Image processing method, device, equipment and readable storage medium

Abstract

This application discloses an image processing method, apparatus, device, and readable storage medium. The method includes: sampling a service message to obtain sampled message data; acquiring an original image and dynamic metadata; the dynamic metadata includes a first image parameter for tone mapping and a second image parameter for color reconstruction; performing brightness conversion on the original image to obtain an original brightness image; mapping the original brightness image to obtain a mapped brightness image based on the first image parameter; acquiring the signal difference between the original image and the original brightness image; generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameter; acquiring brightness signal data corresponding to the mapped brightness image; generating a target signal value based on the brightness signal data and the color data items; and using the target signal value to generate a reconstructed image. Using this application can improve the reconstruction effect of the reconstructed image.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an image processing method, apparatus, device, and readable storage medium. Background Technology

[0002] When converting HDR (High Dynamic Range) images to SDR (Standard Dynamic Range) images (or converting SDR images to HDR images, HDR images to HDR images, etc., involving different peak brightness), in order to ensure the visual consistency between the HDR image at the production end and the SDR image at the playback end, the production end can generate parameters for tone mapping, and send the original image in HDR format and the parameters to the playback end. Then the playback end can perform tone mapping processing on the original image according to the parameters to obtain the SDR reconstructed image.

[0003] However, since the parameters used for tone mapping only focus on adjusting the brightness data of the original image, the generated reconstructed image may only be reconstructed in terms of brightness data, and the color attributes of the reconstructed image are difficult to control. As a result, the reconstructed image may not perform well in terms of color attributes, thus reducing the reconstruction effect presented by the reconstructed image. Summary of the Invention

[0004] This application provides an image processing method, apparatus, device, and readable storage medium that can improve the reconstruction effect of reconstructed images.

[0005] One embodiment of this application provides an image processing method, including: Acquire the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. The original image is converted to brightness to obtain the original brightness image. The original brightness image is then mapped to brightness based on the first image parameters to obtain the mapped brightness image. Obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters; Obtain the luminance signal data corresponding to the mapped luminance image, and generate the target signal value based on the luminance signal data and color data items; the target signal value is used to generate the reconstructed image corresponding to the original image.

[0006] The color attributes include chromaticity deviation, color contrast, and color balance; the second image parameters include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance; color data items for adjusting the color attributes of the original image are generated based on the signal difference and the second image parameters, including: A first sub-item for adjusting the chromaticity deviation of the original image is generated based on the signal difference and the first sub-parameter; A second sub-item for adjusting the color contrast of the original image is generated based on the signal difference and the second sub-parameter; The sum of the first sub-item, the second sub-item, and the third sub-parameter is determined as the color data item used to adjust the color attributes of the original image.

[0007] The first sub-item, generated based on the signal difference and the first sub-parameter, for adjusting the chromaticity deviation of the original image, includes: The product of the signal difference and the first sub-parameter is determined as the first sub-item used to adjust the chromaticity deviation of the original image.

[0008] The second sub-item, generated based on the signal difference and the second sub-parameter, for adjusting the color contrast of the original image, includes: The signal difference is squared to obtain the squared data. The product of the squared term data and the second sub-parameter is determined as the second sub-term used to adjust the color contrast of the original image.

[0009] The generation of target signal values ​​based on luminance signal data and color data includes: The target signal value is obtained by summing the luminance signal data and color data.

[0010] Each pixel in the original image includes pixel components corresponding to M color channels; the second image parameters include second image parameters corresponding to M color channels; the M color channels include color channel K. h M is a positive integer, and h is a positive integer less than or equal to M; obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, including: Based on the color channel K in the original image h The difference between the pixel components below and the luminance transformation values ​​contained in the original luminance image is used to generate the color channel K. h The corresponding signal difference; According to color channel K h The corresponding signal difference and color channel K h The corresponding second image parameters generate color channel K.h The corresponding color data item.

[0011] The target signal value is generated based on the luminance signal data and color data items, including: The color data items corresponding to each color channel are summed with the luminance signal data to obtain the channel component signal value corresponding to each color channel; the channel component signal value corresponding to each color channel is used to form the target signal value.

[0012] The original image consists of N pixels; the N pixels include pixel F. t Pixel F t This includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the original image is subjected to brightness conversion to obtain the original brightness image, including: Get pixel F t The brightness conversion weights are included for each of the M color channels. pixel F t The pixel component corresponding to each of the M color channels is weighted and summed with the luminance conversion weight corresponding to each of the M color channels to obtain the pixel F. t The corresponding brightness conversion values; the brightness conversion values ​​corresponding to N pixels are used to construct the original brightness image corresponding to the original image.

[0013] The original brightness image consists of N pixels; the N pixels include pixel F. t Pixel F t It includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the original brightness image is luminance-mapped according to the first image parameters to obtain a mapped brightness image, including: Get pixel F t Brightness conversion values ​​in the original brightness image; A mapping curve for brightness mapping of the original brightness image is generated based on the first image parameters; Based on the mapping curve, pixel F t The brightness conversion value is mapped to obtain pixel F. t The corresponding luminance signal data; the luminance signal data corresponding to N pixels are used to construct the mapped luminance image corresponding to the original luminance image.

[0014] The process of acquiring the luminance signal data corresponding to the mapped luminance image includes: Obtain the luminance mapping data contained in the mapped luminance image; the luminance mapping data is the luminance data in the linear original luminance domain; The signal parameters used for domain signal transformation between the original luminance domain and the perceived uniform target signal domain are obtained. Based on the signal parameters, the luminance mapping data is processed by nonlinear operation to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0015] The methods also include: The brightness mapping data is normalized to obtain normalized brightness data; Then, based on the signal parameters, nonlinear operations are performed on the luminance mapping data to obtain the luminance signal data of the mapped luminance image in the target signal domain, including: The normalized luminance data is processed nonlinearly based on the signal parameters to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0016] This application provides another image processing method, including: Acquire the original image, generate the first image parameters for tone mapping from the original image, and generate the second image parameters for color reconstruction from the original image. The first image parameters and the second image parameters are encapsulated into dynamic metadata, and the original image and the dynamic metadata are sent to the playback end. The dynamic metadata is used to instruct the playback end to perform brightness mapping on the original brightness image converted from the original image using the first image parameters to obtain a mapped brightness image. The dynamic metadata is also used to instruct the playback end to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameters, and to generate a target signal value based on the brightness signal data and color data items in the mapped brightness image. The signal difference refers to the difference in signal values ​​between the original image and the original brightness image. The target signal value is used to generate the reconstructed image corresponding to the original image.

[0017] The process of generating first image parameters for tone mapping from the original image includes: Obtain the first initial image parameters for tone mapping, and obtain the target image associated with the original image; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to obtain an original brightness image. The original brightness image is then mapped to obtain predicted brightness data based on the first initial image parameters. Perform brightness conversion on the target image to obtain a target brightness image containing the target brightness data; The first initial image parameters are adjusted based on the brightness difference between the predicted brightness data and the target brightness data to obtain the adjusted first initial image parameters. If the adjusted first initial image parameters satisfy the parameter convergence condition, then the adjusted first initial image parameters are determined as the first image parameters.

[0018] This also includes: The original brightness data is remapped using the adjusted first initial image parameters to obtain new predicted brightness data; If the brightness difference between the new predicted brightness data and the target brightness data is within the error range, then the adjusted first initial image parameters are determined to meet the parameter convergence condition.

[0019] The second image parameters for color reconstruction are generated from the original image, including: Obtain the target image and a second initial image parameter for color reconstruction; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to brightness to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first image parameters to obtain a mapped brightness image. The original image is then reconstructed based on the original brightness image, the mapped brightness image, and the second initial image parameters to obtain an intermediate target image. Obtain the original color attributes of the intermediate target image and the target color attributes of the target image. Extract features from the original color attributes to obtain the original attribute features, and extract features from the target color attributes to obtain the target attribute features. Similarity calculation is performed on the original attribute features and the target attribute features to obtain the attribute similarity between the original color attributes and the target color attributes. Based on the attribute similarity, the second initial image parameters are adjusted to obtain the adjusted second initial image parameters. If the original color attribute of the intermediate target image obtained by reconstructing the original image using the adjusted second initial image parameters has an attribute similarity greater than or equal to the target color attribute, then the adjusted second initial image parameters are determined as the second image parameters.

[0020] The second image parameters for color reconstruction are generated from the original image, including: A second initial image parameter for color reconstruction is obtained, and the original image is reconstructed based on the first image parameter and the second initial image parameter to obtain a reconstructed image. The second initial image parameter includes a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. In response to the adjustment operation of the target sub-parameter among the first sub-parameter, second sub-parameter, and third sub-parameter, the reconstructed image is updated and displayed; the updated reconstructed image is obtained by updating the reconstructed image according to the adjusted second initial image parameters; the adjusted second initial image parameters include the adjusted target sub-parameter; In response to the confirmation operation for the updated reconstructed image, the adjusted second initial image parameters are determined as the second image parameters.

[0021] One embodiment of this application provides an image processing apparatus, including: The transceiver module is used to acquire the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. The image processing module is used to perform brightness conversion on the original image to obtain the original brightness image, and to perform brightness mapping on the original brightness image according to the first image parameters to obtain the mapped brightness image; The data item generation module is used to obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters. The signal value generation module is used to acquire the luminance signal data corresponding to the mapped luminance image, and generate the target signal value based on the luminance signal data and color data items; the target signal value is used to generate the reconstructed image corresponding to the original image.

[0022] In one possible implementation, the color attributes include chromaticity deviation, color contrast, and color balance; the second image parameters include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance; when the data item generation module generates color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, it specifically performs the following operations: A first sub-item for adjusting the chromaticity deviation of the original image is generated based on the signal difference and the first sub-parameter; A second sub-item for adjusting the color contrast of the original image is generated based on the signal difference and the second sub-parameter; The sum of the first sub-item, the second sub-item, and the third sub-parameter is determined as the color data item used to adjust the color attributes of the original image.

[0023] In one possible implementation, when the data item generation module generates a first sub-item for adjusting the chromaticity deviation of the original image based on the signal difference and the first sub-parameter, it specifically performs the following operations: The product of the signal difference and the first sub-parameter is determined as the first sub-item used to adjust the chromaticity deviation of the original image.

[0024] In one possible implementation, when the data item generation module generates a second sub-item for adjusting the color contrast of the original image based on the signal difference and the second sub-parameter, it specifically performs the following operations: The signal difference is squared to obtain the squared data. The product of the squared term data and the second sub-parameter is determined as the second sub-term used to adjust the color contrast of the original image.

[0025] In one possible implementation, when the signal value generation module generates the target signal value based on the luminance signal data and color data items, it specifically performs the following operations: The target signal value is obtained by summing the luminance signal data and color data.

[0026] In one possible implementation, each pixel in the original image includes pixel components corresponding to M color channels; the second image parameters include second image parameters corresponding to the M color channels; the M color channels include color channel K. h M is a positive integer, and h is a positive integer less than or equal to M. The data item generation module is used to obtain the signal difference between the original image and the original brightness image. When generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, it is specifically used to perform the following operations: Based on the color channel K in the original image h The difference between the pixel components below and the luminance transformation values ​​contained in the original luminance image is used to generate the color channel K. h The corresponding signal difference; According to color channel K h The corresponding signal difference and color channel K h The corresponding second image parameters generate color channel K. h The corresponding color data item.

