CN111161136B - Image blurring method, image blurring device, equipment and storage device - Google Patents
Image blurring method, image blurring device, equipment and storage device Download PDFInfo
- Publication number
- CN111161136B CN111161136B CN201911398120.0A CN201911398120A CN111161136B CN 111161136 B CN111161136 B CN 111161136B CN 201911398120 A CN201911398120 A CN 201911398120A CN 111161136 B CN111161136 B CN 111161136B
- Authority
- CN
- China
- Prior art keywords
- image
- blurring
- value
- pixel
- invalid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 claims description 36
- 230000004927 fusion Effects 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 20
- 238000001914 filtration Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 14
- 230000007704 transition Effects 0.000 description 14
- 230000000694 effects Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G06T3/04—
Abstract
The application discloses an image blurring method, an image blurring device, equipment and a storage device. The image blurring method comprises the following steps: acquiring an original background image of an image to be virtualized, wherein the original background image comprises an invalid region corresponding to a foreground part of the image to be virtualized; filling the pixel value of the invalid region by using the effective pixel value of the original background map, which is positioned outside the invalid region, so as to obtain a filled background map; blurring the filled background image to obtain a blurring background image; and fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image. By the scheme, image blurring can be achieved, and the halation problem is eliminated.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an image blurring method, an image blurring apparatus, a device, and a storage apparatus.
Background
With the development of technology, people have higher and higher requirements on images. For example, for some images such as a person photograph or a feature photograph, it is desirable for the image to be capable of achieving a blurring effect. However, the image photographed by a common camera, such as a mobile phone camera, cannot obtain the blurring effect, and often the image blurring process is completed by a post-processing technology.
However, the effect of the image blurring process is not ideal at present, and the halation problem exists generally. The halation problem, which may also be referred to as "color leakage", specifically, the leakage of foreground color into the background at the image boundary, results in a blurred transition effect at the boundary. Therefore, the halation problem caused by image blurring extremely affects the blurring look and feel.
Disclosure of Invention
The application mainly provides an image blurring method, an image blurring device, equipment and a storage device.
The first aspect of the present application provides an image blurring method, comprising: acquiring an original background image of an image to be virtualized, wherein the original background image comprises an invalid region corresponding to a foreground part of the image to be virtualized; filling the pixel value of the invalid region by using the effective pixel value of the original background map, which is positioned outside the invalid region, so as to obtain a filled background map; blurring the filled background image to obtain a blurring background image; and fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
Therefore, an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred is obtained, the effective pixel value of the original background image outside the invalid area is utilized to fill the pixel value of the invalid area to obtain a filled background image, so that the pixel value of the invalid area of the filled background image is not related to the foreground any more and is closer to the background part, then the filled background image is subjected to blurring processing to obtain a blurring background image, the blurring background image corresponds to the foreground part and is obtained by blurring the filled pixel value, the color influence of the foreground part on the background part is reduced, and further, the blurring of the image can be realized by utilizing the fusion of the blurring background image and the foreground part of the image to be blurring, the halation problem is eliminated, and the quality of realizing the blurring processing of the image is greatly improved.
The method for filling the pixel value of the invalid region by using the valid pixel value of the original background map, which is positioned outside the invalid region, comprises the following steps: for each invalid pixel point in the invalid region, the value of the invalid pixel point is utilized to be the value of the valid pixel point nearest to the invalid pixel point.
Therefore, the value of the effective pixel point closest to the ineffective pixel point is utilized to obtain the value of the ineffective pixel point, so that the value of the pixel point corresponding to the foreground part in the filled background image is ensured to be closer to the value of the pixel point adjacent to the background part, and the color influence of the foreground part on the background part is further reduced.
Wherein for each invalid pixel point in the invalid region, using a value of the valid pixel point nearest to the invalid pixel point, the value of the invalid pixel point includes: selecting an invalid pixel point from the invalid region, utilizing the value of the invalid pixel point closest to the valid pixel point, and updating the invalid pixel point into a new valid pixel point; and re-executing the steps until all the invalid pixel points are updated to be new valid pixel points.
