Three-dimensional lookup table updating method and device, computer equipment and storage medium

Abstract

The invention provides a three-dimensional lookup table updating method and device, computer equipment and a storage medium. The method comprises the following steps: performing up-sampling processing on an original three-dimensional lookup table to generate a first three-dimensional lookup table; the first three-dimensional lookup table is input into a table updating model to obtain a reference three-dimensional lookup table, the table updating model is obtained by training according to first color difference data of each color point in a display picture, and the reference three-dimensional lookup table is obtained according to the first color difference data of each color point in the display picture; the table updating model is used for converting the first three-dimensional lookup table based on a color standard to generate a second three-dimensional lookup table so as to reduce first color difference data between color information of each color point and the color standard; and performing down-sampling processing on the reference three-dimensional lookup table to obtain a target three-dimensional lookup table. Through the method, the color accuracy of the picture displayed by the screen based on the target three-dimensional lookup table is improved, and the problem of uneven color transition caused by blowing is avoided.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, computer device, and storage medium for updating three-dimensional lookup tables. Background Technology

[0002] With the rapid development of smart terminal technology, screen display quality has become one of the important indicators of user experience. To provide more accurate and richer color representation, modern mobile phones widely use 3D LUT (3D Lookup Table) technology for color gamut mapping and color correction. 3D LUTs can find the corresponding output color based on the input RGB values, thereby improving the accuracy and consistency of displayed colors.

[0003] In related technologies, terminal screens typically have a 10-bit color depth, theoretically capable of displaying over 1.07 billion colors. However, the actual size of 3D LUT modules used is mostly 17×17×17, meaning that a 3D LUT module can only display 4913 color points. Clearly, the display capability of a terminal screen far exceeds the color range that a 3D LUT can represent, potentially leading to problems such as poor color display and uneven color transitions in the displayed image. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a three-dimensional lookup table updating method, apparatus, computer equipment, and storage medium.

[0005] According to a first aspect of the present disclosure, this application provides a three-dimensional lookup table update method, the method comprising:

[0006] The original three-dimensional lookup table is upsampled to generate a first three-dimensional lookup table, wherein the data volume of the first three-dimensional lookup table is higher than that of the original three-dimensional lookup table.

[0007] The first three-dimensional lookup table is input into the table update model to obtain a reference three-dimensional lookup table. The table update model is trained based on the first color difference data of each color point in the display screen. The table update model is used to convert the first three-dimensional lookup table based on the color standard to generate a second three-dimensional lookup table, so as to reduce the color difference data between the color information of each color point and the color standard. The first color difference data of each color point is determined by the original color information of each color point, the second three-dimensional lookup table and the color standard.

[0008] The reference 3D lookup table is downsampled to obtain the target 3D lookup table.

[0009] In any embodiment of this disclosure, the upsampling process of the original three-dimensional lookup table to generate a first three-dimensional lookup table includes:

[0010] Interpolation is performed on every two rows in each dimension of the original three-dimensional lookup table, and the color depth in the original three-dimensional lookup table is expanded to generate a first three-dimensional lookup table.

[0011] In conjunction with any embodiment of this disclosure, the training process of the table update model is as follows:

[0012] The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table;

[0013] For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard;

[0014] Based on the first color difference data of each color point, the table update model is adjusted until the first color difference data is less than the preset color difference threshold.

[0015] In conjunction with any embodiment of this disclosure, the training process of the table update model is as follows:

[0016] The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table;

[0017] For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard;

[0018] Based on the first color difference data of each color point, the table update model and the color restoration model are trained adversarially until the convergence condition is met. The color restoration model is used to generate restored color information of each color point based on the second three-dimensional lookup table and the first color difference data, so as to reduce the color difference data between the color information of each color point and the original color information of each color point.

[0019] In any embodiment of this disclosure, the convergence condition is that the first color difference data is less than a preset color difference threshold, and the absolute value of the difference between the first color difference data and the restored color difference data is less than the preset difference threshold.