[0027] When the data item generation module generates the target signal value based on the luminance signal data and color data items, it specifically performs the following operations: The color data items corresponding to each color channel are summed with the luminance signal data to obtain the channel component signal value corresponding to each color channel; the channel component signal value corresponding to each color channel is used to form the target signal value.

[0028] In one possible implementation, the original image comprises N pixels; the N pixels include pixel F. t Pixel F tIt includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the image processing module is used to perform brightness conversion on the original image to obtain the original brightness image, specifically for performing the following operations: Get pixel F t The brightness conversion weights are included for each of the M color channels. pixel F t The pixel component corresponding to each of the M color channels is weighted and summed with the luminance conversion weight corresponding to each of the M color channels to obtain the pixel F. t The corresponding brightness conversion values; the brightness conversion values ​​corresponding to N pixels are used to construct the original brightness image corresponding to the original image.

[0029] In one possible implementation, the original brightness image comprises N pixels; the N pixels include pixel F. t Pixel F t It includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the image processing module is used to perform brightness mapping on the original brightness image according to the first image parameters, and when obtaining the mapped brightness image, it is specifically used to perform the following operations: Get pixel F t Brightness conversion values ​​in the original brightness image; A mapping curve for brightness mapping of the original brightness image is generated based on the first image parameters; Based on the mapping curve, pixel F t The brightness conversion value is mapped to obtain pixel F. t The corresponding luminance signal data; the luminance signal data corresponding to N pixels are used to construct the mapped luminance image corresponding to the original luminance image.

[0030] In one possible implementation, when the signal value generation module acquires the luminance signal data corresponding to the mapped luminance image, it specifically performs the following operations: Obtain the luminance mapping data contained in the mapped luminance image; the luminance mapping data is the luminance data in the linear original luminance domain; The signal parameters used for domain signal transformation between the original luminance domain and the perceived uniform target signal domain are obtained. Based on the signal parameters, the luminance mapping data is processed by nonlinear operation to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0031] In one possible implementation, the signal value generation module is also used to perform the following operations: The brightness mapping data is normalized to obtain normalized brightness data; Then, based on the signal parameters, nonlinear operations are performed on the luminance mapping data to obtain the luminance signal data of the mapped luminance image in the target signal domain, including: The normalized luminance data is processed nonlinearly based on the signal parameters to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0032] One embodiment of this application provides another image processing apparatus, including: The parameter generation module is used to acquire the original image, generate first image parameters for tone mapping from the original image, and generate second image parameters for color reconstruction from the original image. The data transmission module is used to encapsulate the first image parameters and the second image parameters into dynamic metadata, and send the original image and the dynamic metadata to the playback end. The dynamic metadata is used to instruct the playback end to perform brightness mapping on the original brightness image converted from the original image using the first image parameters to obtain a mapped brightness image. The dynamic metadata is also used to instruct the playback end to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameters, and to generate a target signal value based on the brightness signal data and color data items in the mapped brightness image. The signal difference refers to the difference in signal values ​​between the original image and the original brightness image. The target signal value is used to generate the reconstructed image corresponding to the original image.

[0033] In one possible implementation, when the parameter generation module generates first image parameters for tone mapping from the original image, it specifically performs the following operations: Obtain the first initial image parameters for tone mapping, and obtain the target image associated with the original image; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to obtain an original brightness image. The original brightness image is then mapped to obtain predicted brightness data based on the first initial image parameters. Perform brightness conversion on the target image to obtain a target brightness image containing the target brightness data; The first initial image parameters are adjusted based on the brightness difference between the predicted brightness data and the target brightness data to obtain the adjusted first initial image parameters. If the adjusted first initial image parameters satisfy the parameter convergence condition, then the adjusted first initial image parameters are determined as the first image parameters.

[0034] In one possible implementation, the parameter generation module is also used to perform the following operations: The original brightness data is remapped using the adjusted first initial image parameters to obtain new predicted brightness data; If the brightness difference between the new predicted brightness data and the target brightness data is within the error range, then the adjusted first initial image parameters are determined to meet the parameter convergence condition.

[0035] In one possible implementation, when the parameter generation module generates second image parameters for color reconstruction from the original image, it specifically performs the following operations: Obtain the target image and a second initial image parameter for color reconstruction; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to brightness to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first image parameters to obtain a mapped brightness image. The original image is then reconstructed based on the original brightness image, the mapped brightness image, and the second initial image parameters to obtain an intermediate target image. Obtain the original color attributes of the intermediate target image and the target color attributes of the target image. Extract features from the original color attributes to obtain the original attribute features, and extract features from the target color attributes to obtain the target attribute features. Similarity calculation is performed on the original attribute features and the target attribute features to obtain the attribute similarity between the original color attributes and the target color attributes. Based on the attribute similarity, the second initial image parameters are adjusted to obtain the adjusted second initial image parameters. If the original color attribute of the intermediate target image obtained by reconstructing the original image using the adjusted second initial image parameters has an attribute similarity greater than or equal to the target color attribute, then the adjusted second initial image parameters are determined as the second image parameters.

[0036] In one possible implementation, when the parameter generation module generates second image parameters for color reconstruction from the original image, it specifically performs the following operations: A second initial image parameter for color reconstruction is obtained, and the original image is reconstructed based on the first image parameter and the second initial image parameter to obtain a reconstructed image. The second initial image parameter includes a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. In response to the adjustment operation of the target sub-parameter among the first sub-parameter, second sub-parameter, and third sub-parameter, the reconstructed image is updated and displayed; the updated reconstructed image is obtained by updating the reconstructed image according to the adjusted second initial image parameters; the adjusted second initial image parameters include the adjusted target sub-parameter; In response to the confirmation operation for the updated reconstructed image, the adjusted second initial image parameters are determined as the second image parameters.

[0037] One embodiment of this application provides a computer device, including: a processor, a memory, and a network interface; The processor is connected to a memory and a network interface. The network interface is used to provide data communication functions, and the memory is used to store computer programs. When the computer program is executed by the processor, the computer device performs the method provided in the embodiments of this application.

[0038] One aspect of this application provides a computer-readable storage medium storing a computer program adapted to be loaded and executed by a processor, so that a computer device having the processor performs the method provided in this application.

[0039] One embodiment of this application provides a computer program product comprising a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the method provided in this application embodiment.

[0040] This application embodiment acquires an original image and dynamic metadata including first and second image parameters. It performs brightness conversion on the original image to obtain an original brightness image, then maps the original brightness image to obtain a mapped brightness image based on the first image parameters. By acquiring the signal difference between the original image and the original brightness image, color data items for adjusting the color attributes of the original image can be generated based on the signal difference and the second image parameters. Further, after acquiring the brightness signal data corresponding to the mapped brightness image, a target signal value can be generated based on the brightness signal data and the color data items. By using the signal difference between the original brightness image obtained from brightness conversion and the original image, and the second image parameters used for color reconstruction to generate color data items for adjusting the color attributes of the original image, the attribute differences between the original image and the original brightness image, as well as the color reconstruction effect brought by the second image parameters, can be effectively combined to improve the accuracy of color attribute reconstruction of the original image. In other words, it can improve the reconstruction effect presented by the reconstructed image generated based on the target signal value. Furthermore, the embodiments of this application not only reconstruct the brightness data of the original image based on the first image parameters, but also introduce the second image parameters to reconstruct and adjust the color attributes of the original image. This ensures that the generated reconstructed image is controllable in both brightness and color attributes, that is, the display effect of the reconstructed image in terms of brightness and color attributes can be controlled to meet the expected effect corresponding to the original image, thereby further improving the reconstruction effect presented by the reconstructed image. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this application; Figure 2 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 1 ; Figure 3 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 2 ; Figure 4 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 3 ; Figure 5 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 1 ; Figure 6 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 2 ; Figure 7 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 4 ; Figure 8 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 3 ; Figure 9 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 5 ; Figure 10 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 6 ; Figure 11 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of this application. Figure 1 ; Figure 12 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of this application. Figure 2 ; Figure 13 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0043] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0044] It is understood that in the specific embodiments of this application, user (object or player) data is involved, such as media data and configuration control points that can be provided by the user. When the above and below embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant regions.

[0045] If this application requires the collection of object data (such as user data), a prompt interface or pop-up window will be displayed before and during the collection process. This prompt interface or pop-up window is used to inform the user that certain data is being collected. The data acquisition steps will only begin after the user confirms the prompt interface or pop-up window; otherwise, the process will end. Furthermore, the acquired user data will be used in reasonable and legal scenarios or for legitimate purposes. Optionally, in scenarios where user data needs to be used but user authorization has not been obtained, authorization can be requested from the user, and the user data can only be used after authorization is granted.

[0046] The key terms and definitions used in this application are as follows: Signal value refers to a parameter in a specific dimension of an image standard, such as brightness, color depth, color space, and contrast. These image signals determine the range of brightness, color richness, and contrast that an image or video can display. Image standards include SDR and HDR. SDR is the traditional video standard, with strict upper limits on brightness, color, and contrast, and has been the mainstream standard for televisions, monitors, and DVDs (Digital Video Discs) / Blu-rays for the past few decades. HDR is a new generation video standard that significantly expands the brightness range, color space, and color depth, making the image closer to the real world as seen by the human eye. The image signals referred to in this application include, but are not limited to, the original linear domain image signals, image signals converted by the Opto-Electronic Transfer Function (OETF), or the Electro-Optical Transfer Function (EOTF), or the Opto-Optical Transfer Function (OOTF), and logarithmic domain image signals converted by logarithmic functions. The Opto-Electronic Transfer Functions include, but are not limited to, BT.709 (a high-definition television color standard), PQ (Perceptual Quantizer), HLG (Hybrid Log–Gamma), etc. The embodiments of this application are not limited herein.

[0047] The PQ domain is a non-linear signal coding domain defined by the SMPTE ST (Society of Motion Picture and Television Engineers) 2084 standard. It uses a special electro-optical conversion function to map absolute physical brightness values ​​(in nits) into digital signal values ​​that match the visual characteristics of the human eye, so as to reproduce more realistic and layered images on standard dynamic range (SDR) display devices.

[0048] Tone mapping parameters are a set of core control variables used to implement tone mapping operations. Essentially, they guide how to intelligently compress or map the wide brightness information of a high dynamic range (HDR) scene to the limited brightness range of a standard dynamic range (SDR) or another HDR display device using "rules" or "transformation functions". Tone mapping parameters typically define specific mapping curves, local contrast adjustment intensity, brightness compression ratio, and thresholds for retaining highlight / shadow details.

[0049] Color reconstruction parameters are a set of core control variables used to guide color transfer or stylization processing. They define how to systematically transform the color distribution (such as saturation, hue, and color balance) of the original image to a new state that matches the target image or style.

