Rendering Quality Evaluation Method, Device, Computer Equipment and Medium

Abstract

The embodiments of the present application belong to the technical field of computer graphics, and relate to a rendering quality evaluation method, device, computer device and its medium. The method includes obtaining a reference pseudo-color map of a scene image, obtaining a rendered image of the scene image according to the reference pseudo-color map and preset rendering engine information, converting the rendered image into a pseudo-color map, calculating a similarity value between the pseudo-color map and the reference pseudo-color map, and evaluating the rendering quality of the rendered image according to the similarity value. That is, since the pseudo-color map is generated based on the rendered image, the quality of the pseudo-color map reflects the quality of the rendering engine, and the reference pseudo-color map is used as a reference index for the quality of the rendering engine. By comparing the similarity between the pseudo-color map and the reference pseudo-color map, that is, by judging the size of the difference between the two to determine the rendering quality, the quality of the rendering engine can be quickly verified, and thus the efficiency of rendering image quality evaluation is improved.

Description

Technical Field

[0001] This application relates to the field of computer graphics technology, and particularly to a method and device for evaluating rendering quality, a computer device, and a medium thereof. Background Art

[0002] A rendered image refers to rendering a scene image by adjusting parameters such as light, color, and angle, so that the generated scene image can vividly display the rendered design effect. In a graphics pipeline, rendering is the last important step, through which the final display effect of a 3D model and animation is obtained. A rendered image is generally implemented through a selected rendering engine, and the quality of the rendering engine determines the quality of the rendered image.

[0003] Since the content of a rendered image is relatively complex, directly comparing the rendered images of different rendering engines requires higher and more cumbersome technology, greatly reducing the efficiency of evaluating the quality of rendered images. Summary of the Invention

[0004] The purpose of the embodiments of this application is to propose a method and device for evaluating rendering quality, a computer device, and a medium thereof, to solve the problem of low efficiency in evaluating the quality of rendered images.

[0005] To solve the above technical problem, an embodiment of this application provides a method for evaluating rendering quality, including:

[0006] Obtaining a reference pseudo-color map of a scene image;

[0007] Obtaining a rendered image of the scene image according to the reference pseudo-color map and preset rendering engine information;

[0008] Converting the rendered image into a pseudo-color map;

[0009] Calculating a similarity value between the pseudo-color map and the reference pseudo-color map;

[0010] Evaluating the rendering quality of the rendered image according to the similarity value.

[0011] To solve the above technical problem, an embodiment of this application also provides a device for evaluating rendering quality, including:

[0012] An obtaining module, configured to obtain a reference pseudo-color map of a scene image;

[0013] A rendering module, configured to obtain a rendered image of the scene image according to the reference pseudo-color map and preset rendering engine information;

[0014] A conversion module, configured to convert the rendered image into a pseudo-color map;

[0015] A calculation module, configured to calculate a similarity value between the pseudo-color map and the reference pseudo-color map;

[0016] An evaluation module for evaluating the rendering quality of the rendered image according to the similarity value.

[0017] To solve the above technical problems, an embodiment of the present application further provides a computer device, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of the above rendering quality evaluation method are implemented.

[0018] To solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above rendering quality evaluation method are implemented.

[0019] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects:

[0020] By obtaining the reference pseudo-color map of the scene image, obtaining the rendered image of the scene image according to the reference pseudo-color map and the preset rendering engine information, converting the rendered image into a pseudo-color map, calculating the similarity value between the pseudo-color map and the reference pseudo-color map, and evaluating the rendering quality of the rendered image according to the similarity value. That is, since the pseudo-color map is generated according to the rendered image, the quality of the pseudo-color map reflects the quality of the rendering engine, and the reference pseudo-color map is used as a reference index for the quality of the rendering engine. By comparing the similarity between the pseudo-color map and the reference pseudo-color map, that is, by judging the difference between the two to determine the rendering quality, the quality of the rendering engine can be quickly verified, and thus the efficiency of evaluating the rendering image quality is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] To more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the following described drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 is an exemplary system architecture diagram to which the present application can be applied;

[0023] Figure 2 is a flowchart of an embodiment of the rendering quality evaluation method of the present application;

[0024] Figure 3a is a schematic diagram of an embodiment of the pseudo-color map of the present application;

[0025] Figure 3b is a schematic diagram of an embodiment of the reference pseudo-color map of the present application;

[0026] Figure 4It is an overall schematic diagram of the rendering quality evaluation method of this application;

[0027] Figure 5 It is a schematic diagram of an embodiment of the rendering quality evaluation device of this application;

[0028] Figure 6 It is a basic structural block diagram of the computer device of this application. Detailed implementation manners

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0030] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0031] To enable those skilled in the technical field to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the drawings.

