Image processing method and device, display equipment, storage medium and program product

Abstract

The invention relates to an image processing method and device, display equipment, a storage medium and a program product. According to the embodiment of the invention, under the condition that the switching instruction for indicating switching from the 2D display mode to the 3D display mode is received in the 2D display mode, the global image for 3D display is acquired, so that the pixel value of each pixel point in the global image is adjusted through the pre-trained first image processing model; according to the method and the device, the first target image with the image brightness improved is obtained, so that the first target image can be displayed in the 3D display mode, the image display effect in the 3D mode is ensured, and the display effect is adaptively adjusted when the 2D display mode is switched to the 3D display mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of display, in particular to an image processing method and device, display equipment, storage medium and program product. BACKGROUND

[0002] With the continuous development of display technology, the traditional two-dimensional (2D) display has been unable to meet the needs of users for more immersive and more realistic visual experience. Therefore, naked-eye three-dimensional (3D) technology emerges as the times require, which provides a three-dimensional visual experience without wearing 3D glasses, breaking through the limitations of traditional display technology.

[0003] In the related art, by combining software and hardware, the traditional 2D screen can be upgraded to a screen with naked-eye 3D display capability, so that the display mode can be switched on the same display screen, both in 2D mode and in 3D display mode when needed, to bring users a convenient use experience.

[0004] However, in the process of switching from 2D display to 3D display, due to the difference in display principle, the picture brightness often decreases significantly, resulting in poor display effect in 3D mode. SUMMARY

[0005] The present application provides an image processing method, device, display equipment, storage medium and program product to solve the deficiencies in the related art.

[0006] According to a first aspect of the embodiments of the present application, an image processing method is provided, which comprises: In the case of 2D display mode, in response to receiving a switching instruction, a global image for 3D display is obtained, wherein the switching instruction is used to indicate switching from 2D display mode to 3D display mode; The pixel values of each pixel point in the global image are adjusted by a pre-trained first image processing model to obtain a first target image with improved image brightness; In the 3D display mode, the first target image is displayed.

[0007] According to a second aspect of the embodiments of the present application, an image processing device is provided, which comprises: The acquisition module is configured to, in the case of 2D display mode, in response to receiving a switching instruction, acquire a global image for 3D display, wherein the switching instruction is used to indicate switching from 2D display mode to 3D display mode; an adjusting module, configured to adjust pixel values of each pixel point in the global image by using the pre-trained first image processing model, to obtain a first target image with improved image brightness; a displaying module, configured to display the first target image in the 3D display mode.

[0008] According to a third aspect of the embodiments of the present application, a display device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements operations performed by the image processing method according to the first aspect.

[0009] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a program, and the program is executed by a processor to implement operations performed by the image processing method according to the first aspect.

[0010] According to a fifth aspect of the embodiments of the present application, a computer program product is provided, which comprises a computer program, and the computer program is executed by a processor to implement operations performed by the image processing method according to the first aspect.

[0011] According to the above embodiments, in the case that the switching instruction indicating switching from the 2D display mode to the 3D display mode is received in the 2D display mode, the global image for 3D display is acquired, and then the pixel values of each pixel point in the global image are adjusted by using the pre-trained first image processing model, to obtain the first target image with improved image brightness, so that the first target image can be displayed in the 3D display mode, and the image display effect in the 3D mode is ensured, thereby realizing adaptive adjustment of the display effect when switching from the 2D display mode to the 3D display mode.

[0012] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0014] Figure 1 is a schematic diagram of a grating barrier technology according to an embodiment of the present application.

[0015] Figure 2 is a flowchart of an image processing method according to an embodiment of the present application.

[0016] Figure 3is a schematic diagram of an overall flow of an image processing and display method according to an embodiment of the present application.

[0017] Figure 4 is a block diagram of an image processing device according to an embodiment of the present application.

[0018] Figure 5 is a structural schematic diagram of a display device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, unless otherwise indicated, like numbers in the attached drawings refer to the same or similar elements. The embodiments described in the following exemplary embodiments are not meant to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the present application as detailed in the appended claims.

[0020] In today's digital era, 3D display technology is gradually integrated into people's life and work.