Therefore, in the filling process, more and more effective pixels are in the original background image, so that the rest ineffective pixels can find the nearest effective pixels faster, and the filling efficiency of the ineffective pixels is improved.
Wherein using the value of the invalid pixel point that is closest to the valid pixel point includes: and determining an adjacent area taking the invalid pixel point as a center and the radius as a preset radius, searching an effective pixel point closest to the invalid pixel point from the adjacent area, and obtaining the value of the invalid pixel point based on the value of the searched effective pixel point.
Therefore, the search of the nearest effective pixel point of the ineffective pixel point is realized in the adjacent area taking the ineffective pixel point as the center, and the search is performed by taking the adjacent area as the range, so that the search efficiency of the effective pixel point without any search can be improved.
Wherein using the value of the invalid pixel point that is closest to the valid pixel point includes: if the effective pixel points are not found in the adjacent area, increasing the radius of the adjacent area, searching the effective pixel point closest to the ineffective pixel point in the adjacent area with the increased radius, and based on the value of the searched effective pixel point, obtaining the value of the ineffective pixel point.
Therefore, when no effective pixel points exist in the adjacent area, the area range is continuously expanded to search, namely the area range is gradually expanded to search, and the reliability of searching the effective pixel points is ensured on the premise of ensuring certain searching efficiency of the effective pixel points.
Wherein the value of the invalid pixel point based on the value of the searched valid pixel point comprises: and taking the value of the searched effective pixel point as the value of the ineffective pixel point.
Therefore, the value of the searched effective pixel point is directly used as the value of the ineffective pixel point, no additional operation is needed to be carried out on the effective pixel point, the determination process of the value of the ineffective pixel point is simplified, and the determination efficiency of the value of the ineffective pixel point is improved.
The method for obtaining the original background image of the image to be blurred comprises the following steps: acquiring a first mask image of an image to be virtualized, wherein each pixel value of the first mask image represents that a pixel point corresponding to the image to be virtualized belongs to a foreground or a background; and processing the image to be subjected to blurring based on the first mask map to obtain an original background map.
Therefore, the acquisition of the background image of the image to be virtualized is realized, the background image is obtained by directly utilizing the first mask image, and the acquisition flow of the background image is simplified.
The method for obtaining the first mask image of the image to be blurred comprises the following steps: determining a first mask map of the image to be virtualized by utilizing depth information in the image to be virtualized; or determining a first mask image of the image to be virtualized by using the image segmentation result of the image to be virtualized.
Thus, acquisition of a mask map of an image to be blurred is achieved.
The method for processing the image to be virtualized based on the first mask map to obtain an original background map comprises the following steps: converting the first mask map into a second mask map with pixel values ranging from 0 to 1, wherein the pixel value of the pixel point corresponding to the image to be virtualized, which belongs to the foreground, in the second mask map is 1, and the pixel value of the pixel point corresponding to the image to be virtualized, which belongs to the background, is 0; multiplying the image to be subjected to blurring by the second mask image to obtain an original foreground image, and performing difference between the image to be subjected to blurring and the original foreground image to obtain an original background image.
Therefore, the first mask map is converted into the range of 0 to 1, and then the converted second mask map and the image to be virtualized are used for operation to finally obtain the original background map, namely the acquisition of the background map is realized, and the acquisition flow of the background map is simplified.
Wherein, before filling the invalid region with the valid pixel values of the original background image outside the invalid region to obtain the filled background image, the method further comprises: and taking an area formed by the pixel points corresponding to the pixel value of 1 of the second mask image in the original background image as an invalid area.
Therefore, the invalid region of the original background image is determined directly through the mask image in the range from 0 to 1, the determination of the invalid region can be realized without additional operation, and the determination efficiency of the invalid region is improved.