[0050] Brightness, in physics, refers to the intensity of light emitted from an image (measured in nits), while in perception it corresponds to the lightness or darkness perceived by the human eye. It is the most fundamental visual attribute of an image, directly determining the image's tone, detail (especially in shadows and highlights), contrast, and overall atmosphere.

[0051] In the embodiments of this application, please refer to Figure 1 , Figure 1 This is a schematic diagram of a network architecture provided in an embodiment of this application, such as... Figure 1 As shown in the diagram, the network architecture may include a service server 100, a terminal device 200, and a terminal device 300. The service server 100 may have a communication connection with the terminal devices 200 and 300. The communication connection is not limited to a specific method. It may be a direct or indirect connection via wired communication, a direct or indirect connection via wireless communication, or other methods. This application does not impose any restrictions on these methods.

[0052] Both terminal device 200 and terminal device 300 can be electronic devices, including but not limited to mobile phones, tablets, desktop computers, laptops, PDAs, in-vehicle devices, augmented reality / virtual reality (AR / VR) devices, head-mounted displays, smart TVs, wearable devices, smart speakers, digital cameras, webcams, and other mobile internet devices (MIDs) with network access capabilities, or terminal devices in scenarios such as trains, ships, and airplanes. The business server 100 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, vehicle-to-everything (V2X) communication, content delivery networks (CDNs), and big data and artificial intelligence platforms. It should be understood that, for example... Figure 1 The terminal devices 200 and 300 shown can be equipped with service applications. When the service application runs on terminal device 200 or terminal device 300, it can interact with the aforementioned... Figure 1 Data interaction is performed between the business servers 100 shown.

[0053] like Figure 1 As shown, terminal device 200 can be a production end, and terminal device 300 can be a playback end (or terminal device 200 can also be a playback end, and terminal device 300 can be a production end). The business server 100 can be a transmission component used for data transmission between terminal device 200 and terminal device 300. For example, when it obtains the upload data from terminal device 200 and the request initiated by terminal device 300, the business server 100 can send the upload data to terminal device 300. Terminal device 200 can create an original image (such as an HDR image containing image content) and a target image (such as an SDR image containing the same image content). Based on the original image and the target image, it sets or generates tone mapping parameters for tone mapping and color reconstruction parameters for color reconstruction (the tone mapping parameters and color reconstruction parameters can be used to reconstruct the original image to obtain an SDR reconstructed image that matches the target image). Furthermore, it can encapsulate the tone mapping parameters and color reconstruction parameters into dynamic metadata and send the original image and dynamic metadata to the business server 100. Terminal device 300 can initiate a playback request for the original image to the business server 100. The business server 100 can then send the original image and dynamic metadata to terminal device 300 according to the playback request (terminal device 300 may only support SDR image playback). Thus, terminal device 300 can perform operations such as decoding and data format conversion on the dynamic metadata to obtain tone mapping parameters and color reconstruction parameters, generate an SDR reconstructed image based on the tone mapping parameters and color reconstruction parameters, and display the SDR reconstructed image through terminal device 300. It is understandable that if the original image includes every frame of an original video, then each frame can have corresponding dynamic metadata. Furthermore, based on the dynamic metadata corresponding to each frame, each frame can be reconstructed, and the reconstructed image corresponding to each frame can be played through the terminal device 200, thus achieving the effect of reconstructing the entire original video.

[0054] Please see also Figure 2 , Figure 2 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 1 .like Figure 2As shown, terminal device 200 can upload original images and dynamic metadata to service server 100. Terminal device 300 can obtain the original images and dynamic metadata sent by service server 100 by sending a request. The dynamic metadata can include a first image parameter (i.e., tone mapping parameter) for tone mapping and a second image parameter (i.e., color reconstruction parameter) for color reconstruction. By performing brightness conversion on the original image (e.g., weighted summation of pixel components under different color channels), an original brightness image can be obtained (each pixel can be used to represent a brightness conversion value). Brightness mapping is then performed on the original brightness image according to the first image parameter (e.g., through the first image parameter corresponding to the brightness conversion parameter). The luminance mapping function performs a mapping operation on the luminance conversion value of the original luminance image to obtain a mapped luminance image (where each pixel can be used to represent a luminance signal data). If the original image, the original luminance image, and the mapped luminance image are not in the target signal domain (such as the PQ domain), then all three images can be converted to the target signal domain first, and then the signal difference between the original image and the original luminance image can be obtained (such as the difference between the pixel component of each color channel in the original image in the target signal domain and the luminance conversion value of the original luminance image in the target signal domain). Alternatively, the difference between the original image and the original luminance image in the non-target signal domain can be obtained first, and then the difference can be converted to the target signal domain to obtain the signal difference. If the original image, the original brightness image, and the mapped brightness image are all images in the target signal domain—that is, the original brightness image is obtained by weighted summation of the pixel components of different color channels of the original image in the target signal domain, and the mapped brightness image is obtained by brightness mapping based on the original brightness image in the target signal domain; or, the original brightness image is obtained by weighted summation of the pixel components of different color channels of the original image and then converted to the target signal domain, and the mapped brightness image is obtained by brightness mapping based on the original brightness image and then converted to the target signal domain—then the signal difference between the original image and the original brightness image in the target signal domain can be directly obtained. Further, the luminance signal data corresponding to the mapped luminance image (specifically, the luminance signal data in the target signal domain) can be obtained. After generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters (such as weighted summation), a target signal value can be generated based on the luminance signal data and the color data items. The target signal value can include the signal values ​​of multiple color channels in the target signal domain. By performing domain signal transformation on the signal values ​​of multiple color channels (such as performing inverse PQ transformation to obtain linear pixel components in the original luminance domain), the terminal device 300 can render and display the reconstructed image based on the pixel components after domain signal transformation.

[0055] Please see also Figure 3 , Figure 3This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 2 .like Figure 3 As shown, one applicable scenario for this application embodiment is as follows: When creating image or video content, the terminal device 200 (the production end) can use an automated algorithm to generate baseline versions of tone mapping parameters and color reconstruction parameters (as the basis for further manual adjustments by the creator). For example, the production end has already created an HDR original image (which can be displayed on an HDR display). Then, the original image is reconstructed according to the tone mapping parameters and color reconstruction parameters to obtain an SDR target image. The processed SDR target image can be displayed in real time on an SDR display. Furthermore, the video creator (such as the production object) can continuously adjust and optimize the two parameters (i.e., tone mapping parameters and color reconstruction parameters) according to the real-time rendering of the SDR display. When the image effect of the target image reconstructed according to the adjusted two parameters reaches the expected level (i.e., it has the image effect of displaying the original image on an HDR display), the adjusted two parameters can be encapsulated into dynamic metadata. The original image and dynamic metadata are then sent to the terminal device 300 (i.e., the playback end). The terminal device 300 can then reconstruct the original image according to the tone mapping parameters and color reconstruction parameters in the dynamic metadata to display the SDR reconstructed image on an SDR display.

[0056] Please see also Figure 4 , Figure 4 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 3 .like Figure 4 As shown, another scenario applicable to this application embodiment is as follows: When creating image or video content, the terminal device 200 (i.e., the production end) can acquire two versions of image or video content created for the production object, such as an HDR original image and an SDR target image with the same image content (the HDR original image displayed on an HDR display has the same picture effect as the SDR target image displayed on an SDR display). Then, based on an automated algorithm, tone mapping parameters and color reconstruction parameters associated with the original image and the target image are directly generated. For example, under a specific quality loss assessment method, an optimization algorithm is used to select tone mapping parameters and color reconstruction parameters that minimize the quality loss between the reconstructed image (i.e., the image obtained after tone mapping and color reconstruction processing of the original image using tone mapping parameters and color reconstruction parameters) and the target image. Then, the terminal device 200 can send the original image and dynamic metadata containing tone mapping parameters and color reconstruction parameters to the terminal device 300. The terminal device 300 can then reconstruct the original image based on the tone mapping parameters and color reconstruction parameters in the dynamic metadata to display the SDR reconstructed image on the SDR display.

[0057] Optionally, terminal device 200 can also create SDR original image and HDR target image, and synchronously generate tone mapping parameters and color reconstruction parameters for converting SDR image to HDR image. Then, by sending SDR original image, tone mapping parameters and color reconstruction parameters to business server 100, and by business server 100 sending SDR original image, tone mapping parameters and color reconstruction parameters to terminal device 300 (at this time, HDR image playback is supported), terminal device 300 can reconstruct SDR original image into HDR reconstructed image according to tone mapping parameters and color reconstruction parameters.

[0058] It is understood that by using the signal difference between the original brightness image (obtained through brightness conversion of the original image) and the original image, and combining this signal difference with the second image parameters used for color reconstruction to generate color data items for adjusting the color attributes of the original image, the color reconstruction effect brought about by the attribute differences between the original image and the original brightness image, as well as the color reconstruction effect brought about by the second image parameters, can be effectively combined to improve the accuracy of reconstructing the color attributes of the original image. This means that the reconstruction effect presented by the reconstructed image generated based on the target signal value can be improved. Furthermore, this embodiment not only reconstructs the brightness data of the original image based on the first image parameters but also introduces the second image parameters to reconstruct and adjust the color attributes of the original image. This ensures that the generated reconstructed image is controllable in both brightness and color attributes, meaning that the display effect of the reconstructed image in terms of brightness and color attributes can be controlled to match the expected effect corresponding to the original image, thereby further improving the reconstruction effect presented by the reconstructed image.

[0059] Please see Figure 5 , Figure 5 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 1 This image processing method can be executed by a computer device, which can be, for example, Figure 1 The terminal device 200 or terminal device 300 shown; the computer device may also be as follows Figure 1 The service server 100 shown can send the original image and dynamic metadata to the terminal device 200. The service server 100 can generate a target signal value through the following steps S101 to S104, and send the target signal value to the terminal device 300. The terminal device 300 can then generate and display a reconstructed image based on the target signal value. The following description will use a computer device as the terminal device 300 as an example. This image processing method can include at least the following steps S101-S104: Step S101: Obtain the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. Specifically, the computer device can acquire dynamic metadata and the original image (such as an HDR image) including parameters such as the first image parameter (i.e., tone mapping parameter) and the second image parameter (i.e., color reconstruction parameter). If the first image parameter and the second image parameter are dynamic metadata encapsulated in the original image (such as an MP4 file or atom of a bitstream in HEVC (High Efficiency Video Coding)), then the dynamic metadata can be decoded and processed (such as floating-point conversion) to obtain the first image parameter for tone mapping and the second image parameter for color reconstruction.

[0060] Step S102: Perform brightness conversion on the original image to obtain the original brightness image; perform brightness mapping on the original brightness image according to the first image parameters to obtain the mapped brightness image. Specifically, computer devices can assign luminance conversion weights to multiple color channels (such as the R, G, and B channels in RGB (Red, Green, and Blue) mode) under each pixel of the original image (e.g., the luminance conversion weight of the R channel in the BT.2020 color gamut is 0.2627). Then, the pixel components (such as R, G, and B components) corresponding to the multiple color channels under each pixel are weighted and summed with their corresponding luminance conversion weights to obtain the luminance conversion value for each pixel. The original luminance image can be constructed by using the luminance conversion values ​​corresponding to all pixels. Furthermore, the computer device can perform brightness mapping on the original brightness image in various ways based on the first image parameters. For example, it can generate a mapping curve for brightness mapping of the original brightness image (the horizontal axis of the mapping curve can represent the brightness conversion value in the original brightness image, and the vertical axis can represent the brightness signal data after brightness mapping). Then, by taking the brightness conversion value of each pixel in the original brightness image as the horizontal axis, the corresponding brightness signal data can be obtained in the mapping curve (i.e., brightness mapping of the original brightness image). The mapped brightness image corresponding to the original brightness image can be constructed by using the brightness signal data of all pixels.

