Hole filling method and device, electronic equipment and storage medium

Abstract

The invention provides a hole filling method and device, electronic equipment and a storage medium, and the method comprises the steps: determining an edge point set of a to-be-filled image, the edge point set comprises at least one edge point, and the edge point indicates a projected pixel point of at least one blank pixel point in four neighborhoods; for each edge point in the edge point set, determining each blank pixel point in four neighborhoods of the edge point, and determining an average color value of the blank pixel point in a preset area, so as to fill the blank pixel point according to the average color value to obtain a filled pixel point; and determining that all blank pixel points in the to-be-filled image are filled so as to obtain a complete image. Through the method and the device, the filling continuity is effectively improved, the visual quality is improved, the calculation efficiency of a texture hole filling algorithm is improved, and the technical problems of color mutation, texture incoherence and low efficiency in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of texture hole filling, in particular to a hole filling method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the field of three-dimensional mesh texture encoding, texture mapping based on UV mapping is the mainstream technology. Due to the complex geometry structure of three-dimensional models and the inherent limitations of the reparameterization process, a large number of blank pixel regions that are not covered by the model surface, i.e. texture holes, often appear on the texture map obtained by reparameterization.

[0003] To handle the holes, the existing technology often uses a simple strategy such as nearest neighbor filling, i.e. directly assigning the blank pixels to the color value of the nearest projected pixel at their spatial position. Although this method is simple to calculate, it is easy to produce harsh and stepped color mutations between the filling boundary and the original texture, directly destroying the natural continuity of the texture - and texture continuity is a key prerequisite for encoding compression. Such mutations will lead to the inability to effectively eliminate redundant information during encoding, ultimately resulting in a larger file size after texture map compression and poor encoding effect. At the same time, due to the inherent defects of its own filling strategy, this method has a large amount of invalid redundant calculation, resulting in a large amount of calculation and low execution efficiency in the filling process. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a hole filling method, device, electronic equipment and storage medium, which aims to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, the present application provides a hole filling method, comprising: determining a set of edge points of a to-be-filled image, the set of edge points comprising at least one edge point, the edge point indicating that there is at least one blank pixel point in the four-neighbor domain of the projected pixel point; for each edge point in the set of edge points, determining each blank pixel point in the four-neighbor domain of the edge point, and determining the average color value in the preset region of the blank pixel point, to fill the blank pixel point according to the average color value, to obtain a filled pixel point; determining that all blank pixel points in the to-be-filled image are filled, to obtain a complete image.

[0006] In a preferred example of the present application, all blank pixel points in the to-be-filled image are determined to be filled by the following method: for each filled pixel point, determining whether there is a blank pixel point in the four-neighbor domain of the filled pixel point; When there is no blank pixel point in the four-neighbor domain of each filled pixel point, it is determined that all blank pixel points in the image to be filled are filled.

[0007] In a preferred example of the present application, further comprising: When there is a blank pixel point in the four-neighbor domain of the filled pixel point, for each filled pixel point with a blank pixel point in the four-neighbor domain, the corresponding blank pixel point of the filled pixel point is determined, and the average color value in the preset region of each blank pixel point is determined to fill the blank pixel point according to the average color value.

[0008] In a preferred example of the present application, the average color value in the preset region of each blank pixel point is determined by the following method: For each blank pixel point, a preset region centered on the blank pixel point is determined, the color value of each projected pixel in the preset region is counted to calculate the arithmetic mean of the color values of all projected pixels in the preset region, and the average color value is determined, which includes the component values of the corresponding color space.

[0009] In a preferred example of the present application, the edge point set is determined by the following method: The binary occupancy map corresponding to the image to be filled is obtained, the pixel points with a value of 1 in the binary occupancy map are determined as projected pixel points, and the pixel points with a value of 0 in the binary occupancy map are determined as blank pixel points. All projected pixel points with at least one blank pixel point in the upper, lower, left and right directions form the edge point set.

[0010] In a preferred example of the present application, each blank pixel point in the four-neighbor domain of each edge point is determined by the following method: The breadth-first search framework is used to traverse all pixel points in the four-neighbor domain of each edge point to determine each blank pixel point in the four-neighbor domain of each edge point.