[0021] In the related art, a grating barrier technology can be used to achieve a naked-eye 3D display effect. Alternatively, the grating barrier technology can use a liquid crystal layer and a polarizing film to manufacture a series of vertical stripes with a direction of 90°, and the width of the stripes is generally tens of microns. The vertical stripes can form a vertical fine grid pattern to form a parallax barrier, so as to separate the left-eye and right-eye pictures through the vertical stripe structure, so that the audience can experience the stereoscopic effect without wearing 3D glasses.

[0022] Alternatively, in a 3D display mode (or a stereoscopic display mode), when an image that should be seen by the left eye is displayed on the liquid crystal screen, the opaque stripes will block the right eye; similarly, when an image that should be seen by the right eye is displayed on the liquid crystal screen, the opaque stripes will block the left eye. Referring to Figure 1 , Figure 1 is a schematic diagram of the principle of a grating barrier technology according to an embodiment of the present application, as shown in Figure 1 In the 3D mode, the grating barrier technology can be used to arrange the left-eye and right-eye images alternately, and use the stripe blocking to make the left eye and the right eye receive different images, and finally synthesize a 3D image through the human brain.

[0023] Alternatively, the above grating barrier technology can be applied to the liquid crystal display screen of various display devices to achieve a naked-eye 3D effect. For example, the above grating barrier technology can be applied to televisions, smart phones, tablet computers, notebook computers, game consoles, etc., but is not limited thereto, and the present application does not limit the type of display device.

[0024] Optionally, the displayed content can be related to various scenes such as games, movies, medical images, advertisements, etc., and the present application does not limit this.

[0025] In the related art, the grating barrier type naked eye 3D technology has great advantages in mass production and cost due to its compatibility with the existing liquid crystal display (LCD) process.

[0026] However, due to the shielding of the grating, there is a significant drop in picture brightness when switching from 2D display to naked eye 3D display due to the difference in display principle, which not only affects the user's clear viewing of the content, but also may cause visual fatigue of the user, reducing the overall viewing effect of the image.

[0027] Therefore, the present application expects to provide an image processing method to automatically adjust the display effect when switching from 2D display to naked eye 3D display.

[0028] Referring to Figure 2 , Figure 2 is a flowchart of an image processing method according to an embodiment of the present application, as Figure 2 shown, the method comprises: Step 201, in the case of being in a 2D display mode, in response to receiving a switching instruction, acquiring a global image for 3D display, wherein the switching instruction is used to indicate switching from the 2D display mode to the 3D display mode.

[0029] In some embodiments, in the case of being in a 2D display mode, the switching instruction triggered based on user operation can be listened to, and the switching instruction can be used to trigger the operation of the user switching from the 2D display mode to the 3D display mode, so that the global image for 3D display can be acquired based on the listened switching instruction.

[0030] Optionally, when the user triggers the switching instruction through the corresponding operation, the user can trigger the switching instruction by pressing the physical button (or hardware button) provided on the display device, but is not limited thereto, and can also trigger the switching instruction by touching the virtual button provided on the visual interface of the display device, etc., and the present application does not limit the triggering method of the switching instruction.

[0031] Optionally, no matter how the switching instruction is triggered, the switching instruction can be an event-driven message generated based on a user operation. Optionally, the event-driven message can adopt a special data structure for notifying the operating system that a certain specific event has occurred, and different types of events can correspond to different message types and / or message contents of the event-driven message. Optionally, the operating system can determine whether the event that has occurred is a display mode switching event of switching from the 2D display mode to the 3D display mode according to the message type and / or message content of the event-driven message, to determine whether the switching instruction is monitored.

[0032] Optionally, the image processing method provided by the present application can be packaged as a software, and the operating system can deliver the event-driven message to the Basic Input Output System (BIOS) communication in the case that the operating system determines that the event that has occurred is the display mode switching event of switching from the 2D display mode to the 3D display mode according to the message type and / or message content of the event-driven message, so that the image processing method provided by the present application can be used to improve the display effect.

[0033] Step 202: adjusting the pixel value of each pixel point in the global image by using the first image processing model that is pre-trained, to obtain a first target image with improved image brightness.

[0034] The first image processing model is pre-trained, which can take the global image as input, adjust the pixel value of each pixel point in the global image through a series of processing of the model, realize the image brightness improvement of the global image, and obtain the first target image with improved image brightness output by the model.

[0035] Step 203: displaying the first target image in the 3D display mode.

[0036] Through the above embodiment, in the case that the switching instruction indicating switching from the 2D display mode to the 3D display mode is received in the 2D display mode, the global image for 3D display can be obtained, so that the pixel value of each pixel point in the global image is adjusted by using the first image processing model that is pre-trained, to obtain the first target image with improved image brightness, so that the first target image can be displayed in the 3D display mode, the image display effect in the 3D mode is ensured, and the display effect adaptive adjustment when switching from the 2D display mode to the 3D display mode is realized.

[0037] After introducing the basic implementation process of the present application, various optional implementation manners of the present application are introduced below.

[0038] As described above, in the implementation of naked-eye 3D display using the grating barrier technology, the left and right eyes can receive different images through the stripe blocking, and the human brain can finally synthesize a 3D image. Thus, in some embodiments, for step 201, in response to receiving the switching instruction, the global image for 3D display can be acquired, which can be the left eye image and the right eye image, but is not limited thereto, and the left eye image and the right eye image can be superimposed to obtain a corresponding image of the superimposed effect as the global image.

[0039] In some embodiments, in the case of receiving the switching instruction, a series of initialization preparations can be performed to provide strong support for 3D display.

[0040] Optionally, in the case of receiving the switching instruction, a series of initialization preparations can be performed in sequence, including serial port initialization, microcontroller unit (MCU) initialization, grating initialization, acquisition of calibration data, eye tracking initialization, service start, global capture, interlaced driving, Windows management instrumentation (WMI) communication-MCU activation, and grating start, but is not limited thereto.

[0041] The calibration data can be some hardware parameters related to 3D display of the display device, and the specific content of the calibration data is not limited in the present application.

[0042] Optionally, the eye tracking initialization can refer to the process of calibrating and configuring the display device or the operating system before using the eye tracking technology, to ensure that it can accurately capture the user's eye movement data, and provide strong support for subsequent naked-eye 3D display.

[0043] Optionally, the above steps of acquiring the left eye image and the right eye image can be performed during the global capture, and the above steps of superimposing the left eye image and the right eye image can be performed during the interlaced driving.

[0044] Optionally, after starting the grating, the brightness of the 3D display image can be improved through step 202.

[0045] In some embodiments, whether the acquired global image is the left eye image and the right eye image, or the image corresponding to the superimposed effect of the left eye image and the right eye image, the pixel values of each pixel point in the global image can be adjusted through step 202 to obtain a first target image with improved image brightness, by using a first image processing model trained in advance.

[0046] Optionally, if the global image is a left-eye image and a right-eye image, the left-eye image can be input to the first image processing model to adjust the pixel values of each pixel point in the left-eye image through the first image processing model to obtain a first target left-eye image with improved image brightness, and the right-eye image can be input to the first image processing model to adjust the pixel values of each pixel point in the right-eye image through the first image processing model to obtain a first target right-eye image with improved image brightness, and the first target left-eye image and the first target right-eye image are the first target images with improved image brightness.

[0047] Optionally, if the global image is an image corresponding to the superimposition effect of a left-eye image and a right-eye image, the contents represented by the pixel points at the same pixel position in the left-eye image and the right-eye image are consistent, except that the pixel values may be different. The pixel value superimposition result of the corresponding pixel points in the left-eye image and the right-eye image can be input to the first image processing model to adjust the pixel value superimposition result of each pixel point through the first image processing model to obtain the first target image with improved image brightness.

[0048] The first image processing model can be pre-trained, so that the image brightness can be improved directly through the pre-trained first image model after the global image is obtained.

[0049] In some embodiments, the first image processing model can be a Convolutional Neural Network (CNN) model, but is not limited thereto. Other types of neural network models can also be used as the first image processing model, and the present application does not limit the same.

[0050] In some embodiments, a pre-trained CNN model can be used as the first initial model to train the first initial model based on the first training data set to obtain the trained first image processing model. For example, a Visual Geometry Group (VGG) model can be used as the first initial model, but is not limited thereto.

[0051] Optionally, the first training data set can be an image data set suitable for a game scene, which can include a plurality of first training images of different scenes, different objects, and different lighting conditions. Optionally, the game scene can include role-playing, shooting, strategy simulation, racing sports, adventure and puzzle, etc., but is not limited thereto.

[0052] The first training data set can be used to train the first image processing model. The first training data set can include a plurality of first training images and corresponding first training information. The first training images can be used as input images of the first image processing model, and the first training information can be used as the first training label of the first image processing model. The first training information can be used to indicate the brightness level of the first training image, so that the first image processing model can be trained based on the first training image.

[0053] Optionally, the difference between the first output image obtained by processing the first training image and the first template image satisfying the set condition can be used as a loss function to train the first image processing model.

[0054] Optionally, the first image processing model to be trained can be used to perform brightness enhancement processing on the first training image to obtain the first output image, so that the difference between the first output image and the first template image satisfying the set condition is measured by using the loss function, and the parameters of the first image processing model to be trained are adjusted based on the loss function. In this way, the first image processing model to be trained is trained based on a plurality of first training images until the training termination condition is met, i.e., the trained first image processing model is obtained.

[0055] Optionally, the loss function can be a mean square error (MSE) loss function, but is not limited thereto.

[0056] Optionally, the training termination condition can be that the loss function no longer decreases, reaches a preset first iteration number, reaches a preset performance indicator (such as a preset accuracy indicator), etc., but is not limited thereto.

[0057] Optionally, the first test data set can be used to evaluate the performance of the trained first image processing model. Optionally, the MSE, structural similarity index (SSIM), etc. can be used to evaluate the performance of the model, but is not limited thereto. In evaluating the performance of the model, peak signal-to-noise ratio (PSNR), visual effect, etc. can also be considered.

[0058] Through the above model training process, the first image processing model can know the information elements of an image under normal brightness and where the difference between the original image and the image with increased raster shading is, so that the first image processing model can use artificial intelligence (AI) image processing means to enhance the brightness of the image with increased raster shading.

[0059] Optionally, after the first image processing model is trained, the trained first image processing model can also be compressed through pruning, quantization and other techniques to reduce the storage space and calculation amount of the first image processing model and improve the inference speed of the first image processing model.

[0060] In some embodiments, after the first target image is obtained by enhancing the brightness of the global image through the above embodiments, the first target image can be displayed in the 3D display mode through step 203.

[0061] Optionally, when the first target image is displayed in the 3D display mode, a series of work such as starting the camera, obtaining the portrait, obtaining the eye coordinates, generating the MCU coordinates, refreshing the WMI communication-MCU, and refreshing the grating can be sequentially performed to realize the display of the first target image in the 3D display mode.

[0062] The above embodiments are described by using the AI image processing method to enhance the brightness of the image, and then displaying the first target image after the image brightness enhancement. In more possible implementation manners, the naked-eye 3D display effect can also be improved by increasing the device display brightness.

[0063] In some embodiments, the current device display brightness can be obtained in response to receiving the switching instruction, so that the device display brightness can be increased to the highest device display brightness when the current device display brightness does not reach the highest device display brightness, so that the first target image is displayed in the 3D display mode using the highest device display brightness.

[0064] Optionally, when the current device display brightness is obtained, the System.Management namespace can be loaded after the grating is turned on, and then the ManagementObjectSearcher and ManagementObject classes can be used to query the screen brightness information in the WMI to realize the acquisition of the current device display brightness.

[0065] Optionally, when the brightness is not 100%, a ManagementObjectSearcher object can be created to search the WmiMonitorBrightnessMethods class in the WMI, so that the ManagementObjectSearcher object can be called to traverse all found objects, and the WmiSetBrightness method of each object can be called to set the brightness to 100%, so as to increase the device display brightness to the highest device display brightness.

[0066] It should be noted that the above device brightness adjustment process does not change the brightness of the image itself, but improves the display brightness of the device through the Windows built-in Application Programming Interface (API).

[0067] The above embodiments are described by taking the improvement of naked eye 3D display effect through a series of brightness improvement processes as an example. In more possible implementation manners, color enhancement and / or contrast enhancement can also be implemented by using an AI image processing method to further improve the naked eye 3D display effect.

[0068] In some embodiments, color enhancement and / or contrast enhancement can be performed based on the obtained global image after the global image for 3D display is obtained in response to receiving the switching instruction; or color enhancement and / or contrast enhancement can be performed based on the first target image after the first target image is obtained by processing the first image through the first image processing model.

[0069] In some embodiments, when color enhancement and / or contrast enhancement is performed based on the global image, the pixel values of each pixel point in the global image can be adjusted through the pre-trained second image processing model to obtain a second target image with color enhancement and / or contrast enhancement.

[0070] In some embodiments, when color enhancement and / or contrast enhancement is performed based on the first target image, the pixel values of each pixel point in the first target image can be adjusted through the pre-trained second image processing model to obtain a fourth target image with color enhancement and / or contrast enhancement.

[0071] The second image processing model can be pre-trained, so that the image color enhancement and / or contrast enhancement can be directly implemented through the pre-trained second image model.

[0072] In some embodiments, the second image processing model can be a convolutional neural network (CNN) model, but is not limited thereto. Other types of neural network models can also be used as the second image processing model, and the present application does not limit the same.

[0073] In some embodiments, a pre-trained CNN model can be used as a second initial model to train the second initial model based on a second training data set to obtain a trained second image processing model. Optionally, a supervised learning training method can be used in the training process, or an unsupervised learning training method can be used. The appropriate training method can be selected according to the task requirements, and the present application does not limit the same.

[0074] Optionally, the second training data set can be an image data set suitable for a game scene, which can include a plurality of second training images of different scenes, different objects, and different lighting conditions. Optionally, the game scene can include role-playing, shooting, strategy simulation, racing sports, adventure and puzzle, etc., but is not limited thereto.

[0075] Optionally, each of the second training images in the second training data set can be labeled with semantic information, which can be used to indicate the scene (such as indoor, outdoor, etc.) of the second training image, the object edge in the second training image, the object color, etc., but is not limited thereto, so that the model training based on the second training image can be realized based on the labeled semantic information. Optionally, the semantic information can be labeled by manual labeling or using an existing semantic labeling data set, which is not limited by the present application.

[0076] Optionally, the labeled second training image can also be preprocessed to improve the image quality of the second training image. Optionally, the preprocessing can include image denoising processing, white balance adjustment, brightness normalization, etc., but is not limited thereto.

[0077] Optionally, the difference between the second output image processed from the second training image and the second template image with a corresponding color performance and image contrast satisfying a set condition can be used as a loss function to train the second image processing model.

[0078] Optionally, in order to optimize the color enhancement effect and the contrast enhancement effect, the loss function can include a plurality of loss terms. For example, the loss function can include L1 loss, color fidelity loss, contrast loss, etc., between the second output image and the second template image, but is not limited thereto.

[0079] Optionally, the second training image can be color enhanced and / or contrast enhanced by the second image processing model to be trained to obtain a second output image, so that the difference between the second output image and the second template image with a corresponding color performance and image contrast satisfying a set condition is measured by using the loss function, and the parameter adjustment of the second image processing model to be trained is realized based on the loss function. In this way, the training of the second image processing model to be trained is realized based on a plurality of second training images, until the training termination condition is met, i.e., the trained second image processing model is obtained.

[0080] Optionally, the training termination condition can be that the loss function no longer decreases, reaches a preset second iteration number, reaches a preset performance indicator (such as a preset accuracy indicator, etc.), etc., but is not limited thereto.

[0081] Optionally, the second test data set can be used to evaluate the performance of the trained second image processing model. Optionally, the evaluation of the model performance can be achieved using indicators such as MSE, SSIM, etc., but is not limited thereto. In evaluating the model performance, various indicators such as peak signal-to-noise ratio, visual effect, etc. can also be considered.

[0082] In more possible implementations, the first training set can also be reused for training the second image processing model, which is not limited by the present application.

[0083] Through the above model training process, the second image processing model can perform color correction on the input image through the AI algorithm, making it closer to the color performance in the real world. In addition, the second image processing model can be used to learn the mapping relationship from the input image to the output image, so as to perform color mapping on the original image to make it more vivid and lively.

[0084] Optionally, color correction of the input image can be achieved by methods such as white balance adjustment and color space conversion, but is not limited thereto.

[0085] Optionally, after the second image processing model is trained, pruning, quantization, and other techniques can be used to compress the trained second image processing model, reducing the storage space and computational complexity of the second image processing model, and improving the inference speed of the second image processing model.

[0086] In some embodiments, after the image color enhancement and / or contrast enhancement are achieved through the above embodiments, the image can be displayed in 3D display mode.

[0087] In some embodiments, after the color and / or contrast enhanced second target image is obtained, a third target image can be determined based on the first target image and the second target image, and the third target image can be displayed in 3D display mode.

[0088] Optionally, the pixel values of corresponding pixels in the first target image and the second target image can be superimposed to determine the third target image.

[0089] In some embodiments, after the color and / or contrast enhanced fourth target image is obtained, the fourth target image can be displayed in 3D display mode.

[0090] The above embodiments are described by using AI image processing means to achieve image brightness enhancement processing, color enhancement and / or contrast enhancement processing, and then displaying the corresponding image. In more possible implementations, the naked eye 3D display effect can also be improved by increasing the display brightness of the device.

[0091] In some embodiments, the current device display brightness can be acquired in response to receiving the switching instruction; thus, the device display brightness can be raised to the highest device display brightness in the case that the current device display brightness does not reach the highest device display brightness, so as to display the third target image in the 3D display mode by using the highest device display brightness.

[0092] Alternatively, the current device display brightness can be acquired in response to receiving the switching instruction; thus, the device display brightness can be raised to the highest device display brightness in the case that the current device display brightness does not reach the highest device display brightness, so as to display the fourth target image in the 3D display mode by using the highest device display brightness.

[0093] The implementation of acquiring the current device display brightness and raising the device display brightness to the highest device display brightness can refer to the foregoing, and will not be described herein.

[0094] Referring to Figure 3 , Figure 3 is a whole flowchart of an image processing and display method according to an embodiment of the present application, as shown in Figure 3 , the service can be started after booting, and the service communication can be established to perform a series of initialization preparation work such as serial port initialization, MCU initialization, raster initialization, acquisition of calibration data, eye tracking initialization, etc. After the preparation is completed, the service can be started, and in the case of switching from the 2D display mode to the 3D display mode, a series of operations such as global capture, interlacing start, WMI communication, MCU activation, and opening of the raster can be performed to realize the preparation of 3D display, and the camera can be started after the service is started to acquire the portrait and the eye coordinates, so that the MCU coordinates can be generated based on the acquired portrait and eye coordinates, which are used to perform a series of work such as WMI communication, MCU refresh, and raster refresh, to realize the real-time display of naked-eye 3D.

[0095] In more possible implementation manners, in the case of switching from the 3D display mode to the 2D display mode, the interlacing closing operation can also be performed, and the MCU control, the camera, and the raster can be closed through the WMI communication to switch back to the 2D display mode.

[0096] By the scheme provided in the present application, the current display state can be automatically obtained to automatically perform operations such as brightness adjustment, image color enhancement, and image contrast enhancement when switching from the 2D display mode to the 3D display mode, so as to alleviate the problem of brightness loss caused by the sudden switching from the 2D display mode to the 3D display mode.

[0097] Corresponding to the embodiments of the foregoing method, the present application also provides embodiments of an image processing device and a display device to which the image processing device is applied.

[0098] Referring to Figure 4 , Figure 4 is a block diagram of an image processing apparatus according to an embodiment of the present application, as shown in the figure, the apparatus comprises: Figure 4 The acquisition module 401 is configured to, in the case of being in a 2D display mode, acquire a global image for 3D display in response to receiving a switching instruction, wherein the switching instruction is used to indicate switching from the 2D display mode to the 3D display mode; The adjustment module 402 is configured to adjust the pixel value of each pixel point in the global image by using a pre-trained first image processing model, to obtain a first target image with improved image brightness; The display module 403 is configured to display the first target image in the 3D display mode.

[0099] In some embodiments, the first image processing model is trained based on first training images labeled with brightness information, wherein the brightness information is used to indicate the brightness level of the first training images; The first image processing model is trained based on the difference between the first output image obtained by processing the first training images and a first template image satisfying a set condition in terms of corresponding brightness information.

[0100] In some embodiments, the adjustment module 402 is further configured to adjust the pixel value of each pixel point in the global image by using a pre-trained second image processing model, to obtain a second target image with enhanced color and / or contrast; The apparatus further comprises: The determination module is configured to determine a third target image based on the first target image and the second target image; The display module 403 is further configured to display the third target image in the 3D display mode.