[0061] Step S103: Obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters; Specifically, if neither the original image nor the original luminance image is in the target signal domain (such as the PQ domain), both images can be converted to the target signal domain first, and then the signal difference between the original image and the original luminance image can be obtained (such as the difference between the pixel component of each color channel in the original image in the target signal domain and the luminance conversion value in the original luminance image in the target signal domain). Alternatively, the difference between the original image and the original luminance image in the non-target signal domain can be obtained first, and then the difference can be converted to the target signal domain to obtain the signal difference.

[0062] If both the original image and the original brightness image are images in the target signal domain, such as the original brightness image being obtained by weighted summation of the pixel components of different color channels of the original image in the target signal domain, then the signal difference between the original image and the original brightness image in the target signal domain can be directly obtained. The second image parameters include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. A first sub-item can be generated based on the signal difference of each color channel and the first sub-parameter, and a second sub-item can be generated based on the signal difference of each color channel and the second sub-parameter (both the first and second sub-items are used to adjust the color attributes of the original image). The sum of the first, second, and third sub-parameters determines the color data item corresponding to each color channel.

[0063] Step S104: Obtain the luminance signal data corresponding to the mapped luminance image, and generate a target signal value based on the luminance signal data and color data items; the target signal value is used to generate the reconstructed image corresponding to the original image.

[0064] Specifically, if the mapped luminance image is not an image in the target signal domain, the computer device can first acquire the luminance mapping data in the linear original luminance domain (such as the signal space under physical light intensity, such as the BT.2020 color gamut, AP0 or AP1 linear space, etc.) of the mapped luminance image, and convert the signal parameters based on the domain signal transformation between the original luminance domain and the target signal domain to obtain the luminance signal data in the target signal domain. Further, by summing the luminance signal data and the color data items under each color channel of the original image, the channel component signal values ​​corresponding to each color channel can be obtained. The channel component signal values ​​corresponding to each color channel can form the target signal value used to generate the reconstructed image. That is, the target signal value can include the channel component signal values ​​of multiple color channels in the target signal domain. By performing domain signal transformation on the channel component signal values ​​of multiple color channels (such as performing inverse PQ transformation), the pixel components in the linear original luminance domain are obtained. Then, the pixel value of each pixel in the reconstructed image can be constructed based on the pixel components after domain signal transformation under multiple color channels. The reconstructed image can be rendered using these pixel values. It is understandable that if the original image is an HDR image, the reconstructed image can be an SDR image, and similarly, if the original image is an SDR image, the reconstructed image can be an HDR image. If the original image includes every frame of an original video, then each frame can have corresponding dynamic metadata. Furthermore, based on the dynamic metadata corresponding to each frame, each frame can be reconstructed, and thus the reconstructed image corresponding to each frame can be played through the terminal device 200, thereby achieving the effect of reconstructing the entire original video.

[0065] This application embodiment acquires an original image and dynamic metadata including first and second image parameters. It performs brightness conversion on the original image to obtain an original brightness image, then maps the original brightness image to obtain a mapped brightness image based on the first image parameters. By acquiring the signal difference between the original image and the original brightness image, color data items for adjusting the color attributes of the original image can be generated based on the signal difference and the second image parameters. Further, after acquiring the brightness signal data corresponding to the mapped brightness image, a target signal value can be generated based on the brightness signal data and the color data items. By using the signal difference between the original brightness image obtained from brightness conversion and the original image, and the second image parameters used for color reconstruction to generate color data items for adjusting the color attributes of the original image, the attribute differences between the original image and the original brightness image, as well as the color reconstruction effect brought by the second image parameters, can be effectively combined to improve the accuracy of color attribute reconstruction of the original image. In other words, it can improve the reconstruction effect presented by the reconstructed image generated based on the target signal value. Furthermore, the embodiments of this application not only reconstruct the brightness data of the original image based on the first image parameters, but also introduce the second image parameters to reconstruct and adjust the color attributes of the original image. This ensures that the generated reconstructed image is controllable in both brightness and color attributes, that is, the display effect of the reconstructed image in terms of brightness and color attributes can be controlled to meet the expected effect corresponding to the original image, thereby further improving the reconstruction effect presented by the reconstructed image.

[0066] Please see Figure 6 , Figure 6 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 2 This image processing method can be executed by a computer device, which can be, for example, Figure 1 The terminal device 200 or terminal device 300 shown; the computer device may also be as follows Figure 1 The service server 100 shown can send the original image and dynamic metadata to the terminal device 300. The service server 100 can generate a target signal value through the following steps S201 to S204, and send the target signal value to the terminal device 300. The terminal device 300 can then generate and display a reconstructed image based on the target signal value. The following description will use a computer device as the terminal device 300 as an example. This image processing method can include at least the following steps S201-S204: Step S201: Obtain the original image and dynamic metadata; the original image includes N pixels; the N pixels include pixel F. t Get pixel F t Includes the brightness conversion weights corresponding to the M color channels; and assigns the pixel F... tThe pixel component corresponding to each of the M color channels is weighted and summed with the luminance conversion weight corresponding to each of the M color channels to obtain the pixel F. t The corresponding brightness conversion values; the brightness conversion values ​​corresponding to N pixels are used to construct the original brightness image corresponding to the original image; For details, please refer to the following: Figure 7 , Figure 7 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 4 .like Figure 7 As shown, a computer device can acquire an original image containing N pixels and dynamic metadata. The dynamic metadata can include first image parameters for tone mapping and second image parameters (i.e., color reconstruction parameters) for color reconstruction, and can be encapsulated within the original image. By decoding and converting the dynamic metadata (e.g., converting fixed-point numbers to floating-point numbers), the first image parameters (i.e.,...) can be obtained. Figure 7 The image shown obtains tone mapping parameters and second image parameters (i.e., Figure 7 The parameters for obtaining color reconstruction are shown. Computer equipment can perform brightness conversion on the original image (i.e., perform...). Figure 7 The image shown is a calculated brightness image, such as for pixel F out of N pixels. t (Including the pixel components corresponding to M color channels, where M and N are positive integers, and t is a positive integer less than or equal to N), pixel point F can be obtained. t The brightness conversion weights for the M color channels are given. Taking an image in the BT.2020 color gamut, with M color channels including R, G, and B channels, as an example, the brightness conversion weights for the R, G, and B channels are 0.2627, 0.6780, and 0.0593, respectively. Further calculations can then be made for pixel F. t The product of the luminance conversion weights corresponding to the R color channel and the pixel components corresponding to the R color channel, the product of the luminance conversion weights corresponding to the G color channel and the pixel components corresponding to the G color channel, and the product of the luminance conversion weights corresponding to the B color channel and the pixel components corresponding to the B color channel are all used to obtain the pixel F. t The specific process for converting the brightness values ​​for the three color channels can be shown in the following formula (1): Formula (1) Where i is pixel F t In the original image, the x-coordinate is j, where pixel F is... t The vertical axis in the original image, Represents pixel F tThe pixel components of the R color channel, Represents pixel F t The pixel components of the G color channel, Represents pixel F t The pixel components of the B color channel, then This can be represented by a weighted sum of the pixel components corresponding to each of the three color channels and the corresponding luminance conversion weights. The resulting luminance conversion value can be obtained by similarly weighting the pixel F. t The pixel component corresponding to each of the M color channels is weighted and summed with the luminance conversion weight corresponding to each of the M color channels to obtain the pixel F. t Furthermore, based on the above calculation process, after obtaining the brightness conversion values ​​corresponding to N pixels, the original brightness image corresponding to the original image can be constructed based on the brightness conversion values ​​corresponding to N pixels.

[0067] Step S202: Perform brightness mapping on the original brightness image according to the first image parameters to obtain a mapped brightness image; Specifically, the original brightness image may include N pixels, and the N pixels include pixel F. t Pixel F t Including the pixel components corresponding to M color channels (M and N are positive integers, and t is a positive integer less than or equal to N), the computer device can perform brightness mapping (i.e., perform...) on the original brightness image based on the first image parameters obtained in step S201 above. Figure 7 The tone mapping shown can be specifically described as follows: obtaining pixel F t The brightness conversion value in the original brightness image; generating a mapping curve for brightness mapping of the original brightness image based on the first image parameters; and applying the mapping curve to pixel F. t The brightness conversion value is mapped to obtain pixel F. t The corresponding luminance signal data; the luminance signal data corresponding to each of the N pixels are used to construct the mapped luminance image corresponding to the original luminance image. For example, for pixel F among the N pixels included in the original luminance image... t It can obtain pixel F t The brightness conversion value in the original brightness image (the specific calculation process of the brightness conversion value can be found in the relevant description of formula (1) in step S201), and then a mapping curve for brightness mapping of the original brightness image is generated according to the first image parameters. Based on the mapping function (i.e. the mapping curve), the pixel F is... t The brightness conversion value is mapped to obtain pixel F. t The corresponding luminance signal data, the specific process of which can be shown in the following formula (2): Formula (2) in, This represents the tone mapping parameters (i.e., the first image parameters). Indicates the brightness conversion value. Represents the mapping function (tone mapping algorithm). Represents luminance signal data, where the mapping function... The specific form can be determined by tone mapping parameters. Determine, for example, when the tone mapping parameters When representing slope, the mapping function It can be a linearly scaling proportional function (then the mapping curve is a straight line passing through the origin); when the tone mapping parameters When representing an exponent, the mapping function An exponential function that can be gamma-calibrated (with an exponentially shaped mapping curve) is optional; the mapping function... It can also be a Logistic function (with an S-shaped mapping curve), a piecewise function, etc., without limitation. By using pixel F... t The brightness conversion value is fed into the mapping function, and the resulting function value can be used as the pixel value F. t The corresponding luminance signal data can be used to calculate the luminance signal data corresponding to N pixels. Thus, the mapped luminance image corresponding to the original luminance image can be constructed from the luminance signal data corresponding to N pixels.