[0020] In any embodiment of this disclosure, before performing adversarial training on the table update model and the color restoration model, the method further includes:

[0021] The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table;

[0022] For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard;

[0023] Based on the first color difference data of each color point, the table update model is adjusted until the first color difference data is less than the preset color difference threshold.

[0024] In any embodiment of this disclosure, determining the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table, and the color standard includes:

[0025] Based on the second three-dimensional lookup table, the original color information of the color point is transformed to obtain the transformed color information of the color point;

[0026] The color difference data between the converted color information of the color point and the color standard is used as the first color difference data of the color point.

[0027] In any embodiment of this disclosure, both the first color difference data and the restored color difference data include the original color difference data and the original perceptible color difference data, and the color standard includes the 7500K daylight white point standard and the Digital Cinema Initiative P3 color gamut standard.

[0028] In any embodiment of this disclosure, the step of downsampling the reference three-dimensional lookup table to obtain the target three-dimensional lookup table includes:

[0029] Based on each dimension and color depth of the original 3D lookup table, each dimension and color depth of the reference 3D lookup table are restored to obtain the target 3D lookup table.

[0030] Secondly, this application also provides a three-dimensional lookup table updating device, comprising:

[0031] The first generation module is used to perform upsampling processing on the original three-dimensional lookup table to generate a first three-dimensional lookup table, wherein the data volume of the first three-dimensional lookup table is higher than the data volume of the original three-dimensional lookup table.

[0032] The second generation module is used to input the first three-dimensional lookup table into the table update model to obtain a reference three-dimensional lookup table. The table update model is trained based on the first color difference data of each color point in the display screen. The table update model is used to convert the first three-dimensional lookup table based on the color standard to generate a second three-dimensional lookup table, so as to reduce the first color difference data between the color information of each color point and the color standard. The first color difference data of each color point is determined by the original color information of each color point, the second three-dimensional lookup table and the color standard.

[0033] The third generation module is used to perform downsampling processing on the reference 3D lookup table to obtain the target 3D lookup table.

[0034] In one embodiment, the first generation module is specifically used for:

[0035] Interpolation is performed on every two rows in each dimension of the original three-dimensional lookup table, and the color depth in the original three-dimensional lookup table is expanded to generate a first three-dimensional lookup table.

[0036] In one embodiment, the above-described three-dimensional lookup table updating device further includes:

[0037] The first training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, the first color difference data of the color point is determined according to the original color information of the color point, the second three-dimensional lookup table and the color standard; the table update model is adjusted according to the first color difference data of each color point until the first color difference data is less than a preset color difference threshold.

[0038] In one embodiment, the above-described three-dimensional lookup table updating device further includes:

[0039] The second training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, it determines the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table, and the color standard; based on the first color difference data of each color point, it performs adversarial training on the table update model and the color restoration model until the convergence condition is met, wherein the color restoration model is used to generate the restored color information of each color point based on the second three-dimensional lookup table and the first color difference data, so as to reduce the color difference data between the color information of each color point and the original color information of each color point.

[0040] In one embodiment, the convergence condition is that the first color difference data is less than a preset color difference threshold, and the absolute value of the difference between the first color difference data and the restored color difference data is less than a preset difference threshold.

[0041] In one embodiment, prior to the second training module, the aforementioned three-dimensional lookup table updating device further includes:

[0042] The self-training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, the first color difference data of the color point is determined according to the original color information of the color point, the second three-dimensional lookup table and the color standard; the table update model is adjusted according to the first color difference data of each color point until the first color difference data is less than a preset color difference threshold.

[0043] In one embodiment, the first training module or the second training module is specifically used for:

[0044] Based on the second three-dimensional lookup table, the original color information of the color point is transformed to obtain the transformed color information of the color point;

[0045] The color difference data between the converted color information of the color point and the color standard is used as the first color difference data of the color point.