[0011] In a second aspect, the present application provides a hole filling device, the device comprising: A hole detection module for determining an edge point set of an image to be filled, the edge point set comprising at least one edge point, the edge point indicating a projected pixel point with at least one blank pixel point in the four-neighbor domain; A filling execution module for determining each blank pixel point in the four-neighbor domain of each edge point in the edge point set, and determining the average color value in the preset region of the blank pixel point, to fill the blank pixel point according to the average color value, to obtain a filled pixel point; The output module is configured to determine that all the blank pixel points in the image to be filled are filled to obtain a complete image.

[0012] In a preferred example of the present application, the output module is further configured to: For each filled pixel point, determine whether there is a blank pixel point in the four-neighbor domain of the filled pixel point; When there is no blank pixel point in the four-neighbor domain of each filled pixel point, it is determined that all the blank pixel points in the image to be filled are filled.

[0013] In a third aspect, the present application also provides an electronic device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the above method.

[0014] In a fourth aspect, the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the steps of the above method.

[0015] The present application provides a hole filling method, device, electronic device and storage medium, wherein the method comprises: determining an edge point set of an image to be filled, the edge point set comprising at least one edge point, the edge point indicating a projected pixel point with at least one blank pixel point in the four-neighbor domain; for each edge point in the edge point set, determining each blank pixel point in the four-neighbor domain of the edge point, and determining an average color value in a preset region of the blank pixel point to fill the blank pixel point according to the average color value to obtain a filled pixel point; and determining that all the blank pixel points in the image to be filled are filled to obtain a complete image. Through the present application, on the one hand, the color abrupt change problem in the prior art is effectively eliminated, the texture filling continuity is significantly improved, the texture map has a better encoding compression basis, and the core requirement of smaller file size after texture map compression is effectively achieved; on the other hand, the calculation efficiency of texture hole filling is greatly improved by optimizing the algorithm strategy, and the technical problems of texture incoherence, poor encoding compression effect and low execution efficiency in the prior art are fundamentally solved.

[0016] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0018] Figure 1 A flowchart of a hole filling method provided by an embodiment of the present application; Figure 2 A flowchart of determining a set of edge points provided by an embodiment of the present application; Figure 3 A flowchart of determining that all white pixel points are filled provided by an embodiment of the present application; Figure 4 A comparison diagram of filling results provided by an embodiment of the present application; Figure 5 A structural diagram of a hole filling device provided by an embodiment of the present application; Figure 6 A structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by those skilled in the art without creative labor belongs to the scope of the present application.

[0020] First, the application scenarios applicable to the present application are introduced. The present application can be applied to the technical field of texture hole filling.

[0021] It is found through research that in three-dimensional grid texture coding, texture mapping based on UV mapping is the mainstream technology. However, due to the complex three-dimensional grid geometry structure and the limitations of the reparameterization process, the reparameterized texture map cannot be completely covered by pixels, resulting in a large number of white pixel regions, i.e. texture holes. These holes not only destroy the integrity of the texture map, but also seriously reduce the compression efficiency of the subsequent texture map, because the encoder needs to allocate unnecessary code rate for these regions without actual information.

[0022] To deal with the holes, the prior art usually adopts a simple strategy such as nearest neighbor filling, that is, each blank pixel is directly assigned the color value of the nearest projected pixel at its spatial position. Although this method is simple in calculation logic, it has obvious shortcomings: on the one hand, it is easy to produce a harsh and stepped color boundary between the filled area and the original texture, which seriously destroys the natural coherence of the texture, leads to the inability to effectively eliminate redundant information in the encoding process, and ultimately causes the texture graph to have a larger file size after compression, resulting in poor encoding compression effect; on the other hand, affected by the inherent defects of the initial seed point selection strategy, this method often regards all projected pixels as potential seeds for diffusion, and the pixels that do not need to be seeds participate in the diffusion process, resulting in a large amount of redundant calculation and thus low filling efficiency. For example, the hole filling algorithm built into the AVS grid encoding exploration model software MCEMv0.2 adopts this nearest neighbor strategy, and the file size of the encoded and compressed texture graph after filling cannot be effectively optimized.

[0023] Based on this, the embodiments of the present application provide a hole filling method and device, electronic equipment and storage medium, aiming to effectively improve the filling coherence and the calculation efficiency of the texture hole filling algorithm, so as to solve the technical problems of color mutation, texture incoherence and low efficiency existing in the prior art.