[0068] Step S203: Obtain the signal difference between the original image and the original brightness image; generate a first sub-item for adjusting the chromaticity deviation of the original image based on the signal difference and the first sub-parameter; generate a second sub-item for adjusting the color contrast of the original image based on the signal difference and the second sub-parameter; and determine the sum of the first sub-item, the second sub-item and the third sub-parameter as the color data item for adjusting the color attributes of the original image. Specifically, each pixel in the original image includes pixel components corresponding to M color channels. The second image parameters include second image parameters corresponding to the M color channels. Each second image parameter corresponding to a color channel can include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. For example, it can include the first sub-parameter under the R color channel. Second sub-parameter and the third sub-parameter The first sub-parameter under the G color channel Second sub-parameter and the third sub-parameter and the first sub-parameter under the B color channel. Second sub-parameter and the third sub-parameter The computer equipment can acquire the signal difference between the original image and the original brightness image, and then generate color data items to adjust the color attributes (including chromaticity deviation, color contrast, and color balance) of the original image based on the signal difference and the second image parameters, using M color channels including K color channels. h (M is a positive integer, and h is a positive integer less than or equal to M) Taking this as an example, the specific process can be: based on the color channels K in the original image h The difference between the pixel components below and the luminance transformation values ​​contained in the original luminance image is used to generate the color channel K. h The corresponding signal difference; based on color channel K h The corresponding signal difference and color channel K h The corresponding second image parameters generate color channel K. h The corresponding color data item.

[0069] For example, color channel K h For the R color channel, computer devices can acquire the pixel values ​​in the original image. t Pixel components under the R color channel Then obtain the same coordinates (and the pixel point F, which is the same as the original brightness image) as the original image. t Luminance transformation values ​​with the same coordinates, i.e., coordinates (i,j). This allows the pixel components to be... Conversion value with brightness The difference between , determined to be pixel F t The signal difference under the R color channel (i.e., performing) Figure 7 (The difference calculation shown in the operation component 711), and if neither the original image nor the original brightness image is an image in the target signal domain, then both images can be converted to the target signal domain first (i.e., perform...). Figure 7 The signal transformation shown above is used to obtain the signal difference between the original image and the original brightness image. Alternatively, the difference between the original image and the original brightness image in the non-target signal domain can be obtained first, and then the difference can be transformed to the target signal domain to obtain the signal difference. Further, the color data item corresponding to the R color channel can be generated based on the signal difference corresponding to the R color channel and the second image parameters corresponding to the R color channel. For example, the signal difference can be... The first sub-parameter under the R color channel Product between It was determined to be used to adjust the pixel points F in the original image. t The first sub-item of the chromaticity deviation corresponding to the R color channel; by the signal difference Perform the squaring operation to obtain the squared terms. The squared terms data can be used The second sub-parameter under the R color channel Product between It was determined to be used to adjust the pixel points F of the original image. t The second sub-item corresponding to the color contrast of the R color channel, thus, can be used to determine the first sub-item. Second sub-item and the third sub-parameter The sum is determined as the value used to adjust the original image pixel points F. t The color data item corresponding to the color attribute of the R color channel, i.e. Similarly, the color data items corresponding to the M color channels of all pixels in the original image can be calculated. When adjusting the color attributes of the original image, the chromaticity deviation (the difference in hue and saturation between colors in the image) can be adjusted by adjusting the first sub-parameter in the first sub-item (such as the color difference parameter); the color contrast (the visual difference or separation between different colors in the image) can be adjusted by adjusting the second sub-parameter in the second sub-item (such as the Michelson color contrast parameter); and the color balance (the visual harmony and balance of different color regions in the image) can be adjusted by adjusting the third sub-parameter in the color data item (such as the white point error under the color channel).

[0070] Step S204: Obtain the luminance signal data corresponding to the mapped luminance image, and sum the luminance signal data and color data to obtain the target signal value used to generate the reconstructed image.

[0071] Specifically, the process by which a computer device acquires luminance signal data corresponding to a mapped luminance image can be as follows: acquiring luminance mapping data contained in the mapped luminance image; the luminance mapping data being linear luminance data in the original luminance domain; acquiring signal parameters for performing domain signal transformation between the original luminance domain and the perceived uniform target signal domain; and performing nonlinear operations on the luminance mapping data based on the signal parameters to obtain the luminance signal data of the mapped luminance image in the target signal domain. For example, according to the SMPTE ST 2084 standard, the luminance mapping data contained in each pixel of the mapped luminance image can be acquired first (this can be linear luminance data in the original luminance domain; if the data range is too large (e.g., between 0 nits and 10000 nits), normalization can be performed), and then the luminance mapping data for performing domain signal transformation between the original luminance domain and the perceived uniform target signal domain can be acquired. Figure 7 The signal parameters for the domain signal transformation shown are as follows: , , , , The brightness mapping data can be processed nonlinearly using signal parameters. The specific process is shown in the following formula (3): Formula (3) Where Y represents the brightness mapping data, To map the luminance signal data of the luminance image into the target signal domain, the luminance signal data and color data items are summed. For example, the color data item corresponding to each color channel is summed with the luminance signal data to obtain the channel component signal value corresponding to each color channel. Then, the target signal value used to generate the reconstructed image can be composed based on the channel component signal values ​​corresponding to each color channel. For example, for pixel F in the original image... t The R color channel can be used to store the color data items corresponding to the R color channel. , and pixel F t Corresponding brightness signal data Perform summation to obtain pixel F. t The specific process of the channel component signal value corresponding to the R color channel can be shown in the following formula (4): Formula (4) in, Represents pixel F t The channel component signal value corresponding to the R color channel can be calculated by analogy. Similarly, the channel component signal values ​​corresponding to the M color channels for all pixels in the original image can be calculated. Likewise, the channel component signal values ​​for pixel F can be obtained. t The process of obtaining the channel component signal value corresponding to the G color channel can be shown by the following formula (5) to obtain the pixel point F. t The process of determining the channel component signal value corresponding to the B color channel can be shown by the following formula (6): Formula (5) Formula (6) in, Represents pixel F t The channel component signal value corresponding to the G color channel. Represents pixel F t The channel component signal value corresponding to the B color channel. Represents pixel F t The pixel components under the G color channel, Represents pixel F t The pixel components under the B color channel. Computer equipment can assemble the target signal value (such as pixel F) for the original image based on the signal values ​​of all channel components. tThe corresponding target signal values ​​can include the channel component signal values ​​of the R color channel, the G color channel, and the B color channel. That is, the target signal values ​​can include the channel component signal values ​​of multiple color channels in the target signal domain. By performing domain signal transformation on the channel component signal values ​​of multiple color channels (such as performing inverse PQ transform), the pixel components in the linear original luminance domain are obtained. Then, the pixel values ​​of each pixel in the reconstructed image can be constructed based on the pixel components after domain signal transformation of multiple color channels. The reconstructed image can then be rendered using these pixel values. It can be understood that if the original image is an HDR image, the reconstructed image can be an SDR image; similarly, if the original image is an SDR image, the reconstructed image can be an HDR image. If the original image includes every frame of an original video, then each frame can have corresponding dynamic metadata. Furthermore, based on the dynamic metadata corresponding to each frame, each frame can be reconstructed, thus allowing the playback of the reconstructed image corresponding to each frame, achieving the effect of reconstructing the entire original video.

[0072] This application embodiment acquires an original image and dynamic metadata including first and second image parameters. It performs brightness conversion on the original image to obtain an original brightness image, then maps the original brightness image to obtain a mapped brightness image based on the first image parameters. By acquiring the signal difference between the original image and the original brightness image, color data items for adjusting the color attributes of the original image can be generated based on the signal difference and the second image parameters. Further, after acquiring the brightness signal data corresponding to the mapped brightness image, a target signal value can be generated based on the brightness signal data and the color data items. By using the signal difference between the original brightness image obtained from brightness conversion and the original image, and the second image parameters used for color reconstruction to generate color data items for adjusting the color attributes of the original image, the attribute differences between the original image and the original brightness image, as well as the color reconstruction effect brought by the second image parameters, can be effectively combined to improve the accuracy of color attribute reconstruction of the original image. In other words, it can improve the reconstruction effect presented by the reconstructed image generated based on the target signal value. Furthermore, the embodiments of this application not only reconstruct the brightness data of the original image based on the first image parameters, but also introduce the second image parameters to reconstruct and adjust the color attributes of the original image. This ensures that the generated reconstructed image is controllable in both brightness and color attributes, that is, the display effect of the reconstructed image in terms of brightness and color attributes can be controlled to meet the expected effect corresponding to the original image, thereby further improving the reconstruction effect presented by the reconstructed image.

[0073] Furthermore, by adjusting the chromaticity deviation of the original image using the first sub-parameter of the second image parameters, adjusting the color contrast of the original image using the second sub-parameter, and adjusting the color balance of the original image using the third sub-parameter, it can be ensured that the color attributes of the generated reconstructed image are controllable. By further combining the brightness data of the original image with the first image parameters for reconstruction and adjustment, it can be ensured that the brightness of the generated reconstructed image is also controllable. This ensures that the display effect of the reconstructed image in terms of brightness and color attributes is consistent with the display effect of the original image in the production end, thereby improving the reconstruction effect presented by the reconstructed image.

[0074] Please see Figure 8 , Figure 8 This is a flowchart illustrating an image processing method provided in an embodiment of this application. Figure 3 This image processing method can be executed by a computer device, which can be, for example, Figure 1 The terminal device 200 or terminal device 300 shown; the computer device may also be as follows Figure 1 The business server 100 shown can generate dynamic metadata through the following steps S301 to S302 to send the dynamic metadata to the terminal device 300; the following description will use a computer device as the terminal device 200 as an example. The image processing method can include at least the following steps S301-S302: Step S301: Obtain the original image, generate first image parameters for tone mapping using the original image, and generate second image parameters for color reconstruction using the original image. For details, please refer to the following: Figure 9 , Figure 9 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 5 .like Figure 9As shown, after acquiring the original image, if the computer device can further acquire the target image associated with the original image (e.g., if the original image is an HDR image containing image content, the target image can be an SDR image containing the same image content), then the first image parameters for tone mapping can be obtained by fitting the original image and the target image using an optimization method. The specific process can be: acquiring the first initial image parameters for tone mapping, and acquiring the target image associated with the original image; the original image and the target image have the same image content, and the color dynamic range between the original image and the target image is different (e.g., if the original image is an HDR image, then...). The target image can be an SDR image; similarly, if the original image is an SDR image, the target image can be an HDR image. The original image undergoes brightness conversion to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first initial image parameters to obtain predicted brightness data. The target image undergoes brightness conversion to obtain a target brightness image containing the target brightness data. The first initial image parameters are adjusted based on the brightness difference between the predicted brightness data and the target brightness data to obtain adjusted first initial image parameters. If the adjusted first initial image parameters satisfy the parameter convergence condition, then the adjusted first initial image parameters are determined as the first image parameters.

