Electronic apparatus and wallpaper generation method thereof

Abstract

An electronic device and a method for generating its wallpaper. The method includes the following steps: acquiring an original image; detecting the arrangement and display specifications of multiple display devices; determining a target image resolution based on the arrangement and display specifications of each display device; augmenting the original image into a target augmented image with the target image resolution using an image inpainting model; and generating wallpapers displayed on each display device by segmenting the target augmented image.

Description

Technical Field

[0001] This invention relates to an electronic device, and more particularly to an electronic device and a method for producing a tablecloth therewith. Prior Technology

[0002] With the advancement of technology, powerful performance and a wide range of applications have made electronic devices indispensable items in modern people's daily lives. Generally speaking, these electronic devices can display the user's favorite wallpaper on the screen, thereby enhancing the aesthetics of the device and achieving a personalized effect.

[0003] Currently, when users want to change their monitor's wallpaper, after finally finding a picture they like, they often need to manually edit the image because the image resolution doesn't match the screen resolution, thus requiring them to adjust the wallpaper display to their expectations. This manual image editing process is quite inconvenient and time-consuming for users. Furthermore, when users use multiple monitors, if they want all monitors to display wallpapers of a similar style, they need to spend even more time searching for other images with similar styles. Summary of the Invention

[0004] In view of this, the present invention proposes an electronic device and a method for generating a tablecloth therewith, which can solve the above-mentioned technical problems.

[0005] This invention provides a method for generating tablecloths, the method comprising the following steps: acquiring an original image; detecting the arrangement and display specifications of multiple display devices; determining a target image resolution based on the arrangement and display specifications of each display device; augmenting the original image into a target augmented image with the target image resolution using an image inpainting model; and generating tablecloths displayed on each display device by segmenting the target augmented image.

[0006] This invention provides an electronic device including a storage device and a processor. The processor is coupled to the storage device and configured to perform the following operations: acquiring an original image; detecting the arrangement and display specifications of a plurality of display devices; determining a target image resolution based on the arrangement and display specifications of each display device; augmenting the original image into a target augmented image with the target image resolution using an image inpainting model; and generating a wallpaper to be displayed on each display device by segmenting the target augmented image.

[0007] Based on the above, in embodiments of the present invention, an image restoration model can be used to augment the original image into a target augmented image with a target image resolution, wherein the target image resolution is determined according to the arrangement and display specifications of each display device. Therefore, the target augmented image can be segmented based on the arrangement and display specifications of each display device to generate wallpapers displayed on each display device. In this way, wallpaper images conforming to the resolution and layout configuration of multiple display devices can be dynamically generated, eliminating the need for users to manually edit or search for images, thus improving the user experience. Simple Explanation of the Diagram

[0008] Figure 1A is a block diagram of a multi-screen display system according to an embodiment of the present invention. Figure 1B is a schematic diagram of a multi-screen display system according to an embodiment of the present invention. Figure 2 is a flowchart of a tablecloth generation method according to an embodiment of the present invention. Figure 3 is a flowchart of generating a target augmented image according to an embodiment of the present invention. Figure 4 is a schematic diagram of generating a target augmented image according to an embodiment of the present invention. Figures 5A and 5B are schematic diagrams illustrating an application scenario of multiple displays according to an embodiment of the present invention. Figure 6 is a flowchart of a tablecloth generation method according to an embodiment of the present invention. Figure 7 is a schematic diagram of an application scenario of a plurality of display devices according to an embodiment of the present invention. Implementation

[0009] Some embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Component symbols used in the following description are considered identical or similar when they appear in different drawings. These embodiments are only a part of the present invention and do not disclose all possible implementations of the invention. More precisely, these embodiments are merely examples of the methods and apparatuses within the scope of the present invention's patent application.

[0010] Figure 1A is a block diagram of a multi-screen display system according to an embodiment of the present invention. Referring to Figure 1A, the multi-screen display system 10 includes a plurality of display devices 110_1 to 110_n, a storage device 120, and a processor 130. This disclosure does not limit the number of the plurality of display devices 110_1 to 110_n. Furthermore, in some embodiments, one of the plurality of display devices 110_1 to 110_n may be implemented with the storage device 120 and the processor 130 as an electronic device with display functionality. In some embodiments, the plurality of display devices 110_1 to 110_n may also be daisy-chained, but the present invention is not limited thereto.