The second aspect of the application provides an image blurring device, which comprises an acquisition module, a filling module, a blurring module and a fusion module. The acquisition module is used for acquiring an original background image of the image to be virtualized, wherein the original background image comprises an invalid area corresponding to a foreground part of the image to be virtualized; the filling module is used for filling the pixel values of the invalid region by utilizing the effective pixel values of the original background map, which are positioned outside the invalid region, so as to obtain a filled background map; the blurring module is used for blurring the filled background image to obtain a blurring background image; and the fusion module is used for fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
Therefore, an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred is obtained, the effective pixel value of the original background image outside the invalid area is utilized to fill the pixel value of the invalid area to obtain a filled background image, so that the pixel value of the invalid area of the filled background image is not related to the foreground any more and is closer to the background part, then the filled background image is subjected to blurring processing to obtain a blurring background image, the blurring background image corresponds to the foreground part and is obtained by blurring the filled pixel value, the color influence of the foreground part on the background part is reduced, and further, the blurring of the image can be realized by utilizing the fusion of the blurring background image and the foreground part of the image to be blurring, the halation problem is eliminated, and the quality of realizing the blurring processing of the image is greatly improved.
A third aspect of the present application provides an image blurring apparatus comprising a processor and a memory coupled to each other, wherein the processor is adapted to execute a computer program stored by the memory to perform the image blurring method of the first aspect described above.
Therefore, an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred is obtained, the effective pixel value of the original background image outside the invalid area is utilized to fill the pixel value of the invalid area to obtain a filled background image, so that the pixel value of the invalid area of the filled background image is not related to the foreground any more and is closer to the background part, then the filled background image is subjected to blurring processing to obtain a blurring background image, the blurring background image corresponds to the foreground part and is obtained by blurring the filled pixel value, the color influence of the foreground part on the background part is reduced, and further, the blurring of the image can be realized by utilizing the fusion of the blurring background image and the foreground part of the image to be blurring, the halation problem is eliminated, and the quality of realizing the blurring processing of the image is greatly improved.
A fourth aspect of the present application provides a storage device storing a computer program capable of implementing the image blurring method of the first aspect.
Therefore, an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred is obtained, the effective pixel value of the original background image outside the invalid area is utilized to fill the pixel value of the invalid area to obtain a filled background image, so that the pixel value of the invalid area of the filled background image is not related to the foreground any more and is closer to the background part, then the filled background image is subjected to blurring processing to obtain a blurring background image, the blurring background image corresponds to the foreground part and is obtained by blurring the filled pixel value, the color influence of the foreground part on the background part is reduced, and further, the blurring of the image can be realized by utilizing the fusion of the blurring background image and the foreground part of the image to be blurring, the halation problem is eliminated, and the quality of realizing the blurring processing of the image is greatly improved.
Drawings
FIG. 1 is a flow chart of an embodiment of an image blurring method according to the present application;
FIG. 2 is a flow chart of another embodiment of the image blurring method according to the present application;
FIG. 3 is a schematic diagram of a frame of an embodiment of an image blurring apparatus according to the present application;
FIG. 4 is a schematic diagram of an embodiment of an image blurring apparatus according to the present application;
FIG. 5 is a schematic diagram of a frame of an embodiment of a storage device of the present application.
Detailed Description
The following describes embodiments of the present application in detail with reference to the drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating an embodiment of an image blurring method according to the present application.
Specifically, the method of the embodiment comprises the following steps:
step S101: and acquiring an original background image of the image to be blurred.
The image to be subjected to blurring is called an image to be subjected to blurring, and the image to be subjected to blurring can be obtained by shooting a target object by any shooting device with a shooting function, wherein the shooting device can be any equipment such as a camera, a mobile phone and the like connected with a main execution body of the method of the embodiment, or a device for executing self setting of the main execution body of the method of the embodiment. Wherein the target object is an object that any photographer such as a person, animal, building, etc. wants to focus on. After the image to be virtualized is obtained, preprocessing (such as noise reduction processing) is performed on the image to be virtualized, and then the processing of the step and the subsequent steps is performed, for example, before the step, the noise reduction processing can be performed on the image to be virtualized, and then the processing of the step and the subsequent steps is performed on the image to be virtualized after the noise reduction processing, wherein, in order to improve the noise reduction effect, the noise reduction can be realized by using a neural network model.
The image to be blurred comprises a foreground portion and a background portion. In a specific application, an area where the target object is located in the image to be virtualized is taken as a foreground part, and an area outside the target object in the image to be virtualized is taken as a background part, so that an image in which the area where the target object is located is clear and the area outside the target object is virtualized is obtained through the method of the embodiment.