[0046] In one embodiment, both the first color difference data and the restored color difference data include the original color difference data and the original perceptible color difference data, and the color standard includes the 7500K daylight white point standard and the Digital Cinema Initiative P3 color gamut standard.

[0047] In one embodiment, the third generation module is specifically used for:

[0048] Based on each dimension and color depth of the original 3D lookup table, each dimension and color depth of the reference 3D lookup table are restored to obtain the target 3D lookup table.

[0049] Thirdly, this application provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in any embodiment.

[0050] Fourthly, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method described in any of the above embodiments.

[0051] Fifthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the above embodiments.

[0052] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects:

[0053] In this embodiment, a more accurate first three-dimensional lookup table is obtained by upsampling the original three-dimensional lookup table. A pre-trained table update model is introduced to reduce the color difference between the color information of each color point and the color standard. The first three-dimensional lookup table is updated by the table update model to obtain a reference lookup table that is closer to the color standard. Then, the reference three-dimensional lookup table is downsampled to generate a target three-dimensional lookup table with higher accuracy and a format that conforms to the terminal hardware standard. This improves the color accuracy of the screen display based on the target three-dimensional lookup table and avoids the problem of uneven color transition.

[0054] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0055] The accompanying drawings, which are incorporated in and form part of this disclosure, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0056] Figure 1 This is a flowchart illustrating a three-dimensional lookup table update method using some exemplary embodiments.

[0057] Figure 2 This is a flowchart illustrating the training of a table update model using some exemplary embodiments.

[0058] Figure 3 This is a flowchart illustrating another table update model training process, shown in some exemplary embodiments.

[0059] Figure 4 This is a block diagram illustrating a three-dimensional lookup table updating apparatus according to some exemplary embodiments.

[0060] Figure 5 These are hardware structure diagrams of a computer device illustrating some exemplary embodiments. Detailed Implementation

[0061] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0062] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0063] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0064] In related technologies, terminal screens typically have a color depth of 10 bits, theoretically supporting the display of over 1.07 billion colors. This high color depth design aims to provide a richer, more realistic visual experience, especially in color reproduction and gradient transitions. However, despite the screen's immense potential, the size of the 3D LUT (Look-Up Table) modules used in practical applications is usually limited to 17×17×17, meaning it can only represent 4913 color points. This fails to fully utilize the screen's color depth, resulting in inaccurate color display, particularly in the detail representation of dark and light areas. For example, when displaying complex gradients, the sparse color points may cause noticeable banding rather than a smooth gradient. This phenomenon is particularly pronounced in high dynamic range (HDR) content, where viewers may notice unnatural color transitions, affecting the overall visual experience.

[0065] In view of this, this disclosure provides a method, apparatus, computer device, and storage medium for updating a three-dimensional lookup table. The method can be applied to scenarios where a three-dimensional lookup table needs to be updated to improve accuracy. Optionally, the method can be executed by a table update system that updates the three-dimensional lookup table, which can be integrated into a local server or a cloud server. Specifically, after updating the three-dimensional lookup table to obtain a target three-dimensional lookup table, the target three-dimensional lookup table can be sent to a terminal so that the terminal can update and display the color information of each color point on the screen according to the target three-dimensional lookup table.

[0066] The embodiments of this disclosure will now be described in detail.

[0067] The first aspect of this disclosure provides a method for updating a three-dimensional lookup table. Please refer to [link to relevant documentation]. Figure 1 It includes the following steps:

[0068] S101, Upsample the original 3D lookup table to generate the first 3D lookup table.

[0069] The first three-dimensional lookup table has a larger data volume than the original three-dimensional lookup table. The original three-dimensional lookup table refers to a three-dimensional lookup table with dimensions of 17*17*17 and a color depth of 12 bits; the first three-dimensional lookup table refers to a high-precision three-dimensional lookup table obtained after upsampling processing.

[0070] Optionally, interpolation can be performed on every two rows in each dimension of the original 3D lookup table, and the color depth of the original 3D lookup table can be expanded to generate a first 3D lookup table. For example, each dimension of the original 3D lookup table can be subjected to secondary interpolation to increase the dimension to 65*65*65, and the color depth of the original 3D lookup table can be increased from 12 bits to 14 bits, thus obtaining a first 3D lookup table with an expanded data volume of 16384. It should be noted that the original 3D lookup table with a dimension of 17*17*17 and a color depth of 12 bits, based on gamma2.2 conversion, can only control down to the 72nd gray level of the image; that is, images below the 72nd gray level cannot be accurately controlled for display. However, after upsampling processing, the second 3D lookup table with a dimension of 65*65*65 and a color depth of 14 bits, after gamma2.2 conversion, can control down to the 38th gray level of the displayed image, increasing the degree of control over the nodes. Obviously, the color accuracy displayed based on the first 3D lookup table will also improve accordingly.

[0071] S102, input the first three-dimensional lookup table into the table update model to obtain a reference three-dimensional lookup table.

[0072] The table update model is trained based on the first color difference data of each color point in the displayed image. This model is used to transform the first three-dimensional lookup table based on a color standard to generate a second three-dimensional lookup table, thereby reducing the first color difference data between the color information of each color point and the color standard. The first color difference data of each color point is determined by the original color information of the color point, the second three-dimensional lookup table, and the color standard. The reference three-dimensional lookup table refers to a high-precision three-dimensional lookup table obtained by updating the first three-dimensional lookup table using the table update model. A color standard refers to a specification used to define, measure, and manage color; such standards may include the 7500K daylight white point standard and the Digital Cinema Initiatives P3 color gamut standard.

[0073] Optionally, the table update model can be pre-trained to obtain a trained table update model; the first three-dimensional lookup table is input into the trained table update model, and the table update model updates the first three-dimensional lookup table to generate a reference three-dimensional lookup table.

[0074] S103, perform downsampling processing on the reference three-dimensional lookup table to obtain the target three-dimensional lookup table.

[0075] The target 3D lookup table refers to a 3D lookup table that has been downsampled from the reference 3D lookup table to a format that the terminal hardware module can store.

[0076] Optionally, based on each dimension and color depth of the original 3D lookup table, each dimension and color depth of the reference 3D lookup table are restored to obtain the target 3D lookup table. For example, the dimensions of the reference 3D lookup table can be reduced from 65*65*65 to 17*17*17, and the color depth of the reference 3D lookup table can be converted from 14 bits to 12 bits to obtain the target 3D lookup table.

[0077] In this embodiment, a more accurate first three-dimensional lookup table is obtained by upsampling the original three-dimensional lookup table. A pre-trained table update model is introduced to reduce the color difference between the color information of each color point and the color standard. The first three-dimensional lookup table is updated by the table update model to obtain a reference lookup table that is closer to the color standard. Then, the reference three-dimensional lookup table is downsampled to generate a target three-dimensional lookup table with higher accuracy and a format that conforms to the terminal hardware standard. This improves the color accuracy of the screen display based on the target three-dimensional lookup table and avoids the problem of uneven color transition.

[0078] Based on the above embodiments, in an exemplary embodiment, such as Figure 2 As shown, a self-training method can be provided for the table update model, which specifically includes the following steps:

[0079] S201, input the first three-dimensional lookup table into the table update model to obtain the second three-dimensional lookup table.

[0080] The second three-dimensional lookup table refers to the three-dimensional lookup table obtained by updating the first three-dimensional lookup table through the table update model during the training process.

[0081] S202, for each color point, determine the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table and the color standard.

[0082] Native color information refers to the color information of each color point in the terminal's native state.

[0083] Optionally, for each color point, the original color information of the color point can be converted based on the second three-dimensional lookup table to obtain the converted color information of the color point; then, the color difference data between the converted color information of the color point and the color standard can be used as the first color difference data of the color point, thereby achieving more accurate and reasonable generation of the first color difference data of each color point.