[0011] For example, FIG1B is a schematic diagram of a multi-screen display system according to an embodiment of the present invention. Referring to the embodiment of FIG1B, the number of multiple display devices 110_1 to 110_2 is two. Display device 110_1 can be implemented with storage device 120 and processor 130 as an electronic device 100 with display function. The aforementioned electronic device 100 is, for example, a tablet computer, a laptop computer, a desktop computer, or an all-in-one computer, etc., and this disclosure is not limited thereto. Display device 110_2 can be connected to electronic device 100 via a wired or wireless transmission interface. For example, the aforementioned transmission interface is, for example, a DP transmission interface, an HDMI transmission interface, a USB-C transmission interface, or a WiFi transmission interface, etc.

[0012] The display devices 110_1 to 110_n are, for example, liquid crystal displays (LCDs), light-emitting diode (LED) displays, organic light-emitting diode (OLED) displays, or other types of displays, and the present invention is not limited thereto.

[0013] Storage device 120 is used to store data and software modules (such as operating systems, applications, drivers) accessible to processor 130. It can be, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk, or a combination thereof.

[0014] Processor 130 is coupled to multiple display devices 110_1 to 110_n and storage device 120. Processor 130 may be, for example, a Central Processing Unit (CPU), an application processor (AP), or other programmable general-purpose or special-purpose microprocessor, digital signal processor (DSP), programmable controller, application-specific integrated circuit (ASIC), programmable logic device (PLD), graphics processing unit (GPU), or other similar devices or combinations thereof. Processor 130 can execute program code, software modules, instructions, etc., recorded in storage device 110 to implement the dynamic wallpaper display method of this embodiment.

[0015] Figure 2 is a flowchart of a tablecloth generation method according to an embodiment of the present invention, and the method flow of Figure 2 can be implemented by the components of the multi-screen display system 10 of Figure 1A. Please refer to Figures 1A and 2 simultaneously. The steps of the tablecloth generation method of this embodiment will be described below with reference to the components of Figure 1A.

[0016] In step S210, processor 130 acquires an original image. This disclosure does not limit the resolution of the original image. The original image may be a photograph, a preset wallpaper image built into electronic device 100, or any image downloaded by the user from the internet.

[0017] In some embodiments, the processor 130 can also generate multiple candidate images with different or similar image styles based on a reference image, and select the original image from the multiple candidate images according to user instructions. For example, the processor 130 can input the reference image into a trained image style transfer model to generate these candidate images. Based on this, the diversity of wallpapers for multiple display devices 110_1 to 110_n can be improved.

[0018] In step S220, the processor 130 detects the arrangement and display specifications of the plurality of display devices 110_1 to 110_n. In some embodiments, the display specifications include screen resolution and screen size. In different embodiments, the screen resolution and screen size of these display devices 110_1 to 110_n may be the same or different from each other. For example, in FIG1B, the screen resolution of display device 110_1 may be 1920x1080, and the screen size of display device 110_1 may be 15.6 inches. In addition, the screen resolution of display device 110_2 may be 1920x1080, and the screen size of display device 110_1 may be 24 inches. However, this is only used as an example, and this disclosure is not limited thereto.

[0019] Furthermore, the processor 130 can identify the arrangement of the display devices 110_1 to 110_n to obtain the arrangement position of each display device 110_1 to 110_n. For example, in Figure 1B, the display devices 110_1 to 110_2 are arranged side by side, but this is not a limitation. In other words, the processor 130 can identify that display device 110_2 is located to the right of display device 110_1. The processor 130 can obtain the arrangement position of each display device 110_1 to 110_n, for example, through specific Windows APIs provided by the Windows operating system.

[0020] In step S230, the processor 130 determines a target image resolution based on the arrangement and display specifications of each display device 110_1~110_n. That is, the processor 130 can determine the range of additional image augmentation content to be generated based on the arrangement and display specifications of each display device 110_1~110_n. For example, assuming that display devices 110_1~110_2 are arranged side-by-side and have the same screen size and resolution, the processor 130 can multiply the width of this screen resolution by 2 to obtain the width of the target image resolution (representing the horizontal direction the processor 130 needs to generate image augmentation content), and set the height of the target image resolution equal to the height of this screen resolution. Next, in step S240, the processor 130 uses an image inpainting model to augment the original image into a target augmented image with the target image resolution.

[0021] In some embodiments, FIG3 is a flowchart of generating a target amplified image according to an embodiment of the present invention. To clearly illustrate the implementation principle of the present invention, FIG4 is used in conjunction with the following description. FIG4 is a schematic diagram of generating a target amplified image according to an embodiment of the present invention. Please refer to FIG3 and FIG4.

[0022] In step S310, the processor 130 determines an input mask image IMG_im1, including a mask block MB1 and the original image IMG_ori1, based on the arrangement and layout positions of the various display devices 110_1 to 110_n and the resolution of the target image. The mask block MB1 represents the area that needs to be filled in by the image inpainting model. It is understood that after determining the resolution of the target image, the area of ​​the mask block MB1 can be determined based on the resolution of the original image IMG_ori1 and the arrangement and layout positions of the various display devices 110_1 to 110_n.

[0023] In other embodiments, the processor 130 may first extract a portion of the image from the original image. Then, the processor 130 determines an input mask image, including a mask block and a portion of the original image, based on the arrangement and layout of the various display devices 110_1 to 110_n and the resolution of the target image. That is, the input mask image only includes a portion of the original image, with the remaining portion being a mask block.

[0024] Subsequently, in step S320, the processor 130 uses an image inpainting model to inpaint the input masked image IMG_im1 into the target augmented image IMG_t1. In this embodiment, step S320 can be implemented as steps S321 to S323.

[0025] In step S321, the processor 130 performs an image scaling process on the input mask image IMG_im1 to generate a scaled mask image IMG_s1. That is, the processor 130 first scales the input mask image IMG_im1 to conform to the model input format of the image restoration model.

[0026] In step S322, processor 130 inputs the scaled masked image IMG_s1 into the image inpainting model to obtain an inpainted image IMG_f1. The image inpainting model is a deep learning model used to fill in missing, damaged, or incomplete portions of an image. Image inpainting models are typically based on convolutional neural networks (CNNs) or generative adversarial networks (GANs), which learn to infer the content of missing regions from the context of an image. Furthermore, in some embodiments, processor 130 may also input text content into the image inpainting model, allowing the model to fill in the image based on the text content. For example, processor 130 may use a Stable Diffusion model combined with an inpainting ControlNet model to generate the inpainted image IMG_f1. In some embodiments, the text content may be input by a user. In other embodiments, processor 130 may use an image-to-text model to generate the text content from the original image.

[0027] In step S323, the processor 130 performs another image scaling process on the repaired image IMG_f1 to generate a target augmented image IMG_t1 with the target image resolution. That is, the processor 130 can scale the repaired image IMG_f1, which conforms to the model output format, into a target augmented image IMG_t1 with the target image resolution.

[0028] In some embodiments, the processor 130 may also overlay the original image IMG_ori onto the target augmented image IMG_t1 to ensure that the target augmented image IMG_t1 includes the original content of the original image IMG_ori1, thereby improving the phenomenon that multiple image scaling processes may lead to a decrease in image quality.

[0029] In step S250, the processor 130 generates wallpapers to be displayed on each of the display devices 110_1 to 110_n by segmenting the target augmented image IMG_t1. That is, the target augmented image IMG_t1 is segmented to generate wallpapers for each of the display devices 110_1 to 110_n. It is expected that, compared to directly enlarging the original image and displaying it blurry on each display device, the wallpaper images of this disclosed embodiment will have better quality and clearer images.

[0030] Figures 5A and 5B are schematic diagrams illustrating an application scenario of multiple displays according to an embodiment of the present invention. Referring first to Figure 5A, based on the display specifications and arrangement of display devices 110_1 to 110_3, processor 130 can generate a target augmented image IMG_t2 from the original image IMG_ori2. As shown in Figure 5A, processor 130 generates augmented image content to the right and left of the original image IMG_ori2. Thus, the main display device 110_1 can display the middle sub-image SIMG1 as a wallpaper. The left display device 110_2 can display the left sub-image SIMG2 as a wallpaper. The right display device 110_3 can display the right sub-image SIMG3 as a wallpaper.