In this step S101, pixel points of a background portion in the image to be blurred may be extracted to obtain an original background image of the image to be blurred. Specifically, an original background image of an image to be virtualized can be obtained by adopting a mask image mode; or a neural network model is adopted to identify a foreground part (the target object) in the image to be virtualized, and then the foreground part obtained by identification is segmented to obtain an original background image of the image to be virtualized; the manner of obtaining the original background image is not particularly limited herein.
The application is specifically illustrated by acquiring an original background image in a mask image mode. For example, the present step S101 includes: and acquiring a first mask image of the image to be virtualized, and processing the image to be virtualized based on the first mask image to obtain an original background image. Each pixel value of the first mask map indicates that a corresponding pixel point of the image to be blurred belongs to the foreground or the background, i.e. the first mask map can distinguish the foreground and the background of the image to be blurred. The pixel values of the first mask image are in one-to-one correspondence with the pixel points of the image to be virtualized, and the pixel values of the first mask image are corresponding to the possibility that the pixel points of the image to be virtualized are foreground or background.
The pixel values in the first mask map are values in a preset range, and different values in the preset range represent the possibility that the pixel points of the image to be blurred are foreground or background. Specifically, the preset range may be any range of 0 to 1, 0 to 100, 0 to 255, 100 to 200, etc., which is not particularly limited herein. The following specific examples are given with the pixel values of the first mask pattern being 0 to 1 and 0 to 255, and it should be understood that the following examples do not limit the pixel value range of the mask pattern of the present application.
For example, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the foreground is 1, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the background is 0, and the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the transition between the foreground and the background is a value greater than 0 and less than 1, such as 0.1, 0.5, 0.8, etc. In the first mask diagram, the closer the corresponding pixel point of the image to be blurred is to the pixel value belonging to the foreground, the closer 1 is to the pixel value. Therefore, the pixel points in the image to be virtualized can be determined to belong to the foreground or the background by utilizing the first mask map. If the pixel value of the first mask image is 1, the pixel point corresponding to the image to be virtualized belongs to the foreground; if the pixel value of the first mask image is 0, the pixel point corresponding to the image to be virtualized belongs to the background; if the pixel value of the first mask pattern is greater than 0 and less than 1, the pixel value indicates that the pixel point corresponding to the image to be blurred belongs to the transition portion where the foreground and the background meet.
For another example, the pixel value of the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the foreground is 0, the pixel value of the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the background is 1, and the pixel value of the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the transition between the foreground and the background is a value greater than 0 and less than 1, wherein the pixel value of the first mask map indicating that the pixel corresponding to the image to be blurred is closer to 0 as the pixel corresponding to the image to be blurred is closer to the pixel value belonging to the foreground. At this time, if the pixel value of the first mask image is 0, it indicates that the pixel point corresponding to the image to be blurred belongs to the foreground; if the pixel value of the first mask image is 1, the pixel point corresponding to the image to be virtualized belongs to the background; if the pixel value of the first mask pattern is greater than 0 and less than 1, the pixel value indicates that the pixel point corresponding to the image to be blurred belongs to the transition portion where the foreground and the background meet.
For another example, the pixel values in the first mask map are values between 0 and 255. For example, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the foreground is 0, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the background is 255, and the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the transition between the foreground and the background is a value greater than 0 and less than 255, wherein the closer the pixel corresponding to the image to be blurred is to the pixel value belonging to the foreground is to 0. Of course, in other embodiments, the pixel values in the first mask map representing the foreground and the pixel values in the first mask map representing the background may be swapped, for example, the pixel value in the first mask map representing the pixel point corresponding to the image to be blurred as the foreground is 255, the pixel value in the first mask map representing the pixel point corresponding to the image to be blurred as the background is 0, and the pixel value in the first mask map representing the transition between the foreground and the background is greater than 0 and less than 255, where the pixel value representing the pixel point corresponding to the image to be blurred is closer to 255 as the pixel point corresponding to the image to be blurred is closer to the pixel value belonging to the foreground.
The first mask map of the image to be virtualized can be obtained in various modes, and the first mask map of the image to be virtualized can be determined by utilizing depth information in the image to be virtