Anti-aliasing optimization method for image rendering and related equipment thereof

By using multi-level asymptotic texture resolution downsampling and 3D rendering model matching technology, the jagged edge effect in 3D graphics rendering is solved, improving the smoothness and visual effect of the image.

CN119027567APending Publication Date: 2024-11-26PING AN TECH (SHENZHEN) CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411179514.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In current 3D graphics rendering, the jagged edges reduce the realism and visual appeal of the image, thus affecting the user experience.

Method used

A multi-level Gaussian texture map is generated by using a resolution downsampling technique with multi-level asymptotic textures. A 3D rendering model is trained for each resolution level, and the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed for image rendering.

Benefits of technology

It significantly improves the flexibility and adaptability of image rendering, reduces jagged edges during the rendering process, and enhances image edge smoothness and overall image quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027567A_ABST
    Figure CN119027567A_ABST
Patent Text Reader

Abstract

The invention discloses an anti-aliasing optimization method for image rendering and related equipment thereof, and belongs to the technical field of artificial intelligence. The method comprises the following steps: firstly, aiming at a preset Gaussian texture map, generating a multi-level Gaussian texture map by adopting a resolution degradation sampling technology of a multi-level gradually-distant texture principle so as to adapt to rendering requirements of different precisions; and then, for the Gaussian texture map of each resolution level, independently training a corresponding 3D rendering model to ensure that the model can accurately match and optimize the image details of the resolution level. When an actual image is processed, the most suitable 3D rendering model is automatically matched according to the resolution of the to-be-processed image. And finally, performing image rendering on the image by using the matching model, and generating a sawtooth-free 3D image. The invention further relates to the technical field of block chains, and the Gaussian texture map can be stored on block chain nodes. According to the method, the rendering efficiency and quality are effectively improved, and particularly, the anti-aliasing effect for edge and texture details is remarkable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to an anti-aliasing optimization method for image rendering and related equipment. Background Art

[0002] 3D Gaussian Splatting (3DGS for short) is a rasterization technique for real-time radiation field rendering. It simulates Gaussian distribution to describe the light distribution in the scene, thereby achieving high-quality real-time rendering effects. 3DGS has recently attracted much attention for its efficient representation in 3D reconstruction and rendering. Although 3DGS performs well in image processing at high resolutions and has high rendering quality and speed, its performance drops sharply at low resolutions or when the camera is far away. Specifically, when the camera is far away from an object mapped with a 3D Gaussian texture, or the rendering resolution is low, the number of pixels on the screen used to display the 3D Gaussian texture may not be enough to fully represent its original details and smoothness. At this time, relative to the "screen size" of each 3D Gaussian in the real world or at high resolution, the actual pixel size allocated on the screen may be lower than the Nyquist frequency, resulting in unnatural jagged edges on the edges of the image, causing the aliasing effect.

[0003] The aliasing effect in image processing will cause obvious steps or jagged edges on the edge of the image, which not only destroys the smoothness and naturalness of the image, but also affects the overall visual effect and detail presentation of the image. In 3D graphics rendering, the impact of the aliasing effect is particularly obvious, which reduces the realism and viewing quality of the picture and affects the user experience. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose an anti-aliasing optimization method, device, computer equipment and storage medium for image rendering, so as to solve the technical problem that in the existing 3D graphics rendering, the realism and viewing quality of the picture are reduced due to the existence of the anti-aliasing effect, which affects the user experience.

[0005] In order to solve the above technical problems, the embodiment of the present application provides an anti-aliasing optimization method for image rendering, which adopts the following technical solution:

[0006] An anti-aliasing optimization method for image rendering, comprising:

[0007] Obtain a preset original Gaussian texture map, and sample the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels;

[0008] Use the Gaussian texture maps at each resolution level to train the 3D rendering models corresponding to each resolution level.

[0009] Acquire a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions;

[0010] Identify a 3D rendering model that matches the resolution of the image to be processed, and obtain a matching 3D rendering model;

[0011] The image to be processed is rendered using the matching 3D rendering model to obtain a 3D rendered image.

[0012] Furthermore, the steps of sampling the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels specifically include:

[0013] Setting a resolution downsampling standard, wherein the resolution downsampling standard is that the sampling resolution of the next layer is half of the sampling resolution of the previous layer;

[0014] Construct sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard;

[0015] The sampling window of each resolution level is used in turn to slide sample on the original Gaussian texture map to obtain Gaussian texture maps of several resolution levels.

[0016] Furthermore, the step of constructing sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard specifically includes:

[0017] Identify the resolution of the original Gaussian texture map, and use the resolution of the original Gaussian texture map as the maximum sampling window;

[0018] Calculate the minimum sampling window according to the original Gaussian texture map and the resolution downsampling standard;

[0019] Starting from the maximum sampling window, the sampling windows are set in sequence based on the resolution downsampling standard until the minimum sampling window is obtained, thereby obtaining sampling windows of several resolution levels.