[0031] Referring first to Figure 5B, based on the display specifications and layout of display devices 110_1 to 110_3, processor 130 can generate a target augmented image IMG_t3 from the original image IMG_ori2. As shown in Figure 5B, processor 130 generates augmented image content towards the upper right of the original image IMG_ori2. Then, processor 130 can cut three sub-images SIMG4 to SIMG6 from the target augmented image IMG_t3. Thus, the main display device 110_1 can display the lower left sub-image SIMG4 as a background image. The upper display device 110_2 can display the upper left sub-image SIMG5 as a background image. The right display device 110_3 can display the right sub-image SIMG6 as a background image.

[0032] It should be noted that when the pixel density (Pixels Per Inch, PPI) of these display devices 110_1~110_n differs too much, if the target image resolution and image segmentation are determined solely based on the screen resolution of display devices 110_1~110_n, misalignment of the wallpaper content displayed on these display devices 110_1~110_n may occur (e.g., the wallpaper content of display device 110_1 in Figure 5A is not properly aligned with the wallpaper content of display device 110_2). Therefore, in some embodiments, the processor 130 may further determine the target image resolution and perform image segmentation based on the pixel density of these display devices 110_1~110_n. An embodiment will be described in detail below.

[0033] Figure 6 is a flowchart of a tablecloth generation method according to an embodiment of the present invention, and the method flow of Figure 6 can be implemented by the various components of the electronic device 100 of Figure 1. Please refer to Figures 1 and 6 simultaneously.

[0034] In step S610, processor 130 acquires an original image. In step S620, processor 130 detects the arrangement and display specifications of the plurality of display devices 110_1 to 110_n. The display specifications include screen resolution and screen size. These steps can be referred to the foregoing embodiments for description, and will not be repeated here.

[0035] In step S630, the processor 130 determines the resolution of a target image based on the arrangement and display specifications of each display device 110_1~110_n. In this embodiment, step 630 can be implemented as steps S631 to S632.

[0036] In step S631, the processor 130 calculates the pixel density (Pixels Per Inch, PPI) of each display device 110_1 to 110_n based on the display specification parameters of each display device 110_1 to 110_n. For example, the processor 130 may calculate the pixel density of each display device 110_1 to 110_n according to the following formula (1). Equation (1) Where dp is the screen diagonal resolution; wp is the screen horizontal resolution; hp is the screen vertical resolution; and di is the actual length of the screen diagonal (in inches).

[0037] In step S632, the processor 130 compares the pixel density of each display device 110_1 to 110_n. In step S633, the processor 130 determines the target image resolution based on the comparison result and the screen resolution of each display device 110_1 to 110_n.

[0038] In some embodiments, when the pixel densities of the various display devices 110_1 to 110_n are quite similar, the processor 130 can determine the target image resolution solely based on the screen resolution and layout position of each display device 110_1 to 110_n. For example, when the display devices 110_1 to 110_n are arranged horizontally, the width of the target image resolution can be the sum of the widths of the screen resolutions of the display devices 110_1 to 110_n. When the display devices 110_1 to 110_n are arranged vertically, the height of the target image resolution can be the sum of the heights of the screen resolutions of the display devices 110_1 to 110_n.

[0039] In some embodiments, when the pixel densities of the various display devices 110_1 to 110_n differ significantly, the processor 130 can determine the target image resolution based on the ratio between the pixel densities of the display devices, the screen resolution of each display device 110_1 to 110_n, and their layout arrangement. That is, the processor 130 needs to determine the range of image augmentation content based on the degree of difference in pixel density, so that display devices with lower pixel densities can acquire a larger range of image content for reduced-size display.

[0040] In some embodiments, the pixel density comparison includes a ratio between the pixel density of the first display device and the pixel density of the second display device, where the ratio is greater than or equal to 1. The processor 130 can calculate a first multiplication of the width of the screen resolution of the first display device with the ratio. Then, the processor 130 can add the width of the screen resolution of the second display device to the first multiplication result to produce the width of the target image resolution. Here, the pixel density of the first display device is less than the pixel density of the second display device. Furthermore, in some embodiments, the processor 130 can calculate a second multiplication of the height of the screen resolution of the first display device with the ratio. Then, the processor 130 can set the larger of the second multiplication result and the height of the screen resolution of the second display device as the height of the target image resolution.

[0041] In another embodiment, processor 130 may calculate a first multiplication result of the height of the screen resolution of the first display device and the ratio. Then, processor 130 may add the first multiplication result to the height of the screen resolution of the second display device to produce the height of the target image resolution. Here, the pixel density of the first display device is less than the pixel density of the second display device. Furthermore, in some embodiments, processor 130 may calculate a second multiplication result of the width of the screen resolution of the first display device and the ratio. Then, processor 130 may set the larger of the second multiplication result and the width of the screen resolution of the second display device as the width of the target image resolution.

[0042] For example, Figure 7 is a schematic diagram of an application scenario of multiple display devices according to an embodiment of the present invention. Referring to Figure 7, to clearly illustrate the principle of the present invention, Figure 7 uses two display devices 110_1 to 110_2 arranged horizontally side by side as an example. Furthermore, the display specifications of display device 110_1 are A inches and W1 x H1, and the display specifications of display device 110_2 are B inches and W2 x H2.

[0043] Assuming A = 15.6 inches; B = 24 inches; W1 = W2 = 1920; H1 = H2 = 1080, processor 130 can calculate that the pixel density of display device 110_1 is approximately 142 PPI, and the pixel density of display device 110_2 is approximately 94 PPI. The ratio between the pixel density of display device 110_1 and the pixel density of display device 110_2 is approximately 1.5. Therefore, since the pixel density of display device 110_2 (i.e., the first display device) is smaller than the pixel density of display device 110_1 (i.e., the second display device), processor 130 can first multiply the width W2 and height H2 of the screen resolution of display device 110_2 by 1.5 respectively, to produce a first multiplication result W' = 1.5 * W2 and a second multiplication result 1.5 * H2. Then, the height H' of the target image resolution is equal to the second multiplication result 1.5 * H2, and the width W71 of the target image resolution is equal to the second multiplication result W' plus the width W1 of the screen resolution of the display device 110_1. Substituting the values ​​assumed above, we know that the target image resolution is equal to 4800 x 1620.

[0044] Next, in step S640, the processor 130 uses an image inpainting model to augment the original image into a target augmented image with the resolution of the target image. These steps can be referred to the foregoing embodiments for description, and will not be repeated here.

[0045] In step S650, the processor 130 generates a wallpaper to be displayed on each of the display devices 110_1 to 110_n by segmenting the target augmented image. In this embodiment, step 650 can be implemented as steps S651 to S652.

[0046] In step S651, the processor 130 divides the target augmented image into multiple sub-images corresponding to multiple display devices 110_1 to 110_n according to the comparison result and the arrangement and layout positions of each display device 110_1 to 110_n.

[0047] In some embodiments, when the pixel densities of the various display devices 110_1 to 110_n are quite similar, the processor 130 can segment the target augmented image based solely on the screen resolution and layout position of each display device 110_1 to 110_n. For example, when the display devices 110_1 to 110_n are arranged horizontally, the processor 130 can segment the target augmented image into multiple horizontally arranged sub-images based solely on the width of the screen resolution of each display device 110_1 to 110_n, thereby obtaining multiple sub-images of the multiple display devices 110_1 to 110_n. When the display devices 110_1 to 110_n are arranged vertically, the processor 130 can segment the target augmented image into multiple vertically arranged sub-images based solely on the height of the screen resolution of each display device 110_1 to 110_n, thereby obtaining multiple sub-images of the multiple display devices 110_1 to 110_n.

[0048] In some embodiments, when the pixel density differences between the various display devices 110_1 to 110_n are large, the processor 130 can determine the target image resolution based on a ratio between the pixel densities of two adjacent display devices, the screen resolution of each display device 110_1 to 110_n, and their layout arrangement, to segment the target augmented image. That is, the processor 130 needs to determine the image content allocated to each display device based on the degree of difference in pixel density, so that display devices with lower pixel density can acquire a larger range of image content for reduced-size display.

[0049] In some embodiments, this comparison result includes a ratio between the pixel density of the first display device and the pixel density of the second display device, wherein the ratio is greater than or equal to 1. That is, the larger of the pixel density of the first display device and the pixel density of the second display device is used as the numerator of the ratio, and the smaller of the pixel density of the first display device and the pixel density of the second display device is used as the denominator of the ratio.

[0050] In some embodiments, the pixel density of the first display device is less than that of the second display device. Therefore, the image resolution of the second sub-image corresponding to the second display device is equal to the screen resolution of the second display device, and the image resolution of the first sub-image corresponding to the first display device is equal to the screen resolution of the first display device multiplied by a ratio.

[0051] For example, please refer to Figure 7 again. After the processor 130 determines the target image resolution W71 x H'2, the processor 130 can generate an input mask image IMG_im2, which includes the original image IMG_ori3 and the masked block. Then, the processor 130 can use an image inpainting model to generate a target augmented image IMG_t4 based on the input mask image IMG_im2. Next, the processor 130 can segment sub-images SIMG7 to SIMG8 from the target augmented image IMG_t4 based on the ratio between pixel densities and the respective screen resolutions of display devices 110_1 to 110_2. Since the pixel density of display device 110_2 (i.e., the first display device) is smaller than the pixel density of display device 110_1 (i.e., the second display device), the image resolution of the sub-image SIMG7 acquired by the processor 130 is equal to the screen resolution of display device 110_1. Furthermore, the image resolution of the sub-image SIMG8 acquired by the processor 130 is equal to the screen resolution of the display device 110_2 multiplied by a ratio of 1.5. Assuming A=15.6; B=24; W1=W2=1920; H1=H2=1080, then the image resolution of the sub-image SIMG7 of the display device 110_1 is 1920x1080, while the image resolution of the sub-image SIMG8 of the display device 110_2 is 2880x1620.

[0052] In step S652, the processor 130 generates a wallpaper to be displayed on each of the display devices 110_1 to 110_n based on multiple sub-images. In some embodiments, the processor 130 performs an image reduction process on the first sub-image corresponding to the first display device according to the screen resolution of the first display device to obtain the wallpaper for the first display device. That is, the processor 130 can perform image reduction processing on the sub-image of the display device with poor pixel density to generate the final wallpaper. Taking FIG7 as an example, the processor 130 can display the 1920x1080 sub-image SIMG7 as the wallpaper of the display device 110_1. In addition, the processor 130 can perform image reduction processing on the 2880x1620 sub-image SIMG8 to obtain a 1920x1080 wallpaper displayed by the display device 110_2. Based on this, the content of the wallpaper displayed on the display device 110_1 and the wallpaper displayed on the display device 110_2 can be aligned.

[0053] In summary, in the embodiments of the present invention, an image inpainting model can be used to augment the original image into a target augmented image with a target image resolution, wherein the target image resolution is determined based on the arrangement and display specifications of each display device. Therefore, the target augmented image can be segmented based on the arrangement and display specifications of each display device to generate wallpapers displayed on each display device. Based on this, wallpaper images conforming to the resolution and layout configuration of multiple display devices can be dynamically generated, eliminating the need for users to manually edit or search for images, thus improving the user experience. Furthermore, in the embodiments of the present invention, wallpaper content suitable for each display device can be generated based on the differences in pixel density between these display devices, thereby improving the aesthetics and alignment of the wallpapers displayed on these display devices.

[0054] Although the present invention has been disclosed above by way of embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make some modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0055] 10: Multi-screen display system 100: Electronic devices 110_1~110_n: Display device 120: Storage device 130: Processor IMG_ori1, IMG_ori2, IMG_ori3: Original images MB1: Masking Block IMG_t1, IMG_t2, IMG_t3, IMG_t4: Target augmented images IMG_im1, IMG_im2: Input masking images IMG_s1: Scaled masked image IMG_f1: Repaired image SIMG1~SIMG8: Sub-images S210~S250, S310~S323, S610~S651: Steps

Claims

1. A method for generating a tablecloth, the method comprising: Obtain a raw image; Detects the arrangement and display specifications of multiple display devices; Based on the arrangement and display specifications of the plurality of display devices, a target image resolution is determined; after determining the target image resolution, based on the resolution of the original image and the arrangement of the plurality of display devices, the area of ​​a masking block is determined, and an input masking image is formed using the original image and the masking block, wherein the masking block represents a block in the input masking image where content is missing; an image inpainting model is used to restore the input masking image into a target augmented image with the target image resolution, wherein the image inpainting model is a deep learning model, the image inpainting model infers and generates the content of the masking block based on the original image in the input masking image, and fills the masking block with the generated content; and a wallpaper displayed on the plurality of display devices is generated by segmenting the target augmented image.