[0024] Please refer to Figure 1 , Figure 1 The flowchart of the hole filling method provided by the embodiments of the present application is shown in FIG. 1. Figure 1 As shown in FIG. 1, the hole filling method provided by the embodiments of the present application comprises the following steps. S101, determining an edge point set of a to-be-filled image.

[0025] Here, the edge point set includes at least one edge point, and the edge point indicates a projected pixel point with at least one blank pixel point in the four-neighbor domain.

[0026] The specific process of determining the edge point set will be described below. Figure 2 Please refer to

[0027] , Figure 2 Figure 2 The flowchart of determining the edge point set provided by the embodiments of the present application is shown in FIG. 2. Figure 2 As shown in FIG. 2, the steps of determining the edge point set provided by the embodiments of the present application comprise the following steps. S201, acquiring a binary occupancy map corresponding to the to-be-filled image, determining a pixel point with a value of 1 in the binary occupancy map as a projected pixel point, and determining a pixel point with a value of 0 in the binary occupancy map as a blank pixel point.

[0028] ​Specifically, the image to be filled and its binary occupancy map are generated by parameterizing a 3D mesh, where the occupancy map is used to identify pixel status: a value of 1 indicates a projected pixel and a value of 0 indicates a blank pixel.

[0029] S202. Form an edge point set by including all projected pixels that have at least one blank pixel in the top, bottom, left and right directions.

[0030] Here, this application uses a breadth-first search (BFS) framework to traverse all pixels in the four-neighborhood of each edge point to determine each blank pixel in the four-neighborhood of each edge point. By traversing the occupancy map, the projected pixels that satisfy the condition that there is at least one blank pixel in the four-neighborhood are determined as edge points and selected as initial seed points.

[0031] return Figure 1 S102. For each edge point in the edge point set, determine each blank pixel in the four neighboring areas of the edge point, and determine the average color value of the blank pixel in the preset area, so as to fill the blank pixel according to the average color value to obtain the filled pixel.

[0032] Here, starting from each edge point in the set of edge points, we iterate step by step based on BFS to process all blank pixels corresponding to each edge point.

[0033] In a preferred embodiment of this application, the average color value within a preset area of ​​each blank pixel is determined in the following manner: For each blank pixel, a preset area centered on that blank pixel is determined. The color value of each projected pixel within the preset area is counted. The arithmetic mean of the color values ​​of all projected pixels within the preset area is calculated to determine the average color value, which includes the component values ​​of the corresponding color space.

[0034] Specifically, during the BFS traversal, a local region averaging operation is performed on each blank pixel to be filled: a local region of a preset size (e.g., 16×16 pixels) is defined with it as the center, the R, G, and B color components of all projected pixels in the region are counted, the arithmetic mean (Ravg, Gavg, Bavg) of each color component is calculated, and the obtained average value is assigned as the color value (Ravg, Gavg, Bavg) of the blank pixel.

[0035] S103. Ensure that all blank pixels in the image to be filled are filled to obtain a complete image.

[0036] The following is through Figure 3 This section describes the specific process of ensuring that all blank pixels in the image to be filled are filled.

[0037] Please see Figure 3 , Figure 3 This is a flowchart illustrating how all blank pixels are filled, provided as an embodiment of this application. Figure 3 As shown in the embodiment of this application, the step of determining that all blank pixels are filled includes: S301. For each filled pixel, determine whether there are any blank pixels in the four neighboring regions of the filled pixel.

[0038] Here, this step involves performing a BFS traversal on all currently filled pixels to check if there are any blank pixels in the four neighboring areas (top, bottom, left, and right) of each pixel.

[0039] If not, proceed to step S302 to determine that all blank pixels in the image to be filled are filled.

[0040] Here, when the traversal check finds that there are no blank pixels within the four-neighborhood of any filled pixel, this constitutes a sufficient condition indicating that there are no blank pixels in the image adjacent to any filled area. Therefore, it can be determined that all blank pixels have been filled.

[0041] If it exists, then execute step S303: for each filled pixel with a blank pixel in its four neighboring regions, determine each blank pixel corresponding to the filled pixel, and fill the blank pixel according to the average color value of each blank pixel.

[0042] Here, if a filled pixel with a blank pixel in its neighborhood is found in step S301, it indicates that there are still holes to be filled. At this time, these filled pixels with blank pixels in their four neighborhoods are regarded as the starting point of a new round of diffusion, that is, new "edge points".