[0020] Further, the step of identifying a 3D rendering model that matches the resolution of the image to be processed and obtaining the matching 3D rendering model specifically includes:

[0021] Identify the Gaussian texture mapping object in the image to be processed, and obtain the distance from the Gaussian texture mapping object to the camera to obtain the camera distance;

[0022] Estimating the pixel size of Gaussian texture mapped objects when displayed on screen;

[0023] Calculate the distance-pixel ratio based on the camera distance and pixel size;

[0024] According to the distance-pixel ratio, a 3D rendering model with matching resolution is selected from the 3D rendering models corresponding to each resolution level obtained through training to obtain a matching 3D rendering model.

[0025] Further, the step of identifying a Gaussian texture mapping object in the image to be processed, and obtaining the distance from the Gaussian texture mapping object to the camera to obtain the camera distance specifically includes:

[0026] Construct a three-dimensional space coordinate system, and determine the camera position coordinates in the three-dimensional space coordinate system;

[0027] Identify the Gaussian texture mapping object in the image to be processed, and determine the position coordinates of the Gaussian texture mapping object in the three-dimensional space coordinate system to obtain the object position coordinates;

[0028] The distance from the Gaussian texture mapping object to the camera is calculated based on the camera position coordinates and the object position coordinates to obtain the camera distance.

[0029] Furthermore, the step of evaluating the pixel size of the Gaussian texture mapping object when displayed on the screen specifically includes:

[0030] Obtaining the viewing angle data of the camera, and calculating the display range of the display screen based on the viewing angle data of the camera;

[0031] Use the preset projection matrix to map the Gaussian texture mapping object to the display range of the display screen;

[0032] The screen pixel coordinates of the Gaussian texture mapping object on the display screen are obtained, and the pixel size of the Gaussian texture mapping object when displayed on the screen is calculated based on the screen pixel coordinates.

[0033] Further, according to the distance-pixel ratio, a 3D rendering model with a matching resolution is selected from the 3D rendering models corresponding to each resolution level obtained through training to obtain a matching 3D rendering model, which specifically includes:

[0034] comparing the distance-pixel ratio with a preset ratio threshold;

[0035] When the distance-pixel ratio is greater than a preset ratio threshold, the 3D rendering model corresponding to the high-resolution layer is selected as the matching 3D rendering model;

[0036] When the distance-pixel ratio is less than a preset ratio threshold, the 3D rendering model corresponding to the low-resolution layer is selected as the matching 3D rendering model.

[0037] In order to solve the above technical problems, the embodiment of the present application further provides an anti-aliasing optimization device for image rendering, which adopts the following technical solution:

[0038] An anti-aliasing optimization device for image rendering, comprising:

[0039] A downsampling module is used to obtain a preset original Gaussian texture map, and sample the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels;

[0040] A model training module is used to train the 3D rendering models corresponding to each resolution level using Gaussian texture maps of each resolution level;

[0041] An image acquisition module is used to acquire a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions;

[0042] A rendering matching module, used to identify a 3D rendering model that matches the resolution of the image to be processed, and obtain a matching 3D rendering model;

[0043] The image rendering module is used to perform image rendering on the image to be processed by using the matching 3D rendering model to obtain a 3D rendered image.

[0044] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0045] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the anti-aliasing optimization method for image rendering as described in any one of the above items are implemented.

[0046] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0047] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the anti-aliasing optimization method for image rendering as described in any one of the above.

[0048] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0049] The present application discloses an anti-aliasing optimization method for image rendering and related equipment, and belongs to the field of artificial intelligence technology. First, for a preset Gaussian texture map, a multi-level Gaussian texture map is generated by using a resolution downsampling technique based on the principle of multi-level asymptotic texture to meet the rendering requirements of different precisions. Subsequently, for each Gaussian texture map of each resolution level, the corresponding 3D rendering model is independently trained to ensure that the model can accurately match and optimize the image details of the resolution level. When processing the actual image, the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed. Finally, the image is rendered using the matching model to generate a 3D image without aliasing. The present application generates a multi-level Gaussian texture map by resolution downsampling, and trains a 3D rendering model of the corresponding resolution accordingly, which significantly improves the flexibility and adaptability of image rendering, especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the aliasing phenomenon in the rendering process, and improve the image edge smoothness and overall image quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0052] Figure 2 A flow chart of an embodiment of an anti-aliasing optimization method for image rendering according to the present application is shown;

[0053] Figure 3 A schematic structural diagram of an embodiment of an anti-aliasing optimization device for image rendering according to the present application is shown;

[0054] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0056] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0058] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0059] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0060] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0061] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0062] It should be noted that the anti-aliasing optimization method for image rendering provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the anti-aliasing optimization device for image rendering is generally arranged in the server / terminal device.