2. The wallpaper generation method as described in claim 1, wherein the display specifications include screen resolution and screen size.

3. The tablecloth generation method as described in claim 1, wherein the step of restoring the input mask image to the target augmented image using the image inpainting model includes: The input mask image is subjected to an image scaling process to produce a scaled mask image; The scaled masked image is input into the image restoration model to obtain a restored image; and the restored image is subjected to another image scaling process to generate the target augmented image with the resolution of the target image.

4. The tablecloth generation method as described in claim 2, wherein the step of determining the target image resolution based on the arrangement and layout positions of each of the plurality of display devices and the display specification parameters includes: Calculate the pixel density (Pixels Per Inch, PPI) of each of the plurality of display devices based on the display specification parameters of each of the plurality of display devices; compare the pixel densities of each of the plurality of display devices; and determine the target image resolution based on the comparison results and the screen resolution of each of the plurality of display devices.

5. The method for generating a tablecloth as described in claim 4, wherein the plurality of display devices includes a first display device and a second display device, the comparison result includes a ratio between the pixel density of the first display device and the pixel density of the second display device, the ratio being greater than or equal to 1, and the step of determining the target image resolution based on the comparison result and the screen resolution of each of the plurality of display devices includes: Calculate a first multiplication result of the width of the screen resolution of the first display device and the ratio, wherein the pixel density of the first display device is less than the pixel density of the second display device; and add the first multiplication result to the width of the screen resolution of the second display device to generate the width of the target image resolution.

6. The tablecloth generation method as described in claim 5, wherein the step of determining the target image resolution based on the comparison result and the screen resolution of each of the plurality of display devices further includes: Calculate the second product of the height of the screen resolution of the first display device and the ratio; And the larger of the second multiplication result and the high resolution of the screen of the second display device is set as the high resolution of the target image.

7. The tablecloth generation method as claimed in claim 4, wherein the step of generating the tablecloth displayed on each of the plurality of display devices by segmenting the target augmented image includes: Based on the comparison results and the arrangement positions of the plurality of display devices, the target augmented image is segmented into a plurality of sub-images corresponding to the plurality of display devices; and a wallpaper is generated based on the plurality of sub-images and displayed on the plurality of display devices.

8. The tablecloth generation method as claimed in claim 7, wherein the plurality of display devices includes a first display device and a second display device, the comparison result includes a ratio between the pixel density of the first display device and the pixel density of the second display device, the ratio being greater than or equal to 1, the pixel density of the first display device being less than the pixel density of the second display device, the image resolution corresponding to a second sub-image of the second display device being equal to the screen resolution of the second display device, and the image resolution corresponding to a first sub-image of the first display device being equal to the screen resolution of the first display device multiplied by the ratio.

9. The method for generating a tablecloth as claimed in claim 7, wherein the plurality of display devices includes a first display device and a second display device, the pixel density of the first display device is less than the pixel density of the second display device, and the step of generating a tablecloth displayed on each of the plurality of display devices based on the plurality of sub-images includes: Based on the screen resolution of the first display device, an image reduction process is performed on the first sub-image corresponding to the first display device to obtain the tablecloth of the first display device.

10. An electronic device comprising: A storage device that records multiple instructions; The system includes at least one processor coupled to the storage device, configured to: acquire an original image; detect the arrangement and display specifications of a plurality of display devices; determine a target image resolution based on the arrangement and display specifications of each of the plurality of display devices; after determining the target image resolution, determine the area of ​​a masking block based on the resolution of the original image and the arrangement of each of the plurality of display devices, thereby forming an input masking image with the original image and the masking block, wherein the masking block represents a block of missing content in the input masking image; restore the input masking image to a target augmented image with the target image resolution using an image inpainting model, wherein the image inpainting model is a deep learning model that infers and generates the content of the masking block based on the original image in the input masking image, and fills in the masking block with the generated content; and generate a wallpaper to be displayed on each of the plurality of display devices by segmenting the target augmented image.

Images