[0043] Then, for each new "edge point", a local area average filling operation is performed on each blank pixel in its four neighboring areas (the specific calculation method and filling method are as described in step S102, that is, the value is assigned based on the average color value of known pixels in the preset area around the blank pixel).

[0044] After all the blank pixels corresponding to the new "edge points" have been filled, they will become the new "filled pixels" in the next round of checks (i.e., returning to step S301). If there are still blank pixels in the neighborhood of the new "filled pixels", they will continue to serve as new starting points to trigger subsequent diffusion. This cycle repeats, forming an automatic iterative diffusion mechanism that starts from the initial set of edge points and progresses layer by layer from the outside in, until the completion condition of step S302 is met, outputting the final, complete texture map.

[0045] Please see Figure 4 , Figure 4 This is a schematic diagram comparing the filling results provided in the embodiments of this application.

[0046] Figure 4 In the image, (a) is the original texture map, (b) is the reparameterized texture map with holes, (c) is the nearest neighbor filling result, and (d) is the filling result of this application.

[0047] Specifically, this application was tested on the AVS 3D mesh dataset and comprehensively compared with the nearest neighbor filling algorithm (Anchor) used in the original MCEMv0.2. Subjectively, visually, as... Figure 4 The comparative results show that the hole-filling method of this application makes the texture transition of the filled region natural and completely eliminates the blocky artifacts produced by the nearest neighbor algorithm. In terms of objective indicators, the peak signal-to-noise ratio (PSNR) of the filled texture map remains stable, with fluctuations within 0.1 dB. At the same time, due to the smoother filled texture, the bitrate allocation in the encoding process is optimized. Specifically, the data shows that compared with the Anchor algorithm, the reduction in texture information is optimized by approximately 5.591%, indicating that this application significantly improves the visual quality of the reconstructed texture while also improving compression performance.

[0048] In summary, the hole-filling method proposed in this application effectively solves the problems of visual quality and execution efficiency in the existing technology, and provides a key optimization technology for AVS 3D mesh encoding.

[0049] This application has the following advantages by limiting the seed point to the "edge point" and adopting a "local region averaging" filling strategy: First, visual quality and encoding adaptability are significantly improved. The local region averaging strategy makes the fill color more closely match the surrounding texture features, effectively avoiding the abrupt boundaries and color abrupt changes caused by the nearest neighbor algorithm. This achieves a natural transition between the filled area and the original texture, greatly improving texture coherence—creating a superior prerequisite for subsequent texture encoding compression and helping to achieve the core requirement of smaller file size. Test data shows that the reduction in the amount of filled texture image information after encoding is optimized by approximately 5.591%, while the peak signal-to-noise ratio (PSNR) fluctuation is less than 0.1, fully demonstrating excellent stability and encoding adaptability value.

[0050] Secondly, the filling efficiency is significantly improved. By precisely defining and selecting only "edge points" as initial seed points, the initial scale of breadth-first search (BFS) diffusion is greatly reduced, avoiding redundant calculations caused by globally projected pixels, making the diffusion process more directional and efficient.

[0051] Furthermore, it boasts strong compatibility and scalability. This application relies solely on standard occupancy map information, requiring no additional parameters or modifications to existing encoding / decoding processes, and can be seamlessly integrated into mainstream mesh coding standards such as AVS. Key parameters in the algorithm (such as local region kernel size) support adaptive adjustment, laying the foundation for future dynamic optimization combined with intelligent decision-makers.

[0052] Finally, its effectiveness has been verified through practical application. This application has been integrated into an optimized version of the AVS mesh encoding platform MCEM. Tests on the AVS 3D mesh dataset show that the algorithm significantly improves the subjective quality of the reconstructed texture while maintaining compression performance, thus verifying its effectiveness and practicality.

[0053] Based on the same inventive concept, this application also provides a cavity filling device corresponding to the cavity filling method. Since the principle of the device in this application is similar to the cavity filling method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0054] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of the cavity filling device provided in the embodiments of this application, as shown below. Figure 5 As shown, the cavity filling device 400 includes: Hole detection module 401 is used to determine the set of edge points of the image to be filled, the set of edge points including at least one edge point, the edge point indicating a projected pixel point in which at least one blank pixel point exists in its four neighboring regions.