[0032] Based on this, this application provides a rendering quality evaluation method to solve the above technical problems.

[0033] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0034] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0035] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0036] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0037] It should be noted that the rendering quality assessment method provided in the embodiment of the present application is executed by a server / terminal device, and accordingly, the rendering quality assessment device is generally arranged in the server / terminal device.

[0038] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0039] Continue to refer Figure 2 , Figure 2 A flowchart of an embodiment of a rendering quality assessment method includes:

[0040] S201: Obtain a reference pseudo-color image of a scene image.

[0041] Specifically, for interior decoration design, a pseudo-color image can be used to visualize the brightness and temperature of indoor lights to reflect the indoor effects brought by the indoor lighting design. Among them, a pseudo-color image is a special digital image processing technology that converts grayscale images into full-color color images. The principle is to use the grayscale (brightness) in the original image to infer the color in the initial original color image. That is, the pseudo-color image is converted from the rendered image and is a color-reflecting data image, which is often used in temperature and light diagrams. Therefore, the quality of the pseudo-color image reflects the quality of the rendering engine.

[0042] It should be noted that since DIALux is a lighting design software, its lighting design effect is already very mature and belongs to the top level in the industry. Moreover, the method and technology for generating false color maps by it cannot be replicated by others. In the embodiments of the present application, DIALux is used to render the scene image. For example, one or several IES (Infrastructure Enabling System) light sources are added to the set position of the scene image for rendering, and the corresponding reference false color map is extracted from the rendered image to be used as the reference false color map for subsequent reference and comparison in the embodiments of the present application. Among them, the set position can be, for example, the background wall position, the corner position or the ceiling position of the living room, etc.

[0043] Among them, the scene image can be a household type scene image. For example, it can be spatial images such as a living room image, a kitchen image and a master bedroom image, etc., and there is no limitation here. The way to obtain the scene image can be that the user uploads it through a client terminal (such as a computer, a tablet computer, a mobile phone, etc.), or uploads it through Bluetooth, WiFi or a local area network, etc., or obtains it by modeling with modeling software. There is no limitation on the obtaining method in the embodiments of the present application.

[0044] S202: Obtain the rendered image of the scene image according to the reference false color map and the preset rendering engine information.

[0045] Specifically, the scene image is rendered according to the set position and IES light source corresponding to the reference false color map, and the preset rendering engine information, so that the generated rendered image includes the same position and light source as the reference false color map. Among them, the rendering engine information includes the currently selected rendering engine version, and different rendering engine versions have different rendering effects on the scene image.

[0046] For example, the same scene image is used to build living room scene images of the same size in the set rendering engine version and DIALux respectively, and the same one or several IES light sources are added to the same ceiling position of the living room to generate the rendered image under the rendering of the rendering engine version and the rendered image under the rendering of DIALux respectively.

[0047] In some embodiments, obtaining the rendered image of the scene image according to the reference false color map and the preset rendering engine information includes:

[0048] Obtain the configuration data of the reference false color map;

[0049] Generate an illuminance file according to the configuration data and the rendering engine information;

[0050] Render the scene image according to the illuminance file and the preset fitting algorithm to obtain the rendered image.

[0051] Among them, the configuration data is obtained from a configuration file, which can be of types such as xml files, txt files, and config files. The configuration data is used to configure the rendering data used for rendering, such as rendering models, texture maps, lighting information, camera parameters, and so on.

[0052] Furthermore, the benchmark pseudo-color map generated by DIALux rendering is parsed and extracted to obtain configuration data from the configuration file of the benchmark pseudo-color map. For example, configuration data such as the IES light source corresponding to each position of the benchmark pseudo-color map and the lighting data corresponding to the IES light source are obtained from the configuration file where DIALux is located. According to the configuration data of the benchmark pseudo-color map, the configuration data required for rendering is obtained from the configuration file where the pre-stored rendering engine information is located, that is, the rendering configuration data, and the rendering configuration data is modified according to the configuration data of the benchmark pseudo-color map.