[0075] For example, a computer device can set or generate first initial image parameters for tone mapping using a model (i.e., to perform tone mapping). Figure 9 The generated tone mapping parameters are shown, and the original image undergoes a brightness transformation (i.e., a process is performed). Figure 9 The calculated brightness image shown can be used to obtain the original brightness image (the specific process can be found above). Figure 4 (In the corresponding embodiment, regarding the specific description of performing brightness conversion on the original image to obtain the original brightness image), the original brightness image is brightness mapped according to the first initial image parameters (i.e., performing...) Figure 9 The tone mapping shown above can be used to obtain predicted brightness data (the specific process can be found above). Figure 4 (The corresponding embodiment describes the luminance mapping of the original luminance image based on the first image parameters to obtain the mapped luminance image). Similarly, the target image can be luminance converted to obtain a target luminance image containing the target luminance data. (If the original image, the mapped luminance image, or the target luminance image is not in the target signal domain (such as the PQ domain), then the original image, the mapped luminance image, and the target luminance image can be first processed.) Figure 9 The domain signal transformation shown can be further used to determine the brightness difference between the predicted brightness data and the target brightness data (e.g., based on the domain signal transformation). Figure 9The difference calculation function provided by the computing component 912 can calculate the brightness difference and the mean square error (in the Zth round). In this way, the first initial image parameters in the Zth round are adjusted iteratively using optimization methods such as gradient descent to obtain the adjusted first initial image parameters in the Z+1th round. Based on the adjusted first initial image parameters, the original brightness data can be remapped to obtain new predicted brightness data. The error data in the Z+1th round can be calculated based on the brightness difference between the new predicted brightness data and the target brightness data. This process continues until the adjusted first initial image parameters meet the parameter convergence condition. If the brightness difference obtained based on the first initial image parameters is within the error range, or the calculated error data is less than or equal to the error threshold, or the number of iterations reaches the number threshold, the adjusted first initial image parameters of that iteration round can be determined as the first image parameters.

[0076] Optionally, if the computer device is unable to acquire or generate the target image, the first image parameters can also be generated by other static or dynamic methods. For example, the first image parameters can be determined by manual setting or by using a static tone mapping algorithm. Alternatively, the first image parameters can be generated by configuring a color gamut mapping algorithm with dynamic parameters or by using AI (Artificial Intelligence) methods such as large language models, based on different levels of image content such as video clips, image sequences, image frames, and image windows. This application does not impose any limitations on these methods.

[0077] Furthermore, if the computer device can acquire the target image associated with the original image, the original image and the target image can be fitted using optimization methods to obtain second image parameters for color reconstruction. The specific process can be as follows: acquire the target image and second initial image parameters for color reconstruction; the original image and the target image have the same image content, and the color dynamic ranges of the original image and the target image are different; perform brightness conversion on the original image to obtain the original brightness image; perform brightness mapping on the original brightness image according to the first image parameters to obtain the mapped brightness image; reconstruct the original image according to the original brightness image, the mapped brightness image, and the second initial image parameters to obtain the intermediate target image; acquire the intermediate target image. The original color attributes of the image and the target color attributes of the target image are obtained by extracting features from the original color attributes to obtain original attribute features and from the target color attributes to obtain target attribute features. Similarity calculation is performed on the original attribute features and target attribute features to obtain the attribute similarity between the original color attributes and the target color attributes. Based on the attribute similarity, the second initial image parameters are adjusted to obtain the adjusted second initial image parameters. If the attribute similarity between the original color attributes corresponding to the intermediate target image obtained by reconstructing the original image using the adjusted second initial image parameters and the target color attributes is greater than or equal to the similarity threshold, then the adjusted second initial image parameters are determined as the second image parameters.

[0078] For example, second initial image parameters for color reconstruction can be obtained through manual setting or AI generation. By performing brightness conversion on the original image, an original brightness image is obtained. Then, based on the first image parameters, the original brightness image is brightness mapped to obtain a mapped brightness image. After obtaining the mapped brightness image, the original image can be reconstructed based on the original brightness image, the mapped brightness image, and the second initial image parameters to obtain an intermediate target image. The specific process can be found above. Figure 6The specific descriptions of performing brightness conversion on the original image to obtain an original brightness image, mapping the original brightness image to obtain a mapped brightness image based on the first image parameters, and generating a reconstructed image in the corresponding embodiment are not repeated here. The computer device can extract the original color attributes of the intermediate target image and the target color attributes of the target image. Furthermore, it can perform feature extraction on the original color attributes using a large language model to obtain original attribute features, and on the target color attributes to obtain target attribute features. By performing similarity calculations on the original and target attribute features, the attribute similarity between the original and target color attributes can be obtained. For example, the dot product between the original and target attribute features can be calculated using cosine similarity. Further normalization of the moduli of the original and target attribute features allows for the calculation of the product of their moduli, as well as the ratio of the dot product to the moduli product. This ratio is then used as the attribute similarity between the original and target color attributes. The second initial image parameters can be iteratively adjusted to obtain the adjusted second initial image parameters. This process continues until the attribute similarity between the original color attribute of the intermediate target image reconstructed from the original image using the adjusted second initial image parameters is greater than or equal to a similarity threshold (e.g., 0.7). At this point, the second initial image parameters for this iteration can be determined as the second image parameters (i.e., ...). Figure 9 The generated color reconstruction parameters are shown.

[0079] Understandable, please refer to the above as well. Figure 10 , Figure 10 This is a schematic diagram of an image processing scenario provided in an embodiment of this application. Figure 6 .like Figure 10 As shown, if the computer device cannot obtain the target image associated with the original image, a second image parameter for color reconstruction can be determined through dynamic interaction. The specific process can be as follows: obtain the second initial image parameter for color reconstruction; reconstruct the original image based on the first image parameter and the second initial image parameter to obtain a reconstructed image; the second initial image parameter includes a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance; in response to adjustment operations on the target sub-parameter among the first, second, and third sub-parameters, update the reconstructed image; the updated reconstructed image is obtained by updating the reconstructed image based on the adjusted second initial image parameter; the adjusted second initial image parameter includes the adjusted target sub-parameter; in response to a confirmation operation on the updated reconstructed image, determine the adjusted second initial image parameter as the second image parameter.

[0080] For example, after acquiring the second initial image parameters for color reconstruction, the computer device can perform reconstruction rendering and other processes on the original HDR image based on the first and second initial image parameters to obtain an SDR reconstructed image. Furthermore, by responding to the production object on the production end, adjustments can be made on page 1111 to the target sub-parameters (any one or more of the three sub-parameters) of the first, second, and third sub-parameters in the second initial image parameters. This allows the SDR reconstructed image to be updated and displayed on page 1112 (of an SDR display or similar device). For example, by responding to adjustments to the first and second sub-parameters... The fidelity and detail of color reproduction in the SDR reconstructed image can be updated. By responding to adjustments to the first sub-parameter, the color saturation of the SDR reconstructed image can be updated to meet personalized needs. By responding to adjustments to the third sub-parameter, the offset of pixel components in one or more color channels of the SDR reconstructed image can be changed to achieve artistic effects such as adjusting color temperature, hue, and image style. Furthermore, by responding to a confirmation operation (i.e., a trigger operation on control 1113) on the updated SDR reconstructed image (in devices such as SDR displays), the adjusted second initial image parameters can be determined as the second image parameters. Optionally, the second image parameters can also be determined through manual setting or AI generation, etc., which is not limited in this embodiment.

[0081] Step S302: Encapsulate the first image parameters and the second image parameters into dynamic metadata, and send the original image and dynamic metadata to the playback end.

[0082] Specifically, the computer device can encapsulate the generated first and second image parameters into dynamic metadata, such as HEVC SEI, MP4 file, or bitstream Atom data, and can also encapsulate it into the original image, so that the original image and dynamic metadata can be transmitted together to the playback end (the specific transmission method is not limited, and the playback end can be, for example,...). Figure 1The terminal device 300 shown can also encapsulate the original image, the first image parameter, and the second image parameter into dynamic metadata for transmission. This is not limited here. The playback end can perform encoding / decoding and data format conversion on the dynamic metadata to obtain the original image, the first image parameter, and the second image parameter. The dynamic metadata instructs the playback end to perform brightness mapping on the original brightness image converted from the original image using the first image parameter, resulting in a mapped brightness image. The dynamic metadata also instructs the playback end to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameter. Furthermore, it generates a target signal value based on the brightness signal data and color data items in the mapped brightness image. The signal difference refers to the difference in signal values ​​between the original image and the original brightness image; the target signal value is used to generate the reconstructed image corresponding to the original image. If the original image, original luminance image, and mapped luminance image are not in the target signal domain (e.g., PQ domain), then all three images can be converted to the target signal domain first, and then the signal difference between the original image and the original luminance image can be obtained (e.g., the difference between the pixel components of each color channel in the original image in the target signal domain and the luminance conversion value of the original luminance image in the target signal domain). Alternatively, the difference between the original image and the original luminance image in the non-target signal domain can be obtained first, and then the difference can be converted to the target signal domain to obtain the signal difference. If the original image, original luminance image, and mapped luminance image are all in the target signal domain, that is, the original luminance image is obtained by weighted summation of the pixel components of different color channels of the original image in the target signal domain, and the mapped luminance image is obtained by luminance mapping based on the original luminance image in the target signal domain, then the signal difference between the original image and the original luminance image in the target signal domain and the luminance signal data corresponding to the mapped luminance image can be directly obtained.

[0083] This application embodiment updates the detail of the reconstructed image by adjusting the first and second sub-parameters in the second image parameters, updates the color saturation of the reconstructed image by adjusting the first sub-parameter, and adjusts the color temperature, hue, and artistic style of the reconstructed image by adjusting the third sub-parameter. This ensures more precise control over the color attributes of the reconstructed image. Furthermore, by adjusting the brightness of the reconstructed image in conjunction with the first image parameters, it ensures control over both brightness and color attributes. Therefore, the production end can provide more accurate dynamic metadata to the playback end, and the playback end can more accurately reconstruct the original image based on the dynamic metadata. This ensures that the display effect of the reconstructed image on the playback end's display is consistent with the display effect of the original image on the production end's display, that is, it meets the expected effect corresponding to the original image, thereby improving the reconstruction effect presented by the reconstructed image.

[0084] Please see Figure 11 , Figure 11 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of this application. Figure 1 .like Figure 11 As shown, the image processing device includes a transceiver module 1100, an image processing module 1200, a data item generation module 1300, and a signal value generation module 1400.

[0085] The transceiver module 1100 is used to acquire the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. Image processing module 1200 is used to perform brightness conversion on the original image to obtain an original brightness image, and to perform brightness mapping on the original brightness image according to the first image parameters to obtain a mapped brightness image; The data item generation module 1300 is used to obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters. The signal value generation module 1400 is used to acquire the luminance signal data corresponding to the mapped luminance image, and generate a target signal value based on the luminance signal data and color data items; the target signal value is used to generate the reconstructed image corresponding to the original image.

[0086] In one possible implementation, the color attributes include chromaticity deviation, color contrast, and color balance; the second image parameters include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance; when the data item generation module 1300 generates color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, it is specifically used to perform the following operations: A first sub-item for adjusting the chromaticity deviation of the original image is generated based on the signal difference and the first sub-parameter; A second sub-item for adjusting the color contrast of the original image is generated based on the signal difference and the second sub-parameter; The sum of the first sub-item, the second sub-item, and the third sub-parameter is determined as the color data item used to adjust the color attributes of the original image.

[0087] In one possible implementation, when the data item generation module 1300 generates a first sub-item for adjusting the chromaticity deviation of the original image based on the signal difference and the first sub-parameter, it specifically performs the following operations: The product of the signal difference and the first sub-parameter is determined as the first sub-item used to adjust the chromaticity deviation of the original image.

[0088] In one possible implementation, when the data item generation module 1300 generates a second sub-item for adjusting the color contrast of the original image based on the signal difference and the second sub-parameter, it specifically performs the following operations: The signal difference is squared to obtain the squared data. The product of the squared term data and the second sub-parameter is determined as the second sub-term used to adjust the color contrast of the original image.