[0055] The filling execution module 402 is used to determine each blank pixel in the four-neighborhood of each edge point in the edge point set, and to determine the average color value in the preset area of ​​the blank pixel, so as to fill the blank pixel according to the average color value to obtain a filled pixel.

[0056] The output module 403 is used to determine that all blank pixels in the image to be filled are filled in order to obtain a complete image.

[0057] In a preferred embodiment of this application, the output module 403 is further configured to: For each filled pixel, determine whether there are any blank pixels in the four neighboring regions of that filled pixel; when there are no blank pixels in the four neighboring regions of each filled pixel, determine that all blank pixels in the image to be filled are filled.

[0058] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6As shown, the electronic device 500 includes a processor 510, a memory 520, and a bus 530.

[0059] The memory 520 stores machine-readable instructions that can be executed by the processor 510. When the electronic device 500 is running, the processor 510 and the memory 520 communicate via the bus 530. When the machine-readable instructions are executed by the processor 510, the steps of the method described above can be performed. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0060] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the method described above. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0061] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0062] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0063] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0065] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0066] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A hole filling method characterized by, The method comprises: determining a set of edge points of a to-be-filled image, the set of edge points comprising at least one edge point, the edge point indicating a projected pixel point with at least one blank pixel point in a four-neighbor domain; for each edge point in the set of edge points, determining each blank pixel point in the four-neighbor domain of the edge point, and determining an average color value in a preset region of the blank pixel point, so as to fill the blank pixel point according to the average color value, and obtain a filled pixel point; determining that all blank pixel points in the to-be-filled image are filled, to obtain a complete image.

2. The method of claim 1, wherein, The determination that all blank pixel points in the to-be-filled image are filled is made in the following manner: for each filled pixel point, determining whether there is a blank pixel point in the four-neighbor domain of the filled pixel point; when there is no blank pixel point in the four-neighbor domain of each filled pixel point, it is determined that all blank pixel points in the to-be-filled image are filled.

3. The method of claim 2, wherein, Further comprising: when there is a blank pixel point in the four-neighbor domain of a filled pixel point, for each filled pixel point with a blank pixel point in the four-neighbor domain, determining each blank pixel point corresponding to the filled pixel point, and filling the blank pixel point according to an average color value in a preset region of each blank pixel point.

4. The method of claim 1, wherein, The average color value in the preset region of each blank pixel point is determined in the following manner: for each blank pixel point, determining a preset region centered on the blank pixel point, counting color values of each projected pixel in the preset region, and calculating an arithmetic mean value of color values of all projected pixels in the preset region as the average color value, the average color value comprising component values of a corresponding color space.

5. The method of claim 1, wherein, The set of edge points is determined in the following manner: obtaining a binary occupancy map corresponding to the to-be-filled image, determining a projected pixel point as a pixel point with a value of 1 in the binary occupancy map, and determining a blank pixel point as a pixel point with a value of 0 in the binary occupancy map; all projected pixel points with at least one blank pixel point in the upper, lower, left, and right directions form the set of edge points.

6. The method of claim 1, wherein, Each blank pixel point in the four-neighbor domain of each edge point is determined in the following manner: all pixel points in the four-neighbor domain of each edge point are traversed using a breadth-first search framework to determine each blank pixel point in the four-neighbor domain of each edge point.

7. A hole filling apparatus characterized by comprising: The device comprises: a hole detection module configured to determine a set of edge points of a to-be-filled image, the set of edge points comprising at least one edge point, the edge point indicating a projected pixel point with at least one blank pixel point in a four-neighbor domain; a filling execution module configured to, for each edge point in the set of edge points, determine each blank pixel point in the four-neighbor domain of the edge point, and determine an average color value in a preset region of the blank pixel point, so as to fill the blank pixel point according to the average color value, and obtain a filled pixel point; an output module configured to determine that all blank pixel points in the to-be-filled image are filled, to obtain a complete image.

8. The apparatus of claim 7, wherein, The output module is further configured to: For each filled pixel point, it is determined whether there is a blank pixel point in the four-neighbor domain of the filled pixel point; When there is no blank pixel point in the four-neighbor domain of each filled pixel point, it is determined that all the blank pixel points in the image to be filled are filled.

9. An electronic device, comprising: It comprises: A processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, the processor executes the machine readable instructions to execute the steps of the method as claimed in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the steps of the method as claimed in any one of claims 1 to 6.

Images