[0053] Specifically, according to the configuration data of the benchmark pseudo-color map, the configuration file where the rendering configuration data is located is parsed to obtain the IES file path used for rendering. According to the IES file path, the lighting data and camera parameters used in the same configuration data as the benchmark pseudo-color map are downloaded, and the maximum luminous flux value of the lighting data is parsed and the camera parameters are adjusted. Among them, the way to parse the maximum luminous flux value can be to multiply the luminous flux value of the lighting data by a preset coefficient. For example, the result of multiplying the luminous flux value of the lighting data by the coefficient 10 is used as the maximum luminous flux. Adjusting the camera parameters means making the camera view angle in the rendering engine information consistent with the camera view angle in DIALux.

[0054] Furthermore, the obtained maximum luminous flux value and camera parameters are modified in the configuration file where the rendering configuration data is located, and the configuration file where the modified rendering configuration data is located is used to generate a corresponding illuminance file, that is, an HDR file (High-Dynamic Range, dynamic lighting rendering) through the set current rendering engine information. The HDR file can provide more dynamic range and image details. According to LDR (Low-Dynamic Range) images with different exposure times, the LDR images corresponding to the best details for each exposure time are used to synthesize the final rendered image, which can better reflect the visual effect in the real environment.

[0055] In an embodiment of the present application, the configuration data of a reference pseudo-color map can be used to modify the configuration files of multiple different versions of rendering engine information, that is, different illumination files are generated according to the same configuration data and different versions of rendering engine information, so that the rendering quality of the same scene image by different rendering engine information can be compared simultaneously. The rendered image generated by converting the HDR file and the rendering engine information can be used to show whether the lighting design tool used in the scene image is close to the real lighting effect. The closer the lighting effect is to the real one, the better the rendering engine quality of the rendering engine information.

[0056] In an embodiment of the present application, the rendered image generated by converting the HDR file and the rendering engine information includes rendering the scene image using a preset fitting algorithm, that is, the preset fitting algorithm is used to make the generated rendered image approximate the scene image rendered by DIALux, which is convenient for subsequent comparison of the pseudo-color map and the reference pseudo-color map in the rendered image, making the comparison referable. Among them, the preset fitting algorithm can be a polynomial fitting algorithm, such as an interpolation algorithm for scale transformation, a weighted average method for image enhancement, a filtering algorithm, and a fitting algorithm such as a texture wrapping method, which is not limited here. Therefore, by rendering the scene image with the illumination file and the preset fitting algorithm, the rendered image corresponding to the selected rendering engine information can be generated, that is, the obtained rendered image is consistent with the position and light source set by the reference pseudo-color map, improving the accuracy of comparing the pixel value differences between the pseudo-color map of the rendered image corresponding to different rendering engine information and the reference pseudo-color map at the same position, and at the same time realizing a quick comparison of the rendering engine quality.

[0057] In some embodiments, rendering the scene image according to the illumination file and the preset fitting algorithm to obtain a rendered image includes:

[0058] Extracting the rendering data in the illumination file;

[0059] Rendering the scene image through at least one fitting algorithm according to the rendering data to generate at least one rendered image.

[0060] Reading the rendering data from the illumination file. The rendering data can be the luminous flux in the light data, that is, the illumination value in the rendered image. The RGB value of each pixel point in the scene image is modified through the polynomial fitting algorithm and the illumination value, so that the rendering effect of the generated rendered image approximates the rendering effect of DIALux. Among them, the fitting algorithm can be understood as a quadratic function. According to the different coefficients of the quadratic function, the rendered results achieved are also different. Therefore, the selection of the fitting algorithm generally only needs to approximate the rendering effect of DIALux, and different fitting algorithms can quickly verify the differences in the rendering effects brought by different fitting algorithms.

[0061] Further, since different illuminance files come from different rendering engine information, appropriate fitting algorithms can be selected according to different illuminance files, so as to generate at least one rendering image approximating the rendering effect of DIALux corresponding to the same rendering data at the same time, that is, obtain rendering images with different rendering effects generated by different versions of rendering engine information, improve the generation efficiency of rendering images, and facilitate subsequent comparison of false color maps of different rendering engine information at the same position pixel points.

[0062] S203: Convert the rendering image into a false color map.

[0063] In some embodiments, converting the rendering image into a false color map includes:

[0064] Convert the number of channels in the rendering image into a single channel to generate a false color map.