[0063] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0064] In view of the aliasing problem existing in the existing 3DGS, the embodiment of the present application uses the idea of ​​multi-level mipmap to improve the 3DGS method. The idea of ​​multi-level mipmap is a technology widely used in graphics rendering, which aims to optimize the display effect of texture maps at different distances, while reducing the rendering burden and improving performance. The basic idea is to form a texture pyramid by pre-generating a series of texture images of different resolutions. The texture image of each level is the result of downsampling the previous level. During the rendering process, according to the distance between the object and the camera, a texture image with a suitable resolution is selected for mapping to achieve the purpose of optimizing the rendering effect and performance.

[0065] The core idea of ​​mipmap is to generate a series of texture images of different resolutions in advance and dynamically select the appropriate texture level for sampling according to the distance between the object and the observer. This can be applied to 3DGS to reduce the jagged artifacts caused by insufficient sampling frequency or changes in rendering parameters by optimizing the mapping process from Gaussian distribution to pixel plane.

[0066] At the same time, during the 3DGS rendering process, lower-resolution textures can be used for areas that are far away or where details are not important, thereby reducing computing and storage requirements, reducing high-resolution texture sampling, and improving rendering efficiency.

[0067] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for optimizing anti-aliasing of image rendering according to the present application. The method for optimizing anti-aliasing of image rendering comprises the following steps:

[0068] S201, obtaining a preset original Gaussian texture map, and sampling the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels;

[0069] Specifically, first, one or more original 3D Gaussian texture maps are required, which can be obtained by simulation, scanning or other methods. These original Gaussian texture maps usually exist in high-resolution form and are used to represent the lighting, reflection and other characteristics of the surface of objects in the scene.

[0070] The idea of ​​multi-level mipmap is used to implement resolution downsampling. The original Gaussian texture map is downsampled by resolution downsampling to obtain a series of texture images from high resolution to low resolution, forming a texture image pyramid structure for subsequent training of 3D rendering models corresponding to each resolution level.

[0071] S202, using the Gaussian texture maps of each resolution level to respectively train the 3D rendering models corresponding to each resolution level;

[0072] Specifically, we use Gaussian texture maps at multiple resolution levels as training data, and train the corresponding 3D rendering models for each resolution level, ensuring that each model can accurately capture and express the texture details at its corresponding resolution level, maintaining the delicate texture of high resolution while optimizing rendering efficiency at low resolution. Through layered training, the system can flexibly respond to different rendering requirements, achieve a balance between rendering quality and performance, and bring users a more delicate and smooth 3D visual experience.

[0073] S203, obtaining a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions;

[0074] Specifically, when an image rendering task is required, by collecting a set of images to be processed containing at least two different resolutions, for example, in medical image analysis, high-resolution CT scan images and low-resolution ultrasound images may be obtained at the same time, such an image set can support a more comprehensive disease assessment. For images to be processed with different resolutions, the system can assign a 3D rendering model of the corresponding resolution to achieve image rendering, and by optimizing the mapping process from Gaussian distribution to pixel plane, reduce the jagged artifacts caused by insufficient sampling frequency or changes in rendering parameters.

[0075] S204, identifying a 3D rendering model that matches the resolution of the image to be processed, and obtaining a matching 3D rendering model;

[0076] Specifically, after obtaining the image set to be processed, the system matches the 3D rendering model with the images of different resolutions contained in the images to be processed. Generally speaking, when the object is far away from the camera or its pixel size on the screen is small, the 3D rendering model corresponding to the Mipmap level with a lower resolution should be selected; when the object is close to the camera or its pixel size on the screen is large, the 3D rendering model corresponding to the Mipmap level with a higher resolution should be selected.

[0077] S205 , performing image rendering on the image to be processed using the matching 3D rendering model to obtain a 3D rendered image.

[0078] Specifically, the system matches 3D rendering models that are adapted to images to be processed with different resolutions, and uses the adapted 3D rendering models for image rendering, which significantly improves the flexibility and adaptability of image rendering and reduces aliasing during the rendering process.

[0079] In the above embodiments, the present application generates a multi-layer Gaussian texture map through resolution downsampling, and trains a 3D rendering model of the corresponding resolution based on it, which significantly improves the flexibility and adaptability of image rendering. Especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the aliasing phenomenon in the rendering process, and improve the smoothness of the image edge and the overall image quality.

[0080] Furthermore, the steps of sampling the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels specifically include:

[0081] Setting a resolution downsampling standard, wherein the resolution downsampling standard is that the sampling resolution of the next layer is half of the sampling resolution of the previous layer;

[0082] Construct sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard;

[0083] The sampling window of each resolution level is used in turn to slide sample on the original Gaussian texture map to obtain Gaussian texture maps of several resolution levels.