[0101] In some embodiments, the adjustment module 402 is further configured to adjust the pixel value of each pixel point in the first target image by using a pre-trained second image processing model, to obtain a fourth target image with enhanced color and / or contrast; The display module 403 is further configured to display the fourth target image in the 3D display mode.

[0102] In some embodiments, the second image processing model is trained based on second training images labeled with semantic information, wherein the semantic information is used to indicate at least one of the scene of the second training images, the edge of the objects in the second training images, and the color of the objects; The second image processing model is trained based on the difference between the second output image obtained by processing the second training images and a second template image satisfying a set condition in terms of corresponding color representation and image contrast.​

[0103] In some embodiments, the obtaining module 401 is further configured to, in response to receiving the switching instruction, obtain a current device display brightness; The adjusting module 402 is further configured to, in the case that the current device display brightness does not reach the highest device display brightness, increase the device display brightness to the highest device display brightness, so as to display the image in the 3D display mode by using the highest device display brightness.

[0104] In some embodiments, the global image comprises left-eye images and right-eye images, or the global image is an image corresponding to the effect after superimposing the left-eye images and the right-eye images.

[0105] The implementation process of the functions and roles of each module in the above apparatus is specifically described in the implementation process of the corresponding steps in the above method, which will not be repeated here.

[0106] For the device embodiment, since it basically corresponds to the method embodiment, the related parts can be referred to the part of the method embodiment. The above described device embodiment is only illustrative, and the modules described as separate components can be or can not be physically separated, and the components displayed as modules can be or can not be physical modules, that is, they can be located in one place or distributed on multiple network modules. According to the actual needs, some or all of the modules can be selected to achieve the purpose of the present application. Those skilled in the art can understand and implement without creative labor.

[0107] The present application also provides a display device, which is described in detail as follows. Figure 5 , Figure 5 is a structural schematic diagram of a display device according to an embodiment of the present application. As shown in Figure 5 , the display device comprises a processor 510, a memory 520 and a network interface 530, the memory 520 is used to store computer instructions executable on the processor 510, the processor 510 is used to implement the image processing method provided by any embodiment of the present application when executing the computer instructions, and the network interface 530 is used to implement the input and output functions. In more possible implementation manners, the display device can further comprise other hardware such as a display screen, and the present application does not limit this.

[0108] The computer readable storage medium can be in various forms, for example, in different examples, the computer readable storage medium can be: RAM (Radom Access Memory), volatile memory, non-volatile memory, flash memory, storage drive (such as a hard disk drive), solid state disk, any type of storage disk (such as an optical disk, DVD, etc.), or similar storage medium, or a combination thereof. In particular, the computer readable medium can also be paper or other suitable medium capable of printing programs. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the image processing method provided by any embodiment of the present application.

[0109] The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the image processing method provided by any embodiment of the present application.

[0110] Those skilled in the art will appreciate that one or more embodiments of the present application can be provided as a method, apparatus, display device, computer readable storage medium or computer program product. Therefore, one or more embodiments of the present application can take the form of a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, one or more embodiments of the present application can take the form of a computer program product implemented on one or more computer usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0111] Each embodiment of the present application is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the embodiment corresponding to the computing device, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0112] The above describes a specific embodiment of the present application. Other embodiments are within the scope of the present application. In some cases, the actions or steps described in the present application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0113] Embodiments of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non-transitory program carrier for execution by, or to control the operation of, image processing apparatus. Alternatively or additionally, the program instructions can be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus. The computer storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0114] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit), and the apparatus can be implemented as special purpose logic circuitry.

[0115] Computers suitable for the execution of a computer program include, by way of example, general and / or special purpose microprocessors, or any other kind of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The essential elements of a computer are a central processing unit for performing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer need not have such devices. Moreover, a computer can be embedded in another device, e.g., a mobile telephone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device (e.g., a universal serial bus (USB) flash drive), to name just a few.

[0116] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0117] While the application encompasses a number of specific implementations, it will be understood by those skilled in the art that these are presented by way of example only and that the scope of the application is not intended to be limited to any one or more of the specific embodiments described. Certain features of the application described in the context of one embodiment can also be implemented in combination with features of another embodiment. Conversely, various features of the application described with respect to one embodiment can also be implemented separately from other features described in connection with the same or other embodiments. Further, although features can be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination and the claimed combination can be directed to a subcombination or variation of a subcombination.

