.

[0112] The method of the present invention: When the lighting conditions change, the generated three-dimensional character model can adjust the gloss, reflection properties and color in real time, so that the display effect under strong light, weak light and dynamic light conditions is consistent, and the details are richer and more refined.

[0113]

[0114] Table 1

[0115] Lighting adaptability: measures the model's ability to adapt to different lighting conditions.

[0116] Texture clarity: The fineness of the texture, ranging from low (50%) to high (100%).

[0117] Reflection effect: the strength of the reflection effect on the model surface.

[0118] Multi-view consistency: The lighting and texture consistency of the model under multiple viewpoints.

[0119] Experiment 2: Generation Speed ​​Comparison Experiment Purpose: To evaluate the efficiency of the method of the present invention in the process of generating three-dimensional character models compared with the traditional method.

[0120] Experimental steps:

[0121] Method 1 (traditional method): Use traditional 3D modeling tools to manually build models, perform texture mapping, lighting settings, and render.

[0122] Method 2 (method of the present invention): Use the automated three-dimensional character generation system of the present invention to automatically parse the text style and generate a three-dimensional character model, and perform ray tracing, texture mapping and detail enhancement.

[0123] Evaluation indicators:

[0124] Time efficiency: The total time from inputting text to generating a 3D character model is calculated for each method.

[0125] Experimental results:

[0126] Traditional method: In the process of generating the model, manually setting and adjusting the lighting, texture, material and other steps takes a long time. It takes about 20-30 minutes to generate a complex glyph model.

[0127] The method of the present invention: through an automated process, it only takes about 5-7 minutes to generate a complex three-dimensional character model, which is significantly faster.

[0128] Experimental methods Generation time (one minute) Time Improvement Example 1 20-30 minutes - Experiment 2 5-7 minutes Increased by about 70%

[0129] Table 2

[0130] Generation time: the time from inputting text to generating a complete 3D character model.

[0131] Time Improvement: The percentage by which the generation speed is improved compared to traditional methods.

[0132] Model complexity: The amount of computation required to generate the model based on the complexity of the input text.

[0133] Experiment 3: Environmental adaptability test of the model Experimental purpose: to test the environmental adaptability of the method of the present invention in generating three-dimensional character models under different virtual scenes and lighting conditions.

[0134] Experimental steps:

[0135] Virtual scene design: Design different virtual scenes, including lighting intensity, material properties, and background environment. Scenes include bright urban environments, dim night scenes, and virtual rooms with dynamic light sources.

[0136] Method 1 (traditional method): Use traditional 3D modeling tools to generate models and manually adjust the lighting and materials in the scene.

[0137] Method 2 (method of the present invention): Use the method of the present invention to generate a three-dimensional character model, and apply environmental perception technology to automatically adjust the color and material of the character model to adapt it to different virtual environments.

[0138] Evaluation indicators:

[0139] Adaptability: Compare the visual effects of the generated 3D font models in different scenarios, including how the model's color, gloss, and reflection properties adapt to environmental changes.

[0140] Experimental results:

[0141] Traditional methods: In different scenarios, the 3D character models generated by traditional methods have poor adaptability to changes in lighting and materials. The generated models are prone to produce inconsistent effects with the environment in complex backgrounds.

[0142] The method of the present invention: the generated three-dimensional character model can automatically adjust its color, glossiness and reflection properties according to the lighting, color and background in the virtual environment, ensuring a high degree of integration between the model and the environment.

[0143]

[0144]

[0145] The experimental data comparison in Table 3 clearly demonstrates that the proposed method demonstrates significant advantages over traditional methods in terms of environmental adaptability, adaptive adjustment speed, and detail rendering. This is particularly evident in its adaptability to changing lighting conditions, dynamic light source changes, and diverse virtual scenarios. Based on environmental perception technology and automatic lighting adjustment, the proposed method generates more realistic and natural 3D character models, offering greater flexibility and broad adaptability, making it particularly suitable for applications in advertising design, virtual reality, augmented reality, and other fields.

[0146] in conclusion:

[0147] Lighting adaptability and detail expression: The method of the present invention ensures higher visual quality under different lighting conditions by dynamically adjusting texture, gloss and reflection effects, improves texture clarity and reflection effects, and has significant advantages in multi-view consistency.

[0148] Generation speed: The method of the present invention significantly improves the speed of generating three-dimensional character models. Compared with traditional methods, the efficiency is improved by about 70%-80%, and the generation of complex models can be completed more quickly.

[0149] Environmental adaptability: Through environmental perception and adaptive adjustment, the method of the present invention enables the three-dimensional character model to quickly respond to changes in lighting, color and material in the virtual environment, demonstrating stronger environmental adaptability.

[0150] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for generating a three-dimensional landscape character model, characterized in that: The method comprises the following steps: Step 1: Provide input text style information; Step 2: Analyze the text style information using an artificial intelligence algorithm to extract text style features; Step 3: Automatically generate a three-dimensional matrix model based on the text style features; Step 4: Using polygonal modeling technology to perform preliminary modeling on the three-dimensional matrix; Step 5: Applying a surface modeling method to the polygonal modeling result to generate a smooth surface; Step 6: Mapping and enhancing the detail texture of the three-dimensional base model through a deep neural network; Step 7: Using ray tracing technology to simulate the light and shadow of the three-dimensional matrix model under different lighting conditions; Step 8: Automatically adjust the color, material, and reflection properties of the three-dimensional character model through environmental perception technology to make it blend with the lighting conditions and environment in the virtual scene; The text style information includes font, thickness, curve and appearance features. The text style features are parsed by a deep convolutional neural network, and the obtained text style features are used to construct a three-dimensional matrix model; The environmental perception technology automatically adjusts the color, reflectivity and glossiness of the three-dimensional font model to make it consistent with the surrounding environment by real-time perception of the light distribution, color distribution and material properties in the virtual scene.

2. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The three-dimensional matrix model is generated by polygonal modeling technology, specifically including meshing the text outline information and using surface fitting technology to smoothly optimize the generated polygonal model, and finally generating a three-dimensional font model.

3. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The three-dimensional matrix model is generated by polygonal modeling technology, specifically including meshing the text outline information and using surface fitting technology to smoothly optimize the generated polygonal model, and finally generating a three-dimensional font model.

4. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The ray tracing technology is used to simulate reflection, refraction and diffuse reflection phenomena under lighting conditions.

5. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The detail enhancement of the three-dimensional character model is performed through a deep convolutional neural network, specifically including multi-scale learning of the surface texture of the letters, thereby enhancing the performance of the letter edges, surface gloss and material.

6. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The method further includes performing multi-view rendering on the generated three-dimensional landscape character model, and verifying the consistency of the rendering results at different viewpoints using mean square error.

7. The method for generating a three-dimensional landscape character model according to claim 1, wherein: The method is applicable to advertising design, virtual scene modeling, augmented reality and virtual reality application scenarios. In these scenarios, the three-dimensional character model can be adaptively adjusted according to changes in different environments.

8. A computer-readable storage medium having program code stored thereon, characterized in that: When the program code is executed, the method for generating a three-dimensional landscape character model according to any one of claims 1 to 7 can be implemented.

Images