[0084] In this embodiment, the resolution downsampling standard is set according to the idea of ​​multi-level asymptotic texture Mipmap, and the rendering engine generates a series of texture images with different resolutions based on the original Gaussian texture according to the set resolution downsampling standard. Among them, texture images with different resolutions can be obtained by sliding sampling, and a series of sampling windows are constructed by the original Gaussian texture map and the resolution downsampling standard to realize sliding sampling. For example, the resolution of the original Gaussian texture map is 1024*1024, and the sampling windows with resolution levels of 1024*1024, 512*512, 256*256, ..., 1*1 can be sequentially obtained according to the resolution downsampling standard, and then these sampling windows are sequentially used to slide sample on the original Gaussian texture map to obtain Gaussian texture maps with several resolution levels. These images are arranged from high to low according to the resolution to form a pyramid shape, in which the resolution of each level of texture image is half of the resolution of the previous level of texture image in both length and width.

[0085] In the above embodiments, the present application effectively improves the efficiency and quality of texture rendering through multi-level mipmap technology, and automatically generates a series of texture images from high resolution to low resolution through a preset resolution downsampling standard to form a pyramid structure, so as to facilitate the subsequent training of 3D rendering models corresponding to each resolution level.

[0086] Furthermore, the step of constructing sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard specifically includes:

[0087] Identify the resolution of the original Gaussian texture map, and use the resolution of the original Gaussian texture map as the maximum sampling window;

[0088] Calculate the minimum sampling window according to the original Gaussian texture map and the resolution downsampling standard;

[0089] Starting from the maximum sampling window, the sampling windows are set in sequence based on the resolution downsampling standard until the minimum sampling window is obtained, thereby obtaining sampling windows of several resolution levels.

[0090] In this embodiment, first, the system identifies the resolution of the original Gaussian texture image and uses it as the basis for the maximum sampling window. Then, according to the preset resolution downsampling standard, the size of the minimum sampling window is calculated and determined. Next, starting from the maximum sampling window, following the principle of halving the resolution step by step, the system sets multiple intermediate sampling windows in sequence, and the resolution of each window is half of the resolution of the previous window until the minimum sampling window is reached.

[0091] Taking the resolution of the original Gaussian texture image of 1024*1024 as an example, the resolution downsampling standard should include a downgrade ratio of 2 each time, that is, each time the resolution is reduced by half in both length and width. According to the preset number of downgrades or the minimum resolution requirement, the downgrade ratio is used to calculate the size of the minimum sampling window, starting from 1024*1024, and the resolution is reduced in sequence until it reaches 1*1 pixel, and 1*1 is the minimum resolution.

[0092] In the above embodiment, the present application sets multiple intermediate sampling windows through the original Gaussian texture map and the resolution downsampling standard. This process ensures the generation of a series of sampling windows with resolutions decreasing from high to low and layer by layer.

[0093] Further, the step of identifying a 3D rendering model that matches the resolution of the image to be processed and obtaining the matching 3D rendering model specifically includes:

[0094] Identify the Gaussian texture mapping object in the image to be processed, and obtain the distance from the Gaussian texture mapping object to the camera to obtain the camera distance;

[0095] Estimating the pixel size of Gaussian texture mapped objects when displayed on screen;

[0096] Calculate the distance-pixel ratio based on the camera distance and pixel size;

[0097] According to the distance-pixel ratio, a 3D rendering model with matching resolution is selected from the 3D rendering models corresponding to each resolution level obtained through training to obtain a matching 3D rendering model.

[0098] In this embodiment, first, the system identifies each Gaussian texture mapping object in the image to be processed, and for each Gaussian texture mapping object, evaluates its distance to the camera and its pixel size on the screen. This can be calculated based on parameters such as the position of the camera, the position of the object, the focal length of the camera, and the screen resolution.

[0099] Based on the distance of the Gaussian texture mapping object from the camera and its pixel size on the screen, the distance-pixel ratio is calculated. According to the distance-pixel ratio, a 3D rendering model with matching resolution is selected from the 3D rendering models corresponding to each resolution level obtained through training to obtain a matching 3D rendering model. Generally speaking, when the object is far away from the camera or its pixel size on the screen is small, a 3D rendering model corresponding to a lower resolution Mipmap level should be selected; when the object is close to the camera or its pixel size on the screen is large, a 3D rendering model corresponding to a higher resolution Mipmap level should be selected.