[0065] In the embodiments of the present application, the rendering image is a three-channel color map (RGB map). Convert the three channels in the rendering image into a single-channel grayscale map, and thus convert it into a false color map for output. Among them, the single-channel grayscale map has only one value for each pixel point to represent the color, and the pixel value is between 0 and 255.

[0066] In some embodiments, the method of converting the number of channels into a single channel can call python opencv (Open Source Computer Vision Library, a cross-platform computer vision library). As Figure 3a shown, Figure 3a is a schematic diagram of an embodiment of the false color map of the present application.

[0067] Since the false color map is only composed of different colors, compared with the rendering image for comparing the rendering quality, it is simpler to convert the rendering image into a false color map for comparison, that is, the efficiency of comparing the rendering quality is higher.

[0068] S204: Calculate the similarity value between the false color map and the reference false color map.

[0069] Calculating the similarity value is to count the ratio of the number of pixel points in the false color map whose illuminance values meet the reference conditions to the total number of pixel points in the false color map. Among them, the reference conditions include that the difference between the illuminance value of the pixel point in the false color map and the illuminance value of the pixel point of the reference false color map at the same position of the pixel point is less than or equal to a preset illuminance threshold.

[0070] In some embodiments, calculating the similarity value between the false color map and the reference false color map includes:

[0071] Obtain the pixel points of the false color map and the reference pixel points of the reference false color map at the same position;

[0072] Calculate the illuminance difference between a pixel point and a reference pixel point;

[0073] Determine the similarity value between the pseudo-color map and the reference pseudo-color map according to the illuminance difference.

[0074] Among them, the reference pixel point is the pixel point of the reference pseudo-color map. When comparing the pseudo-color map and the reference pseudo-color map, the positions of the same pixel points in the two maps can be traversed in the order from left to right or from top to bottom, and the illuminance values of the same pixel point positions can be read respectively. For example, the illuminance value of the pixel point traversed in the pseudo-color map is used as the first illuminance value, and the illuminance value of the reference pixel point at the same pixel point position as the pseudo-color map is used as the second illuminance value, and the first illuminance value and the second illuminance value are subtracted to obtain the illuminance difference. Since the illuminance difference reflects the rendering similarity between the pseudo-color map and the reference pseudo-color map, that is, the smaller the illuminance difference, the more the rendering quality meets the rendering quality requirements of the reference pseudo-color map. By comparing the illuminance values of the pseudo-color map and the reference pseudo-color map, the rendering quality of the rendering engine can be quickly judged.

[0075] In some embodiments, determining the similarity value between the pseudo-color map and the reference pseudo-color map according to the illuminance difference includes:

[0076] Taking the pixel points with illuminance difference less than the preset illuminance threshold as target pixel points;

[0077] Obtain the number of target pixel points;

[0078] Calculate the ratio of the number of target pixel points to the total number of pixel points in the pseudo-color map, and take the ratio as the similarity value.

[0079] Specifically, the illuminance threshold can be flexibly adjusted according to the requirements of the actual rendering engine. For example, the illuminance threshold can be set to 40. If the illuminance difference is less than the illuminance threshold of 40, it is determined that the pseudo-color map generated by the preset rendering engine information meets the requirements of the reference pseudo-color map, and the pixel points that meet the reference pseudo-color map are used as target pixel points.

[0080] It should be noted that the result obtained by subtracting the first illuminance value and the second illuminance value may be negative. Therefore, the absolute value of the result after the subtraction process needs to be taken, that is, the illuminance difference is a non-negative number.

[0081] Furthermore, in order to better judge the overall rendering quality of the entire pseudo-color map, it is necessary to count the number of target pixel points and the total number of pixel points in the pseudo-color map. The more the number of target pixel points, that is, the larger the ratio of the number of target pixel points to the total number of pixel points, the closer the pseudo-color map is to the reference pseudo-color map, indicating that the rendering effect of the pseudo-color map is closer to the rendering quality requirements of the reference.

[0082] In an embodiment of the present application, the illuminance value of the reference pixel point of the reference pseudo-color map and the illuminance value of the pixel point of the pseudo-color map at the same pixel point position are stored in the same array, and the illuminance difference between the two illuminance values is calculated in the same array. If the illuminance difference is greater than the illuminance threshold, it is considered that the rendering of the pseudo-color map does not meet the expected rendering requirements. By counting the percentage of target pixel points that meet the expectations, the final similarity result is presented, that is, the overall rendering accuracy of the pseudo-color map output by the rendering engine information is evaluated through the similarity value.