[0118] Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring or implying that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing can be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0119] Accordingly, particular embodiments of the subject matter have been described. Other embodiments within the scope of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. For example, to specify acts or referenced clauses that can be implemented in one embodiment does not imply that they are a requirement of all embodiments. Additionally, the operations employed in the processes depicted in the figures do not have to be performed in the order shown or sequentially, nor do they have to be performed by the same entity. Further, the processes depicted in the figures can be modified in various,equivalent manners without departing from the scope of the present application. It is therefore intended that the application not be limited to the particular embodiment disclosed as the best mode contemplated for carrying out this application, but that the application include all embodiments falling within the scope of the application.

[0120] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. For example, to specify acts or referenced clauses that can be implemented in one embodiment does not imply that they are a requirement of all embodiments. Additionally, the operations employed in the processes depicted in the figures do not have to be performed in the order shown or sequentially, nor do they have to be performed by the same entity. Further, the processes depicted in the figures can be modified in various, equivalent manners without departing from the scope of the present application. It is therefore intended that the application not be limited to the particular embodiment disclosed as the best mode contemplated for carrying out this application, but that the application include all embodiments falling within the scope of the application.

[0121] The above merely provides the optional embodiments of the present application, but does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An image processing method, characterized by, The method comprises: In the case of being in a 2D display mode, in response to receiving a switching instruction, a global image for 3D display is acquired, wherein the switching instruction is used to indicate switching from the 2D display mode to the 3D display mode; By means of a first image processing model trained in advance, pixel values of each pixel point in the global image are adjusted to obtain a first target image with improved image brightness; In the 3D display mode, the first target image is displayed.

2. The method of claim 1, wherein, The first image processing model is trained based on first training images labeled with brightness information, and the brightness information is used to indicate the brightness level of the first training images; The first image processing model is trained by taking the difference between a first output image processed by means of the first training images and a first template image with corresponding brightness information satisfying a set condition as a loss function.

3. The method of claim 1, wherein, After the step of acquiring the global image for 3D display in response to receiving the switching instruction, the method further comprises: By means of a second image processing model trained in advance, pixel values of each pixel point in the global image are adjusted to obtain a second target image with enhanced color and / or contrast; Based on the first target image and the second target image, a third target image is determined, and the third target image is displayed in the 3D display mode.

4. The method of claim 1, wherein, After the step of adjusting, by means of the first image processing model trained in advance, the pixel values of each pixel point in the global image to obtain the first target image with improved image brightness, the method further comprises: By means of a second image processing model trained in advance, pixel values of each pixel point in the first target image are adjusted to obtain a fourth target image with enhanced color and / or contrast; In the 3D display mode, the fourth target image is displayed.

5. The method according to claim 3 or 4, characterized in that, The second image processing model is trained based on second training images labeled with semantic information, and the semantic information is used to indicate at least one of a scene of the second training images, an object edge in the second training images, and an object color; The second image processing model is trained by taking the difference between a second output image processed by means of the second training images and a second template image with corresponding color representation and image contrast satisfying a set condition as a loss function.

6. The method of claim 1, wherein, The method further comprises: In response to receiving the switching instruction, a current device display brightness is acquired; In the case that the current device display brightness does not reach a highest device display brightness, the device display brightness is improved to the highest device display brightness, so that the highest device display brightness is used for image display in the 3D display mode.

7. The method of claim 1, wherein, The global image comprises a left-eye image and a right-eye image, or the global image is an image corresponding to the effect of superimposing the left-eye image and the right-eye image.

8. An image processing apparatus characterized by comprising: The device comprises: An acquisition module, configured to, in the case of being in a 2D display mode, acquire a global image for 3D display in response to receiving a switching instruction, wherein the switching instruction is used to indicate switching from the 2D display mode to the 3D display mode; An adjusting module is configured to adjust pixel values of each pixel point in the global image by using a pre-trained first image processing model to obtain a first target image with improved image brightness. A display module is configured to display the first target image in a 3D display mode.

9. A display device, characterized by The display device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the operations performed by the image processing method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program, and the program is executed by the processor to perform the operations performed by the image processing method according to any one of claims 1 to 7.

11. A computer program product, characterised in that, The computer program product includes a computer program, and when the computer program is executed by the processor, the operations performed by the image processing method according to any one of claims 1 to 7 are implemented.

Images