[0100] In the above embodiments, the present application calculates the distance-pixel ratio by accurately identifying the camera distance and screen pixel size of the Gaussian texture mapping object in the image to be processed, and then intelligently matches the model closest to the actual resolution requirement in the pre-trained 3D rendering model library, thereby effectively improving the accuracy and efficiency of 3D rendering, reducing image distortion or waste of rendering resources caused by resolution mismatch, and optimizing the visual presentation effect and user experience.

[0101] Further, the step of identifying a Gaussian texture mapping object in the image to be processed, and obtaining the distance from the Gaussian texture mapping object to the camera to obtain the camera distance specifically includes:

[0102] Construct a three-dimensional space coordinate system, and determine the camera position coordinates in the three-dimensional space coordinate system;

[0103] Identify the Gaussian texture mapping object in the image to be processed, and determine the position coordinates of the Gaussian texture mapping object in the three-dimensional space coordinate system to obtain the object position coordinates;

[0104] The distance from the Gaussian texture mapping object to the camera is calculated based on the camera position coordinates and the object position coordinates to obtain the camera distance.

[0105] In this embodiment, if the system predetermines the position information of the camera, the system pre-constructs a three-dimensional space coordinate system, obtains the position information of the camera and the object, and obtains the camera position coordinates. Then, the Gaussian texture mapping object in the image to be processed is identified, and the position coordinates of the Gaussian texture mapping object in the same three-dimensional space coordinate system are determined to obtain the object position coordinates, and the distance formula in the three-dimensional space (such as the Euclidean distance formula) is used to calculate the distance between the camera and the object. For example:

[0106]

[0107] Where, is the distance between the camera and the object, (x 1 ,y 1 , z 1 ) is the camera position coordinate, (x 2,y 2 , z 2 ) is the object position coordinate.

[0108] In the above embodiment, the present application constructs a three-dimensional spatial coordinate system to accurately locate the spatial position of the camera and the Gaussian texture mapping object, and then accurately calculates the distance between the two.

[0109] In another embodiment of the present invention, if the system cannot determine the position information of the camera in advance, it is necessary to obtain the distance from the object in the photo to the camera based on the use of reference objects of known sizes. If the photo contains one or more reference objects of known actual sizes (such as objects of standard sizes, average height of people, etc.), then the pixel sizes of these reference objects in the photo can be measured and the principle of similar triangles can be used to estimate the distance from other objects to the camera.

[0110] Furthermore, the step of evaluating the pixel size of the Gaussian texture mapping object when displayed on the screen specifically includes:

[0111] Obtaining the viewing angle data of the camera, and calculating the display range of the display screen based on the viewing angle data of the camera;

[0112] Use the preset projection matrix to map the Gaussian texture mapping object to the display range of the display screen;

[0113] The screen pixel coordinates of the Gaussian texture mapping object on the display screen are obtained, and the pixel size of the Gaussian texture mapping object when displayed on the screen is calculated based on the screen pixel coordinates.

[0114] Estimating the pixel size of an object on the screen requires considering several factors, including the focal length of the camera, the screen resolution, the camera's field of view (FOV), and the distance of the object from the camera.

[0115] In this embodiment, the system calculates the screen height or width corresponding to the camera's field of view data (FOV), that is, the display range of the display screen. The field of view data (FOV) is the angular range of the camera's field of view, usually in degrees. For example, assuming that the screen is square or rectangular, and the resolution of the screen is (such as 1920x1080), the system can calculate the height or width of the screen within the FOV based on the FOV and the aspect ratio of the screen.

[0116] In 3D graphics, a projection matrix (such as a perspective projection matrix) is often used to map points in a 3D scene onto a 2D screen. The projection matrix takes into account factors such as the position, orientation, focal length, and viewing angle of the camera. By multiplying the position of the object by the projection matrix, the coordinates of the object on the screen can be obtained. Finally, the system obtains the screen pixel coordinates of the Gaussian texture mapping object on the display screen, and calculates the pixel size of the Gaussian texture mapping object when it is displayed on the screen based on the screen pixel coordinates.

[0117] In the above embodiments, the present application obtains the camera viewing angle data and combines it with a preset projection matrix to accurately map the Gaussian texture mapping object to the screen display range and accurately calculates the pixel size of the Gaussian texture mapping object on the screen.

[0118] Further, according to the distance-pixel ratio, a 3D rendering model with a matching resolution is selected from the 3D rendering models corresponding to each resolution level obtained through training to obtain a matching 3D rendering model, which specifically includes:

[0119] comparing the distance-pixel ratio with a preset ratio threshold;

[0120] When the distance-pixel ratio is greater than a preset ratio threshold, the 3D rendering model corresponding to the high-resolution layer is selected as the matching 3D rendering model;

[0121] When the distance-pixel ratio is less than a preset ratio threshold, the 3D rendering model corresponding to the low-resolution layer is selected as the matching 3D rendering model.