[0084] S203, adjust the parameters of the table update model according to the first color difference data of each color point until the first color difference data is less than the preset color difference threshold.

[0085] The preset color difference threshold refers to the color difference threshold of the first color difference data that is set in advance. The first color difference data may include the first original color difference data ΔE1 and the first original perceptible color difference data JNCD1. The preset color difference value may include the first original color difference threshold and the first original perceptible color difference threshold.

[0086] Optionally, after determining the first color difference data for each color point, the first color difference data for each color point can be compared with a preset color difference threshold. If the first color difference data is greater than or equal to the preset color difference threshold, the table update model is tuned. If the first color difference data is less than the preset color difference threshold, the table update model is considered to have completed training. For example, if the first original color difference data ΔE1 in the first color difference data is less than the first original color difference threshold 2, and the original perceptible color difference data JNCD1 is less than the first original perceptible color difference threshold 1, then the table update model can be considered to have completed training.

[0087] In this embodiment, the table update model is trained by adjusting the parameters of each color point based on the first color difference data of each color point determined by the original color information of each color point, the second three-dimensional lookup table, and the color standard until the first color difference data is less than the preset color difference threshold. This allows for more reasonable training of the table update model and the generation of a more accurate table update model.

[0088] In one exemplary embodiment, a training method is provided for the table update model, such as... Figure 3 As shown, the specific steps include:

[0089] S301, input the first three-dimensional lookup table into the table update model to obtain the second three-dimensional lookup table.

[0090] S302, for each color point, determine the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table and the color standard.

[0091] Optionally, for each color point, the original color information of the color point can be converted based on the second three-dimensional lookup table to obtain the converted color information of the color point; then the color difference data between the converted color information of the color point and the color standard can be used as the first color difference data of the color point.

[0092] S303, based on the first color difference data of each color point, perform adversarial training on the table update model and the color restoration model until the convergence condition is met.

[0093] The color restoration model is used to generate restored color information for each color point based on the second three-dimensional lookup table and the first color difference data, thereby reducing the restored color difference data between the restored color information and the original color information of each color point. The convergence condition can be that the first color difference data is less than a preset color difference threshold, and the absolute value of the difference between the first color difference data and the restored color difference data is less than a preset difference threshold. The preset difference threshold refers to a pre-set difference threshold used to determine whether the adversarial training between the table update model and the color restoration model is complete.

[0094] Optionally, after generating the second three-dimensional lookup table and the first color difference data through the table update model, the generated second three-dimensional lookup table and the first color difference data can be input into the color restoration model. Through the color restoration model, based on the second three-dimensional lookup table, the converted color information corresponding to the first color difference data is converted towards the original color information of each color point in the terminal to obtain the restored color information, thereby determining the restored color difference data between the restored color information and the original color information. Further, the absolute value of the difference between the first color difference data and the restored color difference data is determined. Based on the comparison result between the absolute value of the difference and the preset difference threshold, the table update model and the color restoration model are subjected to adversarial training. For example, if the absolute value of the difference between the first color difference data and the restored color difference data is greater than or equal to the preset difference threshold, the table update model is further tuned based on the first color difference data, and the color restoration model is further tuned based on the restored color difference data. If the absolute value of the difference between the first color difference data and the restored color difference data is less than the preset difference threshold, it can be determined that both the table update model and the color restoration model have been trained successfully.

[0095] It should be noted that the table update model adjusts the original color information of each color point towards the standard color information, while the color restoration model adjusts the transformed color information of each color point towards the original color information. Since their functions are opposite, they are somewhat adversarial. Therefore, adversarial training can mutually reinforce each other's capabilities, thereby improving the table update model's ability to update the 3D lookup table towards the color standard and the color restoration model's ability to restore the transformed color information of each color point towards the original color information.

