Image processing method and device, storage medium, electronic equipment and chip

Abstract

The invention discloses an image processing method and device, a storage medium, electronic equipment and a chip, and relates to the technical field of image processing.The method comprises the steps that firstly, image attention degrees of different areas in a game image are obtained; according to the image attention of different areas in the game image, determining coloring rates corresponding to the different areas; and processing the game image according to the coloring rates corresponding to the different areas, and displaying the processed game image. Through the mode, the image attention degrees of different areas of the game image can be recognized, the area division of the game image can be performed according to the image attention degrees, and different areas are processed by using different coloring rates, so that the coloring rate of partial areas can be reduced on the premise of ensuring the visual quality, the power consumption of terminal equipment is further reduced, and the user experience is improved. And the overall performance of the terminal equipment is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technologies, and in particular, to an image processing method, apparatus, storage medium, electronic device, and chip. Background Art

[0002] In the process of processing game images, various elements in the game scene can be finely processed to provide users with a realistic visual effect, and maintain a high frame rate under real-time rendering to ensure the interactive experience of users.

[0003] Related technologies usually pre-calibrate corresponding rendering parameters for the game scene and perform rendering processing on the entire game screen according to the calibrated rendering parameters.

[0004] However, the method of performing rendering processing on the entire game screen according to the calibrated rendering parameters in related technologies increases the power consumption of the terminal device and affects the overall performance of the terminal device. Summary of the Invention

[0005] The present disclosure provides an image processing method, apparatus, storage medium, electronic device, and chip, mainly aiming to improve the technical problem that the method of performing rendering processing on the entire game screen according to the calibrated rendering parameters in related technologies increases the power consumption of the terminal device and affects the overall performance of the terminal device.

[0006] According to a first aspect of an embodiment of the present disclosure, an image processing method is provided, including:

[0007] Obtain the image attention degrees of different regions in the game image;

[0008] Determine the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image;

[0009] Process the game image according to the coloring rates corresponding to the different regions, and display the processed game image.

[0010] In some embodiments of the present disclosure, the obtaining the image attention degrees of different regions in the game image includes:

[0011] Determine the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image.

[0012] In some embodiments of the present disclosure, the determining the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image includes:

[0013] Perform saliency detection on the game image to obtain the scene saliency of different regions in the game image;

[0014] Determine the image attention degrees corresponding to the different regions according to the saliency of the screen.

[0015] In some embodiments of the present disclosure, the determining the coloring rates corresponding to the different regions according to the image attention degrees of different regions in the game image includes:

[0016] Determine a coloring rate identification map corresponding to the game image according to the image attention degrees corresponding to the different regions, where the coloring rate identification map includes coloring rate identifications corresponding to different regions in the game image;

[0017] Determine the coloring rates corresponding to the different regions according to the coloring rate identification map.

[0018] In some embodiments of the present disclosure, the processing the game image according to the coloring rates corresponding to the different regions and displaying the processed game image includes:

[0019] Perform coloring processing on different regions in the game image according to the coloring rate identification map;

[0020] Perform image quality processing on the game image after coloring processing, and display the game image after image quality processing.

[0021] In some embodiments of the present disclosure, the performing image quality processing on the game image after coloring processing and displaying the game image after image quality processing includes at least one of the following:

[0022] Perform frame interpolation processing on the game image after coloring processing;

[0023] Perform super-resolution processing on the game image after frame interpolation processing.

[0024] In some embodiments of the present disclosure, the performing frame interpolation processing on the game image after coloring processing includes:

[0025] Obtain inserted frames according to the current game image after coloring processing and the historical game image frames corresponding to the current game image after coloring processing.

[0026] In some embodiments of the present disclosure, before the obtaining the image attention degrees of different regions in the game image, the method further includes:

[0027] Determine the rendering data of the game scene according to the device information when entering the game scene;

[0028] Render the game scene by using the rendering data to obtain a rendered game image;

[0029] The obtaining the image attention degrees of different regions in the game image includes:

[0030] Obtain the image attention degrees of different regions in the rendered game image.

[0031] In some embodiments of the present disclosure, determining the rendering data of the game scene according to the device information when entering the game scene includes:

[0032] Obtain the device information when entering the game scene;

[0033] Determine the rendering data corresponding to the device information according to a preset device information table, where the preset device information table includes device data intervals corresponding to different device information and rendering data corresponding to the device data intervals.

[0034] According to a second aspect of the embodiments of the present disclosure, there is provided an image processing apparatus, including:

[0035] An obtaining module, configured to obtain the image attention degrees of different regions in the game image;

[0036] A determining module, configured to determine the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image;

[0037] A processing module, configured to process the game image according to the coloring rates corresponding to the different regions and display the processed game image.

[0038] According to a third aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0039] According to a fourth aspect of the embodiments of the present disclosure, there is provided an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, the method described in the first aspect is implemented.

[0040] According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, on which a computer program is stored. It is characterized in that when the computer program product is executed by a processor, the method described in the first aspect is implemented.

[0041] According to a sixth aspect of the embodiments of the present disclosure, there is provided a chip, including one or more interface circuits and one or more processors; the interface circuit is used to receive a signal from the memory of the electronic device and send the signal to the processor, and the signal includes computer instructions stored in the memory; when the processor executes the computer instructions, the electronic device is caused to execute the method described in the first aspect.

[0042] With the above technical solutions, the present disclosure provides an image processing method, apparatus, storage medium, electronic device, and chip. Specifically, first, obtain the image attention degrees of different regions in the game image; determine the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image; process the game image according to the coloring rates corresponding to the different regions, and display the processed game image. In this way, it is possible to identify the image attention degrees of different regions in the game image, perform regional division of the game image according to the image attention degrees, and process different regions with different coloring rates, so as to reduce the coloring rates of some regions while ensuring the visual quality, thereby reducing the power consumption of the terminal device and improving the overall performance of the terminal device.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. Brief Description of the Drawings

[0044] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0045] Figure 1 Shows a schematic flowchart of an image processing method provided by an embodiment of the present application;

[0046] Figure 2 Shows a schematic flowchart of an image processing method provided by an embodiment of the present application;

[0047] Figure 3 Shows a schematic diagram of an example provided by an embodiment of the present application;

[0048] Figure 4 Shows a schematic structural diagram of an image processing apparatus provided by an embodiment of the present application. Detailed Description of the Embodiments

[0049] Here, some embodiments of the present disclosure will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatuses, and / or systems described herein will become apparent after understanding the present disclosure. For example, the order of the operations described herein is only an example and is not limited to the orders set forth herein, but can be changed as will be apparent after understanding the present disclosure, except for operations that must be performed in a specific order. Additionally, for the sake of clarity and brevity, the description of features known in the art may be omitted. It should be noted that, without conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0050] Some embodiments of the present disclosure will be described below. It should be noted that the implementation manners described in some embodiments of the present disclosure below do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0051] To address the technical problem in the related art that the overall rendering of game images according to calibrated rendering parameters increases the power consumption of the terminal device and affects the overall performance of the terminal device, embodiments of the present disclosure provide an image processing method, as Figure 1 shown, including the following steps.

[0052] Step 101: Obtain the image attention degrees of different regions in the game image.

[0053] In a specific application scenario, when a user observes and processes an image, the user usually selectively focuses on certain regions of the image according to their own interests, needs, and the content of the image, while ignoring other parts. During the process of the user experiencing the game, the degree of attraction of different regions in the game image to the user is different, so the image attention degrees of the user for each region of the game image are usually different. This difference may stem from various factors, such as game design, plot guidance, user operation habits, visual focus, image features (such as color, brightness, contrast, texture), etc. Therefore, the image attention degrees of the rendered game image can be detected, and for different regions corresponding to different image attention degrees, different coloring rates are used for image processing, effectively improving the rendering efficiency, saving computing resources, and reducing the terminal power consumption while ensuring the game image quality.

[0054] As a possible implementation manner, the attention degrees corresponding to each region in the game scene and the coloring rates corresponding to each region can be preset according to the game design document; the gaze point data of the user during the game can also be collected using an eye tracking device, or the attention degrees corresponding to each region can be inferred by analyzing the user's operation behavior; machine learning algorithms can also be used to predict the image attention degrees of each region according to the image features of the game image, such as color, texture, etc.; the attention algorithm can also be used to calculate the attention degree value of each pixel or region by analyzing the features and content of the game image, and the attention degree value corresponding to the game image can be presented in the form of a grayscale image. For example, a game image region with higher brightness indicates higher attention degree.

[0055] Step 102: Determine the coloring rates corresponding to different regions according to the image attention degrees of different regions in the game image.

[0056] Exemplarily, for the background area and edge area in a game scene (game screen), the image attention may be relatively low. Then, a lower shading rate can be used for rendering in this area, which can reduce the precision of shading in this area or the number of shading times. Thus, on the premise of ensuring visual quality, the rendering process can be optimized, the frame rate and smoothness of the game can be improved, the overall game performance can be enhanced, and the phenomenon of lag and delay can be reduced. Correspondingly, for the central area in the game scene where the image attention may be relatively high, a higher shading rate can be used for rendering to improve the precision of shading in this area or increase the number of shading times to ensure the image quality of the high-attention area and enhance the immersion and realism of the game.

[0057] Step 103: Process the game image according to the shading rates corresponding to different areas, and display the processed game image.

[0058] In some embodiments, after determining the shading rates of different areas, different shading rates are used for rendering at different positions. For the rendered image, further image quality enhancement processing can be performed, such as frame interpolation processing, super-resolution processing, etc. The game image after the image quality enhancement processing is displayed to the user to improve the frame rate and resolution, thereby enhancing the user's game experience while reducing resource consumption.

[0059] Compared with the related art, in this embodiment, the image attention of different areas in the game image is obtained; according to the image attention of different areas in the game image, the shading rates corresponding to different areas are determined; the game image is processed according to the shading rates corresponding to different areas, and the processed game image is displayed. In this way, the image attention of different areas in the game image is recognized, the game image is divided into regions according to the image attention, and different shading rates are used for processing different regions. Thus, on the premise of ensuring visual quality, the shading rate of some areas can be reduced, thereby reducing the power consumption of the terminal device and enhancing the overall performance of the terminal device.

[0060] Further, to illustrate the specific implementation process of the method in this embodiment, the following specific method is provided as Figure 2 shown. The method includes:

[0061] Step 201: Determine the rendering data of the game scene based on the device information when entering the game scene.

[0062] In some embodiments, after a user enters a game scene through a terminal device such as a mobile phone or a tablet computer, the game engine can obtain the device information of the terminal device in real time, and then dynamically adjust the rendering data corresponding to the game scene according to the changes in the device information, so as to be applicable to devices with different hardware configurations, meet the needs of multiple users, and improve the user experience. Exemplarily, this embodiment can be applied to game rendering on mobile devices. During the game process on a mobile phone, according to the game content and device status of the current game scene, the rendering resolution and frame rate are adaptively determined, and a neural network is used to improve the image quality and frame rate, thereby improving the user's game experience on the premise of reducing rendering power consumption.

[0063] Among them, the device information may include but is not limited to temperature, Graphics Processing Unit (GPU) frequency, frequency point, battery power, memory, device type, screen resolution, etc. The rendering data may include rendering resolution, rendering frame rate, etc., which can be used to determine the clarity and smoothness of an image. Specifically, the running state of the current terminal can be determined through information such as temperature and frequency point, and then the rendering data can be adjusted according to the current running state to ensure the best game experience on devices with different running states and different performance levels.

[0064] Exemplarily, if the device temperature is too high or the running frequency is low, the rendering resolution and rendering frame rate can be reduced to reduce the resource consumption and heat generation of the device. On the contrary, if the device performance is good and the temperature is moderate, the rendering resolution and frame rate can be increased to provide a better game experience for the user.

[0065] It should be noted that this embodiment can be applied to other application programs, such as a video playback program. According to the device information when entering different application programs, the rendering data corresponding to the application picture in the application program can be determined, and the rendered application image can be displayed.

[0066] Optionally, step 201 may specifically include: obtaining the device information when entering the game scene; determining the rendering data corresponding to the device information according to a preset device information table, where the preset device information table includes device data intervals corresponding to different device information, and rendering data corresponding to different device data intervals.

[0067] In some embodiments, before the game program runs, a lookup table can be preset as the preset device information table, which is used to preset the rendering data corresponding to each device parameter interval. After entering the game scene, according to the current device temperature, GPU frequency, and the name of the running game, the rendering resolution and rendering frame rate that should be used for the current picture are determined, so as to ensure that the picture content will not drop frames, guarantee the game picture quality, and reduce the impact on the user's game experience. Exemplarily, the data structure of the preset device information table is shown in Table 1.

[0068] Table 1

[0069] Device Temperature GPU Frequency Game Name Rendering Resolution Rendering Frame Rate XXX~XXX XXX~XXX MHz XXX XXX XXX

[0070] In a specific game scenario, the current device status can be determined based on device information, and the rendering data corresponding to different device statuses can be determined by looking up a table, realizing the adaptive adjustment of rendering data, which is applicable to multiple device statuses, meets multiple game scenarios, and improves the user experience.

[0071] Step 202: Render the game scenario using the rendering data to obtain the rendered game image.

[0072] In some embodiments, after determining the rendering data, the rendering data can be informed to the game engine, so that the game engine can perform screen rendering according to the determined rendering data to obtain a game image matching the device status, which is adapted to the device status corresponding to multiple hardware configurations. During the game process, the device status may change according to the game progress. The device status can be detected in real time, and the rendering data can be adjusted accordingly to provide a good game experience for users.

[0073] Step 203: Obtain the image attention degrees of different regions in the game image.

[0074] Optionally, step 203 may include: determining the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image.

[0075] Further optionally, determining the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image may specifically include: performing saliency detection on the game image to obtain the scene saliency of different regions in the game image; determining the image attention degrees corresponding to different regions based on the scene saliency. The saliency detection algorithm can be used to identify the target regions or objects that users are interested in in the image. Its goal is to simulate the human visual system and automatically find the important parts in the image. Exemplarily, saliency can be calculated by comparing local and global features. Or, saliency can be identified based on neural networks and other methods.

[0076] In a specific game scenario, the game screen rendered in the previous frame can be transmitted to a preset recognition model, and then the preset recognition model is used to perform saliency detection to obtain the scene saliency at different positions on the screen, and the corresponding image attention degrees are determined according to the scene saliency of each region. The preset recognition model can be a neural network model, such as UNet, etc.

[0077] Specifically, a saliency detection algorithm can be used to process the game image to generate a corresponding saliency map. Based on the saliency map, the saliency of different regions in each image can be determined, and the preset number of regions with the highest saliency can be extracted as the parts that the user may be interested in. These regions usually contain key information or visual focuses in the image. Operation data such as the user's clicks on the game image can be collected to verify whether the saliency detection results are consistent with the user's actual focus points. Combining the saliency detection results and the user's operations can optimize the neural network model and improve the recognition accuracy rate of the neural network model.

[0078] Optionally, step 203 may further include: obtaining the image attentions of different regions in the rendered game image.

[0079] Exemplarily, after the user enters the game scene, the game engine can load game resources corresponding to each game scene, such as models, textures, lighting, shadows, etc. Then, according to the rendering data corresponding to the current running state of the terminal device, the rendering engine is called to render the game scene to obtain the rendered game image, and then the image attentions of the rendered game image are recognized to optimize the game image quality.

[0080] Step 204: Determine the coloring rate identification map corresponding to the game image according to the image attentions corresponding to different regions.

[0081] Optionally, the coloring rate identification map may include coloring rate identifications corresponding to different regions in the game image.

[0082] In some embodiments, a preset recognition model can be constructed using the UNet architecture. The previously rendered image is input into the preset recognition model, and then the preset recognition model outputs a coloring rate identification map Map between 0 and 1 based on the detected image attentions of each region. Among them, 0 can be used to represent the lowest coloring rate, and 1 can be used to represent the highest coloring rate. The lowest coloring rate and the highest coloring rate can be pre-set parameters and can be preset according to the GPU characteristics. Specifically, to ensure that the output range of the UNet is between 0 and 1, its last layer is the Sigmoid activation function.

[0083] Step 205: Determine the coloring rates corresponding to different regions according to the coloring rate identification map.

[0084] In some embodiments, according to the coloring rate identification maps corresponding to each game image, the coloring rate identifications corresponding to each region in the image can be determined, and the coloring rates during the rendering process of each region can be determined through the corresponding relationship between each coloring rate identification and the coloring rate, so as to facilitate zonal rendering and achieve zonal processing of the game image.

[0085] Step 206: Process the rendered game image according to the coloring rates corresponding to different regions and display the processed game image.

[0086] Optionally, step 206 may specifically include: performing coloring processing on different regions in the game image according to the coloring rate identification map; performing image quality processing on the colored game image, and displaying the game image after image quality processing.

[0087] In some embodiments, the Unet network may input the coloring rate identification map and the rendered game image, and output the result after enhancing the image quality of the game image. The image quality enhancement in this step does not change the frame rate and resolution, but only improves the coloring rate, that is, filling in details and anti-aliasing for low-coloring-rate regions.

[0088] Optionally, performing image quality processing on the colored game image and displaying the game image after image quality processing may specifically include: performing frame interpolation processing on the colored game image to obtain the game image after frame interpolation processing; performing super-resolution processing on the game image after frame interpolation processing, and displaying the game image after super-resolution processing.

[0089] Optionally, performing frame interpolation processing on the colored game image may specifically include: obtaining the inserted frame according to the current game image after coloring processing and the historical game image frame corresponding to the current game image after coloring processing.

[0090] Exemplarily, the preset frame interpolation model may input the current game image after coloring processing and the historical game frame image, such as: the previous frame image of the current game image, the previous two frame images of the current game image, and then output the optical flow information and weights of the two frames interpolated to the intermediate frame, and perform a 2-interpolate-1 operation based on the optical flow and weights, that is, use the two frames to generate the inserted frame (intermediate frame). Among them, the preset frame interpolation model may use RIFE as the basic network, remove the intermediate GridSample operation, and do not process the rest.

[0091] Optionally, performing super-resolution processing on the game image after frame interpolation processing and displaying the game image after super-resolution processing may specifically include: using the preset super-resolution model to perform super-resolution processing on the game image after frame interpolation processing, and displaying the game image after super-resolution processing. The preset super-resolution model is used to improve the resolution of the game image after frame interpolation processing.

[0092] Exemplarily, the input of the preset super-resolution model may be the output frame after frame interpolation processing and the game image after coloring processing, and the output is the corresponding high-resolution image. The preset super-resolution model may use EDSR as the basic network, reduce the number of network layers and channels, and thus meet the running speed.

[0093] As a possible implementation manner, as Figure 3 shown, it can be divided into three stages:

[0094] Phase 1: Confirm Rendering Data (Rendering Parameters)

[0095] 1. After the user enters a certain game scene, relevant rendering information of the current scene is obtained through the game engine;

[0096] 2. Obtain the device information of the current mobile terminal, such as the running status information, which may include temperature, frequency point, etc.;

[0097] 3. According to the obtained device information, judge the current mobile phone status and determine the rendering resolution and frame rate of the game engine;

[0098] 4. Inform the game engine of the resolution and frame rate, and let it perform screen rendering with these parameters;

[0099] Phase 2: Confirm the Shading Rate

[0100] 5. Transmit the game screen rendered in the previous frame to the neural network, process it using the neural network, and obtain the image attention (user attention) at different positions on the game screen, which can be obtained through saliency detection;

[0101] 6. According to the different image attentions corresponding to different screen saliencies, use different shading rates for rendering at different positions;

[0102] 7. For the rendered image, use the neural network for image quality enhancement and perform upsampling of the shading rate for the content with a low shading rate;

[0103] Phase 3: Image Quality Enhancement

[0104] 8. Perform frame interpolation on the rendered game screen to obtain a high-frame-rate image with upsampled frame rate;

[0105] 9. Perform super-resolution processing on the high-frame-rate image to obtain a super-resolved game image;

[0106] 10. Display the game image after performing image quality enhancement operations such as super-resolution and frame interpolation to the user.

[0107] In this way, this embodiment performs two-stage rendering and image quality improvement based on AI. First, it confirms the rendering resolution and frame rate according to the current device status, then uses the neural network to analyze the image attention of the current game image, uses different shading rates for rendering according to the image attention of different regions, and uses AI algorithms to improve the frame rate and resolution for the rendered image. Thus, while reducing resource consumption, it improves the user's gaming experience, reduces the manual calibration of the optimization parameters of the game scene, realizes fine-grained shading rate control, and at the same time improves problems such as resolution and frame rate improvement.

[0108] Compared with the related art, in this embodiment, the rendering data of the game scene can be adaptively adjusted according to the device state when entering the game scene, which is applicable to different hardware configurations. Moreover, the rendered game image is subjected to saliency detection to obtain the image attention of each region in the image, and a corresponding coloring rate identification map is output. Then, the coloring rate of each region is determined according to the coloring rate identification map, and different regions in the same image are partitioned. Then, through frame interpolation processing and super-resolution processing, the image quality of the colored image is enhanced, the frame rate and resolution of the screen are improved, and the user experience is enhanced.

[0109] Figure 4 It is a block diagram of an image processing device shown according to some embodiments of the present disclosure. Referring to Figure 4 this, the device includes: an acquisition module 31, a determination module 32, and a processing module 33.

[0110] The acquisition module 31 is configured to acquire the image attention of different regions in the game image;

[0111] The determination module 32 is configured to determine the corresponding coloring rate of different regions according to the image attention of different regions in the game image;

[0112] The processing module 33 is configured to process the game image according to the corresponding coloring rate of different regions and display the processed game image.

[0113] In some examples of this embodiment, the acquisition module 31 is specifically configured to determine the image attention of different regions in the game image according to the saliency detection result of the game image.

[0114] In some examples of this embodiment, the determination module 32 is specifically configured to perform saliency detection on the game image to obtain the screen saliency of different regions in the game image; and determine the image attention of different regions according to the screen saliency.

[0115] In some examples of this embodiment, the determination module 32 is specifically configured to determine the coloring rate identification map corresponding to the game image according to the image attention of different regions, where the coloring rate identification map includes the coloring rate identifications corresponding to different regions in the game image; and determine the corresponding coloring rate of different regions according to the coloring rate identification map.

[0116] In some examples of this embodiment, the processing module 33 is specifically configured to perform coloring processing on different regions in the game image according to the coloring rate identification map; perform image quality processing on the colored game image, and display the game image after image quality processing.

[0117] In some examples of this embodiment, the processing module 33 is specifically configured to perform frame interpolation processing on the colored game image to obtain the game image after frame interpolation processing; perform super-resolution processing on the game image after frame interpolation processing, and display the game image after super-resolution processing.

[0118] In some examples of this embodiment, the processing module 33 is specifically configured to obtain an inserted frame according to the current colored game image and the previous frame game image corresponding to the current colored game image; obtain the game image after frame interpolation processing based on the inserted frame.

[0119] In some examples of this embodiment, the obtaining module 31 is further specifically configured to determine the rendering data of the game scene according to the device information when entering the game scene; use the rendering data to render the game scene to obtain the rendered game image; obtain the image attention degrees of different regions in the rendered game image.

[0120] In some examples of this embodiment, the obtaining module 31 is specifically configured to obtain the device information when entering the game scene; determine the rendering data corresponding to the device information according to a preset device information table, and the preset device information table includes device data intervals corresponding to different device information and rendering data corresponding to the device data intervals.

[0121] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0122] Based on the above as Figures 1 to 2 shown in the method, correspondingly, this embodiment further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method shown in the above as Figures 1 to 2 shown is implemented.

[0123] Based on the above as Figures 1 to 2 shown in the method, correspondingly, this embodiment further provides a computer program product, on which a computer program is stored, and when the computer program is executed by a processor, the method shown in the above as Figures 1 to 2 shown is implemented.

[0124] Based on such an understanding, the technical solution of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods in various implementation scenarios of the present disclosure.

[0125] Based on the above as Figures 1 to 2 shown in the method, andFigure 4 For the virtual device embodiments shown, to achieve the above object, embodiments of the present disclosure further provide an electronic device, such as a smart phone, smart watch, smart bracelet, tablet computer, drone, smart robot, server, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the above as Figures 1 to 2 the method shown.