[0122] In this embodiment, the system realizes dynamic matching and optimization of the resolution of the 3D rendering model by intelligently analyzing the relationship between the distance-pixel ratio and the preset threshold. Through this mechanism, the system can automatically adjust the resolution level of the rendering model according to the actual distance between the observer and the object. During the rendering process, the rendering engine will select the appropriate texture level for mapping based on the distance between the object and the camera and the correspondence between the screen pixels and the texture pixels. When the object is far away from the camera, a lower resolution texture is used; when the object is close to the camera, a higher resolution texture is used. When the distance is far and the pixel detail requirements are low, a low-resolution model is selected to reduce the computational burden; when the distance is close and the detail requirements are increased, it is switched to a high-resolution model to enhance the visual realism.

[0123] In the above embodiments, the present application dynamically adjusts the strategy to match the corresponding 3D rendering model, which not only improves the rendering efficiency, but also ensures the real-time optimization of the rendering quality, effectively reduces the jagged phenomenon in the rendering process, improves the image edge smoothness and overall picture quality, and provides users with a smoother and more immersive 3D visual experience.

[0124] In order to improve rendering efficiency, a cache mechanism can be introduced to store the most recently used Mipmap levels and texture sampling results. In this way, when rendering adjacent frames or adjacent objects, the required texture data can be quickly obtained, reducing repeated calculations and storage requirements.

[0125] In addition, according to the dynamic changes of objects (such as position, size, shape, etc.) and changes in camera parameters (such as focal length, viewing angle, etc.) during the rendering process, the selection of Mipmap levels and texture mapping parameters are dynamically adjusted to ensure that the rendering results always maintain high quality and efficiency.

[0126] In the above embodiments, the present application discloses an anti-aliasing optimization method for image rendering, which belongs to the field of artificial intelligence technology. First, for a preset Gaussian texture map, a multi-level Gaussian texture map is generated by using a resolution downsampling technique based on a multi-level asymptotic texture principle to meet rendering requirements of different precisions. Subsequently, for each Gaussian texture map of a resolution level, a corresponding 3D rendering model is independently trained to ensure that the model can accurately match and optimize the image details of the resolution level. When processing an actual image, the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed. Finally, the image is rendered using the matching model to generate a 3D image without aliasing. The present application generates a multi-level Gaussian texture map by resolution downsampling, and trains a 3D rendering model of the corresponding resolution accordingly, which significantly improves the flexibility and adaptability of image rendering, especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the aliasing phenomenon in the rendering process, and improve the image edge smoothness and overall image quality.

[0127] In this embodiment, the anti-aliasing optimization method for image rendering is executed on an electronic device (eg Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0128] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned Gaussian texture map information, the above-mentioned Gaussian texture map information can also be stored in a node of a blockchain.

[0129] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0130] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0131] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0132] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0133] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0134] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an anti-aliasing optimization device for image rendering. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0135] like Figure 3 As shown, the anti-aliasing optimization device 300 for image rendering described in this embodiment includes:

[0136] The downsampling module 301 is used to obtain a preset original Gaussian texture map, and sample the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels;

[0137] A model training module 302 is used to use the Gaussian texture images of each resolution level to train the 3D rendering models corresponding to each resolution level;

[0138] The image acquisition module 303 is used to acquire a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions;

[0139] A rendering matching module 304 is used to identify a 3D rendering model that matches the resolution of the image to be processed, and obtain a matching 3D rendering model;

[0140] The image rendering module 305 is used to perform image rendering on the image to be processed using the matching 3D rendering model to obtain a 3D rendered image.

[0141] Furthermore, the downsampling module 301 is specifically used for:

[0142] A resolution downsampling standard is set, wherein the resolution of the next layer of sampling is half of the previous layer of sampling resolution; sampling windows of several resolution levels are constructed based on the original Gaussian texture map and the resolution downsampling standard; and the sampling window of each resolution level is used in turn to slide sample on the original Gaussian texture map to obtain Gaussian texture maps of several resolution levels.

[0143] Furthermore, the downsampling module 301 is further used for:

[0144] Identify the resolution of the original Gaussian texture map, and use the resolution of the original Gaussian texture map as the maximum sampling window; calculate the minimum sampling window based on the original Gaussian texture map and the resolution downsampling standard; starting from the maximum sampling window, set the sampling windows in sequence based on the resolution downsampling standard until the minimum sampling window is obtained, and obtain sampling windows of several resolution levels.

[0145] Furthermore, the rendering matching module 304 is specifically used for:

[0146] Identify the Gaussian texture mapping object in the image to be processed, and obtain the distance from the Gaussian texture mapping object to the camera to obtain the camera distance; evaluate the pixel size of the Gaussian texture mapping object when displayed on the screen; calculate the distance-pixel ratio based on the camera distance and the pixel size; according to the distance-pixel ratio, select a 3D rendering model with matching resolution from the 3D rendering models corresponding to each resolution level obtained by training to obtain a matching 3D rendering model.