[0083] S205: Evaluate the rendering quality of the rendered image according to the similarity value.

[0084] If the obtained illuminance difference is less than the preset illuminance threshold, it indicates that the similarity value between the pseudo-color map and the reference pseudo-color map is very high, that is, the achieved rendering effects are similar and meet the target rendering effect. It can quickly verify the differences in the effects of different polynomial fitting algorithms. According to the configuration information of the reference pseudo-color map, multiple pseudo-color maps corresponding to different versions of the rendering engine information can be generated. By comparing the similarity values obtained by comparing each pseudo-color map with the same reference pseudo-color map, not only can the rendering similarity between the pseudo-color map and the reference pseudo-color map be evaluated, that is, the rendering quality can be quickly evaluated, but also the differences in the rendering effects between different pseudo-color maps can be compared according to the similarity values, thereby helping to improve the comparison method of the rendering effects. At the same time, it can quickly verify the rendering performance of the rendering engine information for different complexity scenarios, such as the scene size, the number of lights, and the light attributes in the house type image, so as to achieve the quality of the pseudo-color map for quick verification.

[0085] By obtaining the reference pseudo-color map of the scene image, according to the reference pseudo-color map and the preset rendering engine information, obtaining the rendered image of the scene image, converting the rendered image into a pseudo-color map, calculating the similarity value between the pseudo-color map and the reference pseudo-color map, and evaluating the rendering quality of the rendered image according to the similarity value. That is, since the pseudo-color map is generated based on the rendered image, the quality of the pseudo-color map reflects the quality of the rendering engine, and the reference pseudo-color map is used as a reference index for the quality of the rendering engine. By comparing the similarity between the pseudo-color map and the reference pseudo-color map, that is, by determining the size of the difference between the two to determine the rendering quality, the quality of the rendering engine is quickly verified, and thus the efficiency of evaluating the quality of the rendered image is improved.

[0086] In some embodiments, Figure 4 is the overall schematic diagram of the rendering quality evaluation method of the present application.

[0087] Specifically, the implementation of the rendering quality assessment can be achieved on a terminal device. For example, an xml file can be pre-stored in the background database of the terminal device, and the configuration data of the stored scene set, as well as the benchmark pseudo-color map of the DIALux scene corresponding to the xml file, can be uploaded from the xml file. Among them, the scene set can be a collection of test cases, and each test case includes different rendering scenes, camera parameters, light source information, etc.

[0088] Furthermore, the background database also includes each rendering version that is uploaded and recorded, as well as a polynomial fitting algorithm. Among them, the polynomial fitting algorithm can be edited and updated on the terminal device according to the actual situation. Generally, editing is to change the coefficients in the polynomial fitting algorithm, or change the quadratic function in the polynomial fitting algorithm to a cubic function or a linear function.

[0089] Furthermore, the user can select the benchmark pseudo-color map and the corresponding configuration information on the terminal device, select a suitable polynomial fitting algorithm and at least one rendering version to be evaluated from the polynomial fitting algorithm, substitute the benchmark pseudo-color map and the corresponding configuration information into the polynomial fitting algorithm and at least one rendering version to generate at least one pseudo-color map, and compare the obtained at least one pseudo-color map with the benchmark pseudo-color map respectively. The comparison can output each comparison result according to the above method of calculating the similarity value, so as to quickly verify the rendering quality of each rendering version.

[0090] Furthermore, by selecting multiple different fitting algorithms to generate different pseudo-color maps of the same rendering version and comparing the generated different pseudo-color maps with the benchmark pseudo-color map, it is possible to quickly verify the differences in the rendering effects produced by different polynomial fitting algorithms on the rendering engine version, that is, by verifying different polynomial fitting algorithms, it is possible to quickly determine the polynomial fitting algorithm that matches the rendering version, so that subsequent rendering versions can generate pseudo-color maps with the best rendering quality in combination with the appropriate polynomial fitting algorithm.

[0091] In some embodiments, before calculating the illuminance difference between the pixel point and the benchmark pixel point, the method further includes:

[0092] Determine the text area from the benchmark pseudo-color map;

[0093] Identify the text area to obtain the illuminance value corresponding to each benchmark pixel point.