[0096] Understandably, this embodiment introduces a color restoration model, inputting the generated second 3D lookup table and the first color difference data into the model to generate restored color information. This determines the restored color difference data between the restored color information and the original color information, effectively adjusting the converted color information corresponding to the first color difference data towards the original color information of each color point, thereby generating high-quality restored color information. Furthermore, by calculating the absolute value of the difference between the first color difference data and the restored color difference data and comparing it with a preset difference threshold, a dynamic adversarial training mechanism is formed between the table update model and the color restoration model. This mechanism ensures continuous optimization of both the table update model and the color restoration model by adjusting model parameters based on real-time feedback. If the difference exceeds the threshold, the model can specifically adjust parameters to reduce the difference between the first color difference data and the restored color difference data, thereby improving the balance between the table update model and the original color information in updating the 3D lookup table. Once training is complete, a more accurate and reasonable table update model can be obtained. This model can then be used to develop an optimal 3D lookup table that balances color standards and native color information. This will improve the color quality of the displayed image based on the updated 3D lookup table and enhance the user's viewing experience.

[0097] Corresponding to the embodiments of the foregoing methods, this disclosure also provides embodiments of the apparatus and the terminal to which it is applied.

[0098] Secondly, this application also provides a three-dimensional lookup table updating device, such as... Figure 4 As shown, it includes:

[0099] The first generation module 401 is used to perform upsampling processing on the original three-dimensional lookup table to generate a first three-dimensional lookup table, wherein the data volume of the first three-dimensional lookup table is higher than the data volume of the original three-dimensional lookup table.

[0100] The second generation module 402 is used to input the first three-dimensional lookup table into the table update model to obtain a reference three-dimensional lookup table. The table update model is trained based on the first color difference data of each color point in the display screen. The table update model is used to convert the first three-dimensional lookup table based on the color standard to generate a second three-dimensional lookup table, so as to reduce the first color difference data between the color information of each color point and the color standard. The first color difference data of each color point is determined by the original color information of each color point, the second three-dimensional lookup table and the color standard.

[0101] The third generation module 403 is used to perform downsampling processing on the reference three-dimensional lookup table to obtain the target three-dimensional lookup table.

[0102] In one embodiment, the first generation module 401 is specifically used for:

[0103] Interpolation is performed on every two rows in each dimension of the original three-dimensional lookup table, and the color depth in the original three-dimensional lookup table is expanded to generate a first three-dimensional lookup table.

[0104] In one embodiment, the above-described three-dimensional lookup table updating device further includes:

[0105] The first training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, the first color difference data of the color point is determined according to the original color information of the color point, the second three-dimensional lookup table and the color standard; the table update model is adjusted according to the first color difference data of each color point until the first color difference data is less than a preset color difference threshold.

[0106] In one embodiment, the above-described three-dimensional lookup table updating device further includes:

[0107] The second training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, it determines the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table, and the color standard; based on the first color difference data of each color point, it performs adversarial training on the table update model and the color restoration model until the convergence condition is met, wherein the color restoration model is used to generate the restored color information of each color point based on the second three-dimensional lookup table and the first color difference data, so as to reduce the color difference data between the color information of each color point and the original color information of each color point.

[0108] In one embodiment, the convergence condition is that the first color difference data is less than a preset color difference threshold, and the absolute value of the difference between the first color difference data and the restored color difference data is less than a preset difference threshold.

[0109] In one embodiment, prior to the second training module, the aforementioned three-dimensional lookup table updating device further includes:

[0110] The self-training module is used to input the first three-dimensional lookup table into the table update model to obtain a second three-dimensional lookup table; for each color point, the first color difference data of the color point is determined according to the original color information of the color point, the second three-dimensional lookup table and the color standard; the table update model is adjusted according to the first color difference data of each color point until the first color difference data is less than a preset color difference threshold.

[0111] In one embodiment, the first training module or the second training module is specifically used for:

[0112] Based on the second three-dimensional lookup table, the original color information of the color point is transformed to obtain the transformed color information of the color point;

[0113] The color difference data between the converted color information of the color point and the color standard is used as the first color difference data of the color point.