[0147] Furthermore, the rendering matching module 304 is further used for:

[0148] Construct a three-dimensional space coordinate system and determine the camera position coordinates in the three-dimensional space coordinate system; identify the Gaussian texture mapping object in the image to be processed, and determine the position coordinates of the Gaussian texture mapping object in the three-dimensional space coordinate system to obtain the object position coordinates; calculate the distance from the Gaussian texture mapping object to the camera based on the camera position coordinates and the object position coordinates to obtain the camera distance.

[0149] Furthermore, the rendering matching module 304 is further used for:

[0150] Obtain the viewing angle data of the camera, and calculate the display range of the display screen based on the viewing angle data of the camera; use a preset projection matrix to map the Gaussian texture mapping object to the display range of the display screen; obtain the screen pixel coordinates of the Gaussian texture mapping object on the display screen, and calculate the pixel size of the Gaussian texture mapping object when displayed on the screen based on the screen pixel coordinates.

[0151] Furthermore, the rendering matching module 304 is also used for:

[0152] comparing the distance-pixel ratio with a preset ratio threshold;

[0153] When the distance-pixel ratio is greater than a preset ratio threshold, the 3D rendering model corresponding to the high-resolution layer is selected as the matching 3D rendering model;

[0154] When the distance-pixel ratio is less than a preset ratio threshold, the 3D rendering model corresponding to the low-resolution layer is selected as the matching 3D rendering model.

[0155] In the above embodiments, the present application discloses an anti-aliasing optimization device for image rendering, which belongs to the field of artificial intelligence technology. First, for a preset Gaussian texture map, a multi-level Gaussian texture map is generated by using a resolution downsampling technique based on a multi-level asymptotic texture principle to meet rendering requirements of different precisions. Subsequently, for each Gaussian texture map of a resolution level, a corresponding 3D rendering model is independently trained to ensure that the model can accurately match and optimize the image details of the resolution level. When processing an actual image, the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed. Finally, the image is rendered using the matching model to generate a 3D image without aliasing. The present application generates a multi-level Gaussian texture map by resolution downsampling, and trains a 3D rendering model of the corresponding resolution accordingly, which significantly improves the flexibility and adaptability of image rendering, especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the aliasing phenomenon in the rendering process, and improve the image edge smoothness and overall image quality.

[0156] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0157] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0158] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0159] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the X method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0160] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the anti-aliasing optimization method for image rendering.

[0161] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0162] In the above embodiment, the present application discloses a computer device, which belongs to the field of artificial intelligence technology. First, for a preset Gaussian texture map, a multi-level Gaussian texture map is generated by using a resolution downsampling technique based on a multi-level asymptotic texture principle to meet rendering requirements of different precisions. Subsequently, for each Gaussian texture map of a resolution level, a corresponding 3D rendering model is independently trained to ensure that the model can accurately match and optimize the image details of the resolution level. When processing an actual image, the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed. Finally, the image is rendered using the matching model to generate a 3D image without aliasing. The present application generates a multi-level Gaussian texture map by resolution downsampling, and trains a 3D rendering model of the corresponding resolution accordingly, which significantly improves the flexibility and adaptability of image rendering, especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the aliasing phenomenon in the rendering process, and improve the image edge smoothness and overall image quality.

[0163] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the anti-aliasing optimization method for image rendering as described above.

[0164] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of artificial intelligence technology. First, for a preset Gaussian texture map, a multi-level Gaussian texture map is generated by using a resolution downsampling technique based on a multi-level asymptotic texture principle to meet rendering requirements of different precisions. Subsequently, for each Gaussian texture map of a resolution level, a corresponding 3D rendering model is independently trained to ensure that the model can accurately match and optimize the image details of the resolution level. When processing an actual image, the most suitable 3D rendering model is automatically matched according to the resolution of the image to be processed. Finally, the image is rendered using the matching model to generate a 3D image without jagged edges. The present application generates a multi-level Gaussian texture map by resolution downsampling, and trains a 3D rendering model of the corresponding resolution accordingly, which significantly improves the flexibility and adaptability of image rendering, especially when processing multi-resolution images, it can automatically match the rendering model of the optimal resolution, effectively reduce the jagged phenomenon in the rendering process, and improve the image edge smoothness and overall image quality.

[0165] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0166] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An anti-aliasing optimization method for image rendering, It is characterized in that include: Obtain a preset original Gaussian texture map, and sample the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels; Use the Gaussian texture maps of each resolution level to respectively train the 3D rendering models corresponding to each resolution level; Acquire a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions; Identifying a 3D rendering model that matches the resolution of the image to be processed, and obtaining a matching 3D rendering model; The image to be processed is rendered using the matching 3D rendering model to obtain a 3D rendered image.