[0089] In one possible implementation, when the signal value generation module 1400 generates the target signal value based on the luminance signal data and color data items, it specifically performs the following operations: The target signal value is obtained by summing the luminance signal data and color data.

[0090] In one possible implementation, each pixel in the original image includes pixel components corresponding to M color channels; the second image parameters include second image parameters corresponding to the M color channels; the M color channels include color channel K. h M is a positive integer, and h is a positive integer less than or equal to M; the data item generation module 1300 is used to obtain the signal difference between the original image and the original brightness image, and when generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, it is specifically used to perform the following operations: Based on the color channel K in the original image h The difference between the pixel components below and the luminance transformation values ​​contained in the original luminance image is used to generate the color channel K. h The corresponding signal difference; According to color channel K h The corresponding signal difference and color channel K h The corresponding second image parameters generate color channel K. h The corresponding color data item.

[0091] When the data item generation module 1300 generates a target signal value based on the luminance signal data and color data items, it specifically performs the following operations: The color data items corresponding to each color channel are summed with the luminance signal data to obtain the channel component signal value corresponding to each color channel; the channel component signal value corresponding to each color channel is used to form the target signal value.

[0092] In one possible implementation, the original image comprises N pixels; the N pixels include pixel F. t Pixel F tIt includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the image processing module 1200 is used to perform brightness conversion on the original image to obtain the original brightness image, specifically for performing the following operations: Get pixel F t The brightness conversion weights are included for each of the M color channels. pixel F t The pixel component corresponding to each of the M color channels is weighted and summed with the luminance conversion weight corresponding to each of the M color channels to obtain the pixel F. t The corresponding brightness conversion values; the brightness conversion values ​​corresponding to N pixels are used to construct the original brightness image corresponding to the original image.

[0093] In one possible implementation, the original brightness image comprises N pixels; the N pixels include pixel F. t Pixel F t It includes pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the image processing module 1200 is used to perform brightness mapping on the original brightness image according to the first image parameters to obtain the mapped brightness image, specifically for performing the following operations: Get pixel F t Brightness conversion values ​​in the original brightness image; A mapping curve for brightness mapping of the original brightness image is generated based on the first image parameters; Based on the mapping curve, pixel F t The brightness conversion value is mapped to obtain pixel F. t The corresponding luminance signal data; the luminance signal data corresponding to N pixels are used to construct the mapped luminance image corresponding to the original luminance image.

[0094] In one possible implementation, when the signal value generation module 1400 acquires the luminance signal data corresponding to the mapped luminance image, it specifically performs the following operations: Obtain the luminance mapping data contained in the mapped luminance image; the luminance mapping data is the luminance data in the linear original luminance domain; The signal parameters used for domain signal transformation between the original luminance domain and the perceived uniform target signal domain are obtained. Based on the signal parameters, the luminance mapping data is processed by nonlinear operation to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0095] In one possible implementation, the signal value generation module 1400 is also used to perform the following operations: The brightness mapping data is normalized to obtain normalized brightness data; Then, based on the signal parameters, nonlinear operations are performed on the luminance mapping data to obtain the luminance signal data of the mapped luminance image in the target signal domain, including: The normalized luminance data is processed nonlinearly based on the signal parameters to obtain the luminance signal data of the mapped luminance image in the target signal domain.

[0096] Please see Figure 12 , Figure 12 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of this application. Figure 2 .like Figure 12 As shown, the image processing device includes a parameter generation module 1500 and a data transmission module 1600.

[0097] The parameter generation module 1500 is used to acquire the original image, generate first image parameters for tone mapping from the original image, and generate second image parameters for color reconstruction from the original image. The data transmission module 1600 is used to encapsulate the first image parameters and the second image parameters into dynamic metadata, and send the original image and dynamic metadata to the playback end. The dynamic metadata is used to instruct the playback end to perform brightness mapping on the original brightness image converted from the original image using the first image parameters to obtain a mapped brightness image. The dynamic metadata is also used to instruct the playback end to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameters, and to generate a target signal value based on the brightness signal data and color data items in the mapped brightness image. The signal difference refers to the difference in signal values ​​between the original image and the original brightness image. The target signal value is used to generate the reconstructed image corresponding to the original image.

[0098] In one possible implementation, when the parameter generation module 1500 generates first image parameters for tone mapping from the original image, it specifically performs the following operations: Obtain the first initial image parameters for tone mapping, and obtain the target image associated with the original image; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to obtain an original brightness image. The original brightness image is then mapped to obtain predicted brightness data based on the first initial image parameters. Perform brightness conversion on the target image to obtain a target brightness image containing the target brightness data; The first initial image parameters are adjusted based on the brightness difference between the predicted brightness data and the target brightness data to obtain the adjusted first initial image parameters. If the adjusted first initial image parameters satisfy the parameter convergence condition, then the adjusted first initial image parameters are determined as the first image parameters.

[0099] In one possible implementation, the parameter generation module 1500 is also used to perform the following operations: The original brightness data is remapped using the adjusted first initial image parameters to obtain new predicted brightness data; If the brightness difference between the new predicted brightness data and the target brightness data is within the error range, then the adjusted first initial image parameters are determined to meet the parameter convergence condition.

[0100] In one possible implementation, when the parameter generation module 1500 generates second image parameters for color reconstruction from the original image, it specifically performs the following operations: Obtain the target image and a second initial image parameter for color reconstruction; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is converted to brightness to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first image parameters to obtain a mapped brightness image. The original image is then reconstructed based on the original brightness image, the mapped brightness image, and the second initial image parameters to obtain an intermediate target image. Obtain the original color attributes of the intermediate target image and the target color attributes of the target image. Extract features from the original color attributes to obtain the original attribute features, and extract features from the target color attributes to obtain the target attribute features. Similarity calculation is performed on the original attribute features and the target attribute features to obtain the attribute similarity between the original color attributes and the target color attributes. Based on the attribute similarity, the second initial image parameters are adjusted to obtain the adjusted second initial image parameters. If the original color attribute of the intermediate target image obtained by reconstructing the original image using the adjusted second initial image parameters has an attribute similarity greater than or equal to the target color attribute, then the adjusted second initial image parameters are determined as the second image parameters.

[0101] In one possible implementation, when the parameter generation module 1500 generates second image parameters for color reconstruction from the original image, it specifically performs the following operations: A second initial image parameter for color reconstruction is obtained, and the original image is reconstructed based on the first image parameter and the second initial image parameter to obtain a reconstructed image. The second initial image parameter includes a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. In response to the adjustment operation of the target sub-parameter among the first sub-parameter, second sub-parameter, and third sub-parameter, the reconstructed image is updated and displayed; the updated reconstructed image is obtained by updating the reconstructed image according to the adjusted second initial image parameters; the adjusted second initial image parameters include the adjusted target sub-parameter; In response to the confirmation operation for the updated reconstructed image, the adjusted second initial image parameters are determined as the second image parameters.

[0102] This application embodiment acquires an original image and dynamic metadata including first and second image parameters. It performs brightness conversion on the original image to obtain an original brightness image, then maps the original brightness image to obtain a mapped brightness image based on the first image parameters. By acquiring the signal difference between the original image and the original brightness image, color data items for adjusting the color attributes of the original image can be generated based on the signal difference and the second image parameters. Further, after acquiring the brightness signal data corresponding to the mapped brightness image, a target signal value can be generated based on the brightness signal data and the color data items. By using the signal difference between the original brightness image obtained from brightness conversion and the original image, and the second image parameters used for color reconstruction to generate color data items for adjusting the color attributes of the original image, the attribute differences between the original image and the original brightness image, as well as the color reconstruction effect brought by the second image parameters, can be effectively combined to improve the accuracy of color attribute reconstruction of the original image. In other words, it can improve the reconstruction effect presented by the reconstructed image generated based on the target signal value. Furthermore, the embodiments of this application not only reconstruct the brightness data of the original image based on the first image parameters, but also introduce the second image parameters to reconstruct and adjust the color attributes of the original image. This ensures that the generated reconstructed image is controllable in both brightness and color attributes, that is, the display effect of the reconstructed image in terms of brightness and color attributes can be controlled to meet the expected effect corresponding to the original image, thereby further improving the reconstruction effect presented by the reconstructed image.

[0103] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0104] Please see Figure 13 , Figure 13 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Figure 13 As shown, the computer device 1000 may include a processor 1001, a network interface 1004, and a memory 1005. Furthermore, the computer device 1000 may also include an object interface 1003 and at least one communication bus 1002. The communication bus 1002 is used to enable communication between these components. The object interface 1003 may include a display screen and a keyboard; optionally, the object interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as at least one disk storage device. Optionally, the memory 1005 may also be at least one storage device located remotely from the processor 1001. Figure 13 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, an object interface module, and a device control application.

[0105] In such Figure 13 In the computer device 1000 shown, the network interface 1004 provides network communication elements; the object interface 1003 is mainly used to provide an input interface for objects; and the processor 1001 can be used to call the computer program stored in the memory 1005, specifically to execute the aforementioned... Figure 5 , Figure 6 and Figure 8 Each step in the embodiments.

[0106] It should be understood that the computer device 1000 described in the embodiments of this application can execute the foregoing text. Figure 5 , Figure 6 and Figure 8The description of the image processing method in any corresponding embodiment will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated.

[0107] Furthermore, it should be noted that this application embodiment also provides a computer-readable storage medium, which stores a computer program. When the processor executes the computer program, it can execute the aforementioned... Figure 5 , Figure 6 and Figure 8 The description of the image processing method in any corresponding embodiment is already provided, and therefore will not be repeated here. Furthermore, the beneficial effects of using the same method will also not be repeated. For technical details not disclosed in the computer-readable storage medium embodiments related to this application, please refer to the description of the method embodiments of this application.

[0108] The aforementioned computer-readable storage medium can be an internal storage unit of the image processing apparatus or computer device provided in any of the foregoing embodiments, such as a hard disk or memory of the computer device. The computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the computer device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the computer device. The computer-readable storage medium is used to store the computer program and other programs and data required by the computer device. The computer-readable storage medium can also be used to temporarily store data that has been displayed or will be displayed.

[0109] Furthermore, it should be noted that this application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the aforementioned... Figure 5 , Figure 6 and Figure 8 The method provided in any of the corresponding embodiments.

[0110] The terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or modules, but may optionally include steps or modules not listed, or may optionally include other step units inherent to these processes, methods, apparatuses, products, or devices.

[0111] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the foregoing description as a network element. Whether these network elements are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can implement the described network elements using different methods for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] The methods and related apparatus provided in this application are described with reference to the method flowcharts and / or structural diagrams provided in this application. Specifically, each block of the method flowcharts and / or structural diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by a computer program. These computer programs can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable device to create a machine, such that the computer program, executed by the processor of the computer or other programmable device, produces a mechanism for implementing the process... Figure 1 A schematic diagram of one or more processes and / or structures. Figure 1 The computer program may be a means for performing the functions specified in one or more boxes. These computer programs may also be stored in a computer-readable storage medium that can direct a computer or other programmable device to function in a particular manner, causing the computer program stored in the computer-readable storage medium to produce an article of manufacture including the program means, or to be transmitted via a computer-readable storage medium. The computer program can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The program means is implemented in the process. Figure 1 A schematic diagram of one or more processes and / or structures. Figure 1The functions specified in one or more boxes. These computer programs may also be loaded onto a computer or other programmable device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby providing the computer program executing on the computer or other programmable device with the means to implement the process. Figure 1 A process or multiple processes and / or structures illustrate the steps of the functions specified in one or more boxes.