[0114] In one embodiment, both the first color difference data and the restored color difference data include the original color difference data and the original perceptible color difference data, and the color standard includes the 7500K daylight white point standard and the Digital Cinema Initiative P3 color gamut standard.

[0115] In one embodiment, the third generation module 403 is specifically used for:

[0116] Based on each dimension and color depth of the original 3D lookup table, each dimension and color depth of the reference 3D lookup table are restored to obtain the target 3D lookup table.

[0117] The specific implementation process of the functions and roles of each module in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0118] A third aspect of this disclosure provides a computer program product including a computer program / instructions that, when executed by a processor, implement the method described in the first aspect.

[0119] For the device embodiments and computer program product embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. Furthermore, the device embodiments described above are merely illustrative; the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0120] Fourthly, embodiments of the three-dimensional lookup table updating device provided in this disclosure can be applied to computer devices. Please refer to the appendix. Figure 5 The illustration exemplifies a hardware schematic of a computer device. For example, device 500 could be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0121] Device 500 may include one or more of the following components: processing component 501, memory 502, power supply component 503, multimedia component 504, audio component 505, input / output (I / O) interface 506, sensor component 507, and communication component 508.

[0122] Processing component 501 typically controls the overall operation of device 500, such as actions associated with display, telephone calls, data communication, camera actions, and recording actions. Processing component 501 may include one or more processors 509 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 501 may include one or more modules to facilitate interaction between processing component 501 and other components. For example, processing component 501 may include a multimedia module to facilitate interaction between multimedia component 504 and processing component 501.

[0123] Memory 502 is configured to store various types of data to support the operation of device 500. Examples of this data include instructions for any application or method operating on device 500, contact data, phonebook data, messages, pictures, videos, etc. Memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0124] The power supply component 503 provides power to the various components of the device 500. The power supply component 503 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 500.

[0125] Multimedia component 504 includes a screen that provides an output interface between the device 500 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe action. In some embodiments, multimedia component 504 includes a front-facing camera and / or a rear-facing camera. When the device 500 is in an active mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0126] Audio component 505 is configured to output and / or input audio signals. For example, audio component 505 includes a microphone (MIC) configured to receive external audio signals when device 500 is in an operational mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 502 or transmitted via communication component 508. In some embodiments, audio component 505 also includes a speaker for outputting audio signals.

[0127] I / O interface 506 provides an interface between processing component 501 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0128] Sensor assembly 507 includes one or more sensors for providing state assessments of various aspects of device 500. For example, sensor assembly 507 can detect the on / off state of device 500, the relative positioning of components such as the display and keypad of device 500, changes in the position of device 500 or a component of device 500, the presence or absence of user contact with device 500, the orientation or acceleration / deceleration of device 500, and temperature changes of device 500. Sensor assembly 507 may also include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 507 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 507 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0129] Communication component 508 is configured to facilitate wired or wireless communication between device 500 and other devices. Device 500 can access wireless networks based on communication standards, such as WiFi, 2G or 3G, 4G or 5G, or combinations thereof. In one exemplary embodiment, communication component 508 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 508 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0130] In an exemplary embodiment, device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the three-dimensional lookup table update method of the computer device described above.

[0131] Fifthly, in exemplary embodiments, this disclosure also provides a non-transitory computer-readable storage medium including instructions, such as a memory 502 including instructions, which can be executed by a processor 509 of device 500 to complete the three-dimensional lookup table update method of the computer device. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0132] The foregoing has described specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0133] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention applied herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0134] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0135] The above description is merely a preferred embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for updating a three-dimensional lookup table, characterized in that, The method includes: The original three-dimensional lookup table is upsampled to generate a first three-dimensional lookup table, wherein the data volume of the first three-dimensional lookup table is higher than that of the original three-dimensional lookup table. The first three-dimensional lookup table is input into the table update model to obtain a reference three-dimensional lookup table. The table update model is trained based on the first color difference data of each color point in the display screen. The table update model is used to convert the first three-dimensional lookup table based on the color standard to generate a second three-dimensional lookup table, so as to reduce the color difference data between the color information of each color point and the color standard. The first color difference data of the color point is determined by the original color information of the color point, the second three-dimensional lookup table and the color standard. The reference 3D lookup table is downsampled to obtain the target 3D lookup table.