[0094] The reference pseudo-color map includes the colors displayed by each reference pixel point and the values represented by the illuminance values in the reference pixel points. Therefore, before comparing the pseudo-color map with the reference pseudo-color map, the text area of the reference pseudo-color map is extracted by the scene text detection algorithm (Efficient and Accuracy Scene Text, EAST), and the illuminance value corresponding to each reference pixel point in the text area is recognized according to the text recognition algorithm (Attentional Scene Text Recognizer with Flexible Rectification, ASTER), so as to reduce the time and labor costs of manually inputting the illuminance values of each reference pixel point in the reference pseudo-color map.

[0095] Furthermore, since the EAST algorithm can detect texts in different directions and sizes and runs fast and efficiently, the recognition efficiency of the illuminance values of the reference pseudo-color map is higher.

[0096] Furthermore, the recognized illuminance values and the positions of the corresponding reference pixel points are bound, and the illuminance values and positions are stored. As Figure 3b is a schematic diagram of an embodiment of the reference pseudo-color map of the present application, which is the illuminance value of each reference pixel point of the obtained reference pseudo-color map.

[0097] In the implementation of the present application, the illuminance value corresponding to each reference pixel point can also be recognized according to the OCR recognition algorithm or the CTPN algorithm that combines the CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory) deep networks. The recognition algorithm for the illuminance value is not limited here.

[0098] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program 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 methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), etc., or a Random Access Memory (RAM), etc.

[0099] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise clearly stated in this document, the execution of these steps has no strict order restriction and 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. 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 alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0100] Further reference is made to Figure 5 , as an implementation of the above Figure 2 shown rendering quality evaluation method, an embodiment schematic diagram of a rendering quality evaluation device is provided in this application. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0101] As Figure 5 shown, the rendering quality evaluation device described in this embodiment includes: an acquisition module 51, a rendering module 52, a conversion module 53, a calculation module 54, and an evaluation module 55. Among them:

[0102] The acquisition module 51 is used to acquire a reference pseudo-color map of the scene image;

[0103] The rendering module 52 is used to acquire a rendered image of the scene image according to the reference pseudo-color map and preset rendering engine information;

[0104] The conversion module 53 is used to convert the rendered image into a pseudo-color map;

[0105] The calculation module 54 is used to calculate the similarity value between the pseudo-color map and the reference pseudo-color map;

[0106] The evaluation module 55 is used to evaluate the rendering quality of the rendered image according to the similarity value.

[0107] In some embodiments, the rendering module 52 includes:

[0108] An acquisition unit 521, used to acquire the configuration data of the reference pseudo-color map;

[0109] A generation unit 522, used to generate an illuminance file according to the configuration data and the rendering engine information;

[0110] A rendering unit 523, used to render the scene image according to the illuminance file and a preset fitting algorithm to obtain a rendered image.

[0111] In some embodiments, the rendering unit 523 includes:

[0112] An extraction subunit 5231, configured to extract rendering data from the illumination file;

[0113] A rendering subunit 5232, configured to render the scene image through at least one fitting algorithm according to the rendering data to generate at least one rendered image.

[0114] In some embodiments, the conversion module 53 includes:

[0115] A conversion unit 531, configured to convert the number of channels in the rendered image into a single channel to generate a pseudocolor map.

[0116] In some embodiments, the calculation module 54 includes:

[0117] A pixel acquisition unit 541, configured to acquire a pixel point of the pseudocolor map and a reference pixel point of the reference pseudocolor map at the same position;

[0118] A difference calculation unit 542, configured to calculate an illumination difference between the pixel point and the reference pixel point;

[0119] A determination unit 543, configured to determine a similarity value between the pseudocolor map and the reference pseudocolor map according to the illumination difference.

[0120] In some embodiments, the determination unit 543 includes:

[0121] A target subunit 5431, configured to use a pixel point with an illumination difference less than a preset illumination threshold as a target pixel point;

[0122] A quantity acquisition subunit 5432, configured to acquire the quantity of the target pixel points;

[0123] A proportion subunit 5433, configured to calculate a proportion value of the quantity of the target pixel points in the total quantity of the pixel points of the pseudocolor map, and use the proportion value as the similarity value.

[0124] In some embodiments, the rendering quality evaluation device further includes:

[0125] A text determination module 56, configured to determine a text area from the reference pseudocolor map;

[0126] An identification module 57, configured to identify the text area to obtain an illumination value corresponding to each reference pixel point.

[0127] Regarding the rendering quality evaluation device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0128] To solve the above technical problems, the embodiments of the present application further provide a computer device. Specifically, please refer to Figure 6 , Figure 6 , which is the basic structural block diagram of the computer device in this embodiment.