[0113] The steps in the method of this application embodiment can be adjusted, combined, or deleted according to actual needs.

[0114] The modules in the device of this application embodiment can be merged, divided, and deleted according to actual needs.

[0115] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. An image processing method, characterized in that, include: Acquire the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. The original image is subjected to brightness conversion to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first image parameters to obtain a mapped brightness image. Obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters; Obtain the luminance signal data corresponding to the mapped luminance image, and generate a target signal value based on the luminance signal data and the color data item; The target signal value is used to generate the reconstructed image corresponding to the original image.

2. The method according to claim 1, characterized in that, The color attributes include chromaticity deviation, color contrast, and color balance; the second image parameters include a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. The step of generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters includes: A first sub-item for adjusting the chromaticity deviation of the original image is generated based on the signal difference and the first sub-parameter; A second sub-item for adjusting the color contrast of the original image is generated based on the signal difference and the second sub-parameter; The sum of the first sub-item, the second sub-item, and the third sub-parameter is determined as the color data item used to adjust the color attributes of the original image.

3. The method according to claim 2, characterized in that, The step of generating a first sub-item for adjusting the chromaticity deviation of the original image based on the signal difference and the first sub-parameter includes: The product of the signal difference and the first sub-parameter is determined as the first sub-item for adjusting the chromaticity deviation of the original image.

4. The method according to claim 2, characterized in that, The step of generating a second sub-item for adjusting the color contrast of the original image based on the signal difference and the second sub-parameter includes: The signal difference is squared to obtain the squared data. The product of the squared term data and the second sub-parameter is determined as the second sub-term used to adjust the color contrast of the original image.

5. The method according to claim 1, characterized in that, The step of generating a target signal value based on the luminance signal data and the color data item includes: The target signal value is obtained by summing the luminance signal data and the color data.

6. The method according to claim 1, characterized in that, Each pixel in the original image includes pixel components corresponding to M color channels; the second image parameters include the second image parameters corresponding to the M color channels; the M color channels include color channel K. h M is a positive integer, and h is a positive integer less than or equal to M; the step of obtaining the signal difference between the original image and the original brightness image, and generating color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters, includes: Based on the color channel K in the original image h The color channel K is generated by taking the difference between the pixel components below and the luminance conversion values ​​contained in the original luminance image. h The corresponding signal difference; According to the color channel K h The corresponding signal difference and the color channel K h The corresponding second image parameters are used to generate the color channel K. h The corresponding color data items; The step of generating a target signal value based on the luminance signal data and the color data item includes: The color data item corresponding to each color channel is summed with the luminance signal data to obtain the channel component signal value corresponding to each color channel; the channel component signal value corresponding to each color channel is used to form the target signal value.

7. The method according to claim 1, characterized in that, The original image comprises N pixels; the N pixels include pixel F. t The pixel F t Includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; the step of performing brightness conversion on the original image to obtain an original brightness image includes: Obtain the pixel F t The brightness conversion weights are included for each of the M color channels. The pixel F t The pixel F is obtained by weighting and summing the pixel components corresponding to the M color channels and the luminance conversion weights corresponding to the M color channels. t The corresponding brightness conversion values; the brightness conversion values ​​corresponding to the N pixels are used to construct the original brightness image corresponding to the original image.

8. The method according to claim 1, characterized in that, The original brightness image comprises N pixels; the N pixels include pixel F. t The pixel F t Includes the pixel components corresponding to M color channels; M and N are positive integers, and t is a positive integer less than or equal to N; The step of performing brightness mapping on the original brightness image based on the first image parameters to obtain a mapped brightness image includes: Obtain the pixel F t The brightness conversion value in the original brightness image; A mapping curve for brightness mapping of the original brightness image is generated based on the first image parameters; According to the mapping curve, the pixel F t The brightness conversion value is mapped to obtain the pixel F. t The corresponding luminance signal data; the luminance signal data corresponding to the N pixels are used to construct the mapped luminance image corresponding to the original luminance image.

9. The method according to claim 1, characterized in that, The step of obtaining the luminance signal data corresponding to the mapped luminance image includes: Obtain the luminance mapping data contained in the mapped luminance image; the luminance mapping data is luminance data in the linear original luminance domain; The signal parameters used for domain signal transformation between the original luminance domain and the perceived uniform target signal domain are obtained. Based on the signal parameters, the luminance mapping data is processed by nonlinear operation to obtain the luminance signal data of the mapped luminance image in the target signal domain.

10. The method according to claim 9, characterized in that, The method further includes: The brightness mapping data is normalized to obtain normalized brightness data; The step of performing nonlinear computation on the luminance mapping data based on the signal parameters to obtain the luminance signal data of the mapped luminance image in the target signal domain includes: Based on the signal parameters, the normalized luminance data is processed by nonlinear operation to obtain the luminance signal data of the mapped luminance image in the target signal domain.

11. An image processing method, characterized in that, include: Acquire the original image, generate first image parameters for tone mapping from the original image, and generate second image parameters for color reconstruction from the original image; The first image parameters and the second image parameters are encapsulated into dynamic metadata, and the original image and the dynamic metadata are sent to the playback terminal. The dynamic metadata is used to instruct the playback terminal to perform luminance mapping on the original luminance image converted from the original image using the first image parameters to obtain a mapped luminance image; the dynamic metadata is also used to instruct the playback terminal to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameters, and to generate a target signal value based on the luminance signal data in the mapped luminance image and the color data items; the signal difference refers to the difference in signal values ​​between the original image and the original luminance image; the target signal value is used to generate the reconstructed image corresponding to the original image.

12. The method according to claim 11, characterized in that, The step of generating first image parameters for tone mapping from the original image includes: Obtain first initial image parameters for tone mapping, and obtain a target image associated with the original image; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is subjected to brightness conversion to obtain an original brightness image. The original brightness image is then mapped to brightness based on the first initial image parameters to obtain predicted brightness data. The target image is subjected to brightness conversion to obtain a target brightness image containing target brightness data; Based on the brightness difference between the predicted brightness data and the target brightness data, the first initial image parameters are adjusted to obtain the adjusted first initial image parameters. If the adjusted first initial image parameters satisfy the parameter convergence condition, then the adjusted first initial image parameters are determined as the first image parameters.

13. The method according to claim 12, characterized in that, Also includes: The original brightness data is remapped using the adjusted first initial image parameters to obtain new predicted brightness data. If the brightness difference between the new predicted brightness data and the target brightness data is within the error range, then the adjusted first initial image parameters are determined to meet the parameter convergence condition.

14. The method according to claim 11, characterized in that, The step of generating second image parameters for color reconstruction from the original image includes: Obtain a target image and second initial image parameters for color reconstruction; the original image and the target image have the same image content, and the color dynamic range of the original image and the target image are different from each other; The original image is subjected to brightness conversion to obtain an original brightness image. The original brightness image is then mapped to brightness according to the first image parameters to obtain a mapped brightness image. The original image is then reconstructed according to the original brightness image, the mapped brightness image, and the second initial image parameters to obtain an intermediate target image. Obtain the original color attributes of the intermediate target image and the target color attributes of the target image, respectively extract features from the original color attributes to obtain original attribute features, and extract features from the target color attributes to obtain target attribute features; Similarity calculation is performed on the original attribute features and the target attribute features to obtain the attribute similarity between the original color attributes and the target color attributes. Based on the attribute similarity, the second initial image parameters are adjusted to obtain the adjusted second initial image parameters. If the original color attribute of the intermediate target image obtained by reconstructing the original image using the adjusted second initial image parameters has an attribute similarity greater than or equal to the target color attribute, then the adjusted second initial image parameters are determined as the second image parameters.

15. The method according to claim 11, characterized in that, The step of generating second image parameters for color reconstruction from the original image includes: A second initial image parameter for color reconstruction is obtained, and the original image is reconstructed based on the first image parameter and the second initial image parameter to obtain a reconstructed image; the second initial image parameter includes a first sub-parameter for adjusting chromaticity deviation, a second sub-parameter for adjusting color contrast, and a third sub-parameter for adjusting color balance. In response to the adjustment operation of the target sub-parameter among the first sub-parameter, the second sub-parameter, and the third sub-parameter, the reconstructed image is updated and displayed; the updated reconstructed image is obtained by updating the reconstructed image according to the adjusted second initial image parameters; the adjusted second initial image parameters include the adjusted target sub-parameter. In response to the confirmation operation for the updated reconstructed image, the adjusted second initial image parameters are determined as the second image parameters.

16. An image processing apparatus, characterized in that, include: The transceiver module is used to acquire the original image and dynamic metadata; the dynamic metadata includes first image parameters for tone mapping and second image parameters for color reconstruction. The image processing module is used to perform brightness conversion on the original image to obtain an original brightness image, and to perform brightness mapping on the original brightness image according to the first image parameters to obtain a mapped brightness image; The data item generation module is used to obtain the signal difference between the original image and the original brightness image, and generate color data items for adjusting the color attributes of the original image based on the signal difference and the second image parameters. The signal value generation module is used to acquire the luminance signal data corresponding to the mapped luminance image, and generate a target signal value based on the luminance signal data and the color data item. The target signal value is used to generate the reconstructed image corresponding to the original image.

17. An image processing apparatus, characterized in that, include: The parameter generation module is used to acquire the original image, generate first image parameters for tone mapping based on the original image, and generate second image parameters for color reconstruction based on the original image. The data transmission module is used to encapsulate the first image parameters and the second image parameters into dynamic metadata, and send the original image and the dynamic metadata to the playback terminal; The dynamic metadata is used to instruct the playback terminal to perform luminance mapping on the original luminance image converted from the original image using the first image parameters to obtain a mapped luminance image; the dynamic metadata is also used to instruct the playback terminal to generate color data items for adjusting the color attributes of the original image using the signal difference and the second image parameters, and to generate a target signal value based on the luminance signal data in the mapped luminance image and the color data items; the signal difference refers to the difference in signal values ​​between the original image and the original luminance image; the target signal value is used to generate the reconstructed image corresponding to the original image.

18. A computer device, characterized in that, include: Processor, memory, and network interface; The processor is connected to the memory and the network interface, wherein the network interface is used to provide data communication functions, the memory is used to store computer programs, and the processor is used to call the computer programs to cause the computer device to perform the method according to any one of claims 1-15.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded and executed by a processor to cause a computer device having the processor to perform the method of any one of claims 1-15.

20. A computer program product, characterized in that, The computer program product includes a computer program stored in a computer-readable storage medium and adapted to be read and executed by a processor so that a computer device having the processor performs the method of any one of claims 1-15.

Images