2. The method according to claim 1, characterized in that, The step of upsampling the original three-dimensional lookup table to generate the first three-dimensional lookup table includes: Interpolation is performed on every two rows in each dimension of the original three-dimensional lookup table, and the color depth in the original three-dimensional lookup table is expanded to generate a first three-dimensional lookup table.

3. The method according to claim 1, characterized in that, The training process of the table update model is as follows: The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table; For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard; Based on the first color difference data of each color point, the table update model is adjusted until the first color difference data is less than the preset color difference threshold.

4. The method according to claim 1, characterized in that, The training process of the table update model is as follows: The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table; For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard; Based on the first color difference data of each color point, the table update model and the color restoration model are trained adversarially until the convergence condition is met. The color restoration model is used to generate restored color information of each color point based on the second three-dimensional lookup table and the first color difference data, so as to reduce the color difference data between the color information of each color point and the original color information of each color point.

5. The method according to claim 4, characterized in that, The convergence condition is that the first color difference data is less than a preset color difference threshold, and the absolute value of the difference between the first color difference data and the restored color difference data is less than a preset difference threshold.

6. The method according to claim 4, characterized in that, Before performing adversarial training on the table update model and the color restoration model, the method further includes: The first three-dimensional lookup table is input into the table update model to obtain the second three-dimensional lookup table; For each color point, the first color difference data of the color point is determined based on the original color information of the color point, the second three-dimensional lookup table, and the color standard; Based on the first color difference data of each color point, the table update model is adjusted until the first color difference data is less than the preset color difference threshold.

7. The method according to any one of claims 4, 5 or 6, characterized in that, The step of determining the first color difference data of the color point based on the original color information of the color point, the second three-dimensional lookup table, and the color standard includes: Based on the second three-dimensional lookup table, the original color information of the color point is transformed to obtain the transformed color information of the color point; The color difference data between the converted color information of the color point and the color standard is used as the first color difference data of the color point.

8. The method according to claim 4, characterized in that, Both the first color difference data and the restored color difference data include the original color difference data and the original perceptible color difference data. The color standard includes the 7500K daylight white point standard and the Digital Cinema Initiative P3 color gamut standard.

9. The method according to claim 1, characterized in that, The step of downsampling the reference 3D lookup table to obtain the target 3D lookup table includes: Based on each dimension and color depth of the original 3D lookup table, each dimension and color depth of the reference 3D lookup table are restored to obtain the target 3D lookup table.

10. A three-dimensional lookup table updating device, characterized in that, The device includes: The first generation module is used to perform upsampling processing on the original three-dimensional lookup table to generate a first three-dimensional lookup table, wherein the data volume of the first three-dimensional lookup table is higher than the data volume of the original three-dimensional lookup table. The second generation module is used to input the first three-dimensional lookup table into the table update model to obtain a reference three-dimensional lookup table. The table update model is trained based on the first color difference data of each color point in the display screen. The table update model is used to convert the first three-dimensional lookup table based on the color standard to generate a second three-dimensional lookup table, so as to reduce the first color difference data between the color information of each color point and the color standard. The first color difference data of each color point is determined by the original color information of each color point, the second three-dimensional lookup table and the color standard. The third generation module is used to perform downsampling processing on the reference 3D lookup table to obtain the target 3D lookup table.

11. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the method described in any one of claims 1 to 9.

12. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any one of claims 1 to 9.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 9.

Images