[0126] Optionally, the above-mentioned physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0127] Those skilled in the art can understand that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0128] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware and software resources of the above-mentioned physical device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to implement communication between components inside the storage medium, and communication between other hardware and software in the information processing physical device.

[0129] Based on the above as Figures 1 to 2 the method shown, and Figure 4 the virtual device embodiments shown, this embodiment further provides a chip, including one or more interface circuits and one or more processors; the interface circuit is used to receive a signal from the memory of the electronic device and send the signal to the processor, and the signal includes computer instructions stored in the memory; when the processor executes the computer instructions, the electronic device is caused to execute the above as Figures 1 to 2 the method shown.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus a necessary general hardware platform, or can also be implemented by hardware. By applying the solution of this embodiment, compared with the related art, this embodiment can adaptively adjust the rendering data of the game scene according to the device state when entering the game scene, is applicable to different hardware configurations, and performs saliency detection on the rendered game image, obtains the image attention of each area in the image, and outputs the corresponding coloring rate identification map. Then, according to the coloring rate identification map, the coloring rate of each area is determined, and different areas in the same image are partitioned. Then, through frame interpolation processing and super-resolution processing, the image quality of the colored image is enhanced, the frame rate and resolution of the image are improved, and the user experience is enhanced.

[0131] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the said element.

[0132] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An image processing method, characterized in that, Including: Obtain the image attention degrees of different regions in the game image; Determine the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image; Process the game image according to the coloring rates corresponding to the different regions, and display the processed game image.

2. The method according to claim 1, characterized in that The obtaining the image attention degrees of different regions in the game image includes: Determine the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image.

3. The method according to claim 2, wherein The determining the image attention degrees corresponding to different regions in the game image according to the saliency detection result of the game image includes: Perform saliency detection on the game image to obtain the scene saliency of different regions in the game image; Determine the image attention degrees corresponding to the different regions according to the scene saliency.

4. The method according to claim 2, wherein The determining the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image includes: Determine the coloring rate identification map corresponding to the game image according to the image attention degrees corresponding to the different regions, where the coloring rate identification map includes the coloring rate identifications corresponding to different regions in the game image; Determine the coloring rates corresponding to the different regions according to the coloring rate identification map.

5. The method according to claim 4, wherein The processing the game image according to the coloring rates corresponding to the different regions and displaying the processed game image includes: Perform coloring processing on different regions in the game image according to the coloring rate identification map; Perform image quality processing on the colored game image and display the game image after image quality processing.

6. The method according to claim 5, wherein The performing image quality processing on the colored game image includes at least one of the following: Perform frame interpolation processing on the colored game image; Perform super-resolution processing on the game image after frame interpolation processing.

7. The method according to claim 6, characterized in that, The performing frame interpolation processing on the colored game image includes: Obtain the inserted frames according to the currently colored game image and the historical game image frames corresponding to the currently colored game image.

8. The method according to claim 1, characterized in that Before the obtaining the image attention degrees of different regions in the game image, the method further includes: Determine the rendering data of the game scene according to the device information when entering the game scene; Use the rendering data to render the game scene and obtain the rendered game image; The obtaining the image attention degrees of different regions in the game image includes: Obtain the image attention degrees of different regions in the rendered game image.

9. The method according to claim 8, wherein The determining the rendering data of the game scene according to the device information when entering the game scene includes: Obtain the device information when entering the game scene; Determine the rendering data corresponding to the device information according to the preset device information table, where the preset device information table includes the device data ranges corresponding to different device information and the rendering data corresponding to the device data ranges.

10. An image processing apparatus, characterized in that, Including: An obtaining module, configured to obtain the image attention degrees of different regions in the game image; A determining module, configured to determine the coloring rates corresponding to the different regions according to the image attention degrees of the different regions in the game image; A processing module, configured to process the game image according to the coloring rates corresponding to the different regions, and display the processed game image.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. An electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

13. A computer program product having a computer program stored thereon, characterized in that, When the computer program product is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

14. A chip, characterized in that, Comprising one or more interface circuits and one or more processors; the interface circuits are used to receive signals from the memory of the electronic device and send the signals to the processors, the signals including computer instructions stored in the memory; when the processors execute the computer instructions, the electronic device is caused to execute the method according to any one of claims 1 to 9.

Images