[0129] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are communicatively connected to each other through a system bus. It should be noted that only the computer device 6 with components 61-63 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of the present technology 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 (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0130] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with the user through a keyboard, a mouse, a remote control, a touchpad, or a voice control device, etc.

[0131] The memory 61 at least includes one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or D interface display 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, magnetic disk, optical disc, etc. In some embodiments, the memory 61 may be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. equipped on the computer device 6. Of course, the memory 61 may also include both the internal storage unit and the external storage device of the computer device 6. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as the program code of the rendering quality evaluation method. In addition, the memory 61 may also be used to temporarily store various data that have been output or will be output.

[0132] In some embodiments, the processor 62 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the program code stored in the memory 61 or process data, such as running the program code of the rendering quality evaluation method.

[0133] The network interface 63 may include a wireless network interface or a wired network interface, and the network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0134] This application also provides another implementation manner, that is, to provide a computer-readable storage medium storing a rendering quality evaluation program, and the rendering quality evaluation program can be executed by at least one processor to enable the at least one processor to execute the steps of the rendering quality evaluation method as described above.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0136] Obviously, the embodiments described above are only a part of the embodiments of the present application, rather than all the embodiments. The preferred embodiments of the present application are given in the 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 disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is equally within the scope of the patent protection of the present application.

Claims

1. A method for evaluating rendering quality, characterized in that, it includes: Obtain the reference pseudo-color map of the scene image; According to the reference pseudo-color map and the preset rendering engine information, obtain the rendered image of the scene image; Convert the rendered image into a pseudo-color map; Calculate the similarity value between the pseudo-color map and the reference pseudo-color map; Evaluate the rendering quality of the rendered image according to the similarity value; The obtaining the rendered image of the scene image according to the reference pseudo-color map and the preset rendering engine information includes: Obtain the configuration data of the reference pseudo-color map; Generate an illumination file according to the configuration data and the rendering engine information; Render the scene image according to the illumination file and the preset fitting algorithm to obtain a rendered image.

2. The method for evaluating rendering quality according to claim 1, characterized in that, The calculating the similarity value between the pseudo-color map and the reference pseudo-color map includes: Obtain the pixel points of the pseudo-color map and the reference pixel points of the reference pseudo-color map at the same position; Calculate the illumination difference between the pixel points and the reference pixel points; Determine the similarity value between the pseudo-color map and the reference pseudo-color map according to the illumination difference.

3. The method for evaluating rendering quality according to claim 2, characterized in that, The determining the similarity value between the pseudo-color map and the reference pseudo-color map according to the illumination difference includes: Take the pixel points with the illumination difference less than the preset illumination threshold as target pixel points; Obtain the number of the target pixel points; Calculate the proportion of the number of the target pixel points in the total number of pixel points of the pseudo-color map, and take the proportion as the similarity value.

4. The method for evaluating rendering quality according to claim 1, characterized in that, The rendering the scene image according to the illumination file and the preset fitting algorithm to obtain a rendered image includes: Extract the rendering data from the illumination file; According to the rendering data, render the scene image through at least one fitting algorithm to generate at least one rendered image.

5. The method for evaluating rendering quality according to claim 2, characterized in that, Before calculating the illumination difference between the pixel points and the reference pixel points, the method further includes: Determine the text area from the reference pseudo-color map; Identify the text area to obtain the illumination value corresponding to each reference pixel point.

6. The method for evaluating rendering quality according to claim 1, characterized in that, The converting the rendered image into a pseudo-color map includes: Convert the number of channels in the rendered image into a single channel to generate a pseudo-color map.

7. A rendering quality evaluation device, characterized in that, it includes: An acquisition module for acquiring the reference pseudo-color map of the scene image; A rendering module for obtaining the rendered image of the scene image according to the reference pseudo-color map and the preset rendering engine information, including: obtaining the configuration data of the reference pseudo-color map; generating an illumination file according to the configuration data and the rendering engine information; rendering the scene image according to the illumination file and the preset fitting algorithm to obtain a rendered image; A conversion module for converting the rendered image into a pseudo-color map; A calculation module, configured to calculate a similarity value between the pseudo-color map and the reference pseudo-color map; An evaluation module, configured to evaluate the rendering quality of the rendered image according to the similarity value.

8. A computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the rendering quality evaluation method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that, a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the rendering quality evaluation method according to any one of claims 1 to 6 are implemented.

Images