2. The anti-aliasing optimization method for image rendering according to claim 1, It is characterized in that The step of sampling the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels specifically includes: Setting a resolution downsampling standard, wherein the resolution downsampling standard is that the sampling resolution of the next layer is half of the sampling resolution of the previous layer; Constructing sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard; The sampling window of each resolution level is used in turn to perform sliding sampling on the original Gaussian texture map to obtain Gaussian texture maps of several resolution levels.

3. The anti-aliasing optimization method for image rendering according to claim 2, It is characterized in that The step of constructing sampling windows of several resolution levels based on the original Gaussian texture map and the resolution downsampling standard specifically includes: Identify the resolution of the original Gaussian texture map, and use the resolution of the original Gaussian texture map as the maximum sampling window; Calculate a minimum sampling window according to the original Gaussian texture map and the resolution downsampling standard; Starting from the maximum sampling window, sampling windows are set in sequence based on the resolution downsampling standard until the minimum sampling window is obtained, thereby obtaining sampling windows of several resolution levels.

4. The anti-aliasing optimization method for image rendering according to claim 1, It is characterized in that The step of identifying a 3D rendering model that matches the resolution of the image to be processed and obtaining the matching 3D rendering model specifically includes: Identify a Gaussian texture mapping object in the image to be processed, and obtain a distance from the Gaussian texture mapping object to a camera to obtain a camera distance; Evaluating the pixel size of the Gaussian texture mapping object when displayed on a screen; Calculating a distance-pixel ratio based on the imaging distance and the pixel size; According to the distance-pixel ratio, a 3D rendering model with matching resolution is selected from the 3D rendering models corresponding to each of the resolution levels obtained through training to obtain the matching 3D rendering model.

5. The anti-aliasing optimization method for image rendering according to claim 4, It is characterized in that The step of identifying the Gaussian texture mapping object in the image to be processed, and obtaining the distance from the Gaussian texture mapping object to the camera to obtain the camera distance specifically includes: Constructing a three-dimensional space coordinate system, and determining the camera position coordinates in the three-dimensional space coordinate system; Identify a Gaussian texture mapping object in the image to be processed, and determine the position coordinates of the Gaussian texture mapping object in the three-dimensional space coordinate system to obtain the object position coordinates; The distance from the Gaussian texture mapping object to the camera is calculated based on the camera position coordinates and the object position coordinates to obtain the camera distance.

6. The anti-aliasing optimization method for image rendering according to claim 4, It is characterized in that The step of evaluating the pixel size of the Gaussian texture mapping object when displayed on the screen specifically includes: Acquiring viewing angle data of the camera, and calculating a display range of a display screen based on the viewing angle data of the camera; Mapping the Gaussian texture mapping object to the display range of the display screen using a preset projection matrix; The screen pixel coordinates of the Gaussian texture mapping object on the display screen are obtained, and the pixel size of the Gaussian texture mapping object when displayed on the screen is calculated based on the screen pixel coordinates.

7. The anti-aliasing optimization method for image rendering according to claim 4, It is characterized in that The step of selecting a 3D rendering model with matching resolution from the 3D rendering models corresponding to each of the resolution levels obtained through training according to the distance-pixel ratio to obtain the matching 3D rendering model specifically includes: comparing the distance-pixel ratio with a preset ratio threshold; When the distance-pixel ratio is greater than a preset ratio threshold, selecting a 3D rendering model corresponding to a high-resolution layer as the matching 3D rendering model; When the distance-pixel ratio is less than a preset ratio threshold, the 3D rendering model corresponding to the low-resolution layer is selected as the matching 3D rendering model. 8.An anti-aliasing optimization device for image rendering, It is characterized in that include: A downsampling module is used to obtain a preset original Gaussian texture map, and sample the original Gaussian texture map by resolution downsampling to obtain Gaussian texture maps of several resolution levels; A model training module, used to use the Gaussian texture maps of each resolution level to respectively train the 3D rendering models corresponding to each resolution level; An image acquisition module, used to acquire a set of images to be processed, wherein the set of images to be processed includes at least two images to be processed with different resolutions; A rendering matching module, used to identify a 3D rendering model that matches the resolution of the image to be processed, and obtain a matching 3D rendering model; An image rendering module is used to perform image rendering on the image to be processed using the matching 3D rendering model to obtain a 3D rendered image.

9. A computer device, It is characterized in that The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the anti-aliasing optimization method for image rendering as claimed in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the anti-aliasing optimization method for image rendering according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Image rendering method and electronic equipment

    CN120259513A

  • Texture fitting mode, device and equipment and computer readable storage medium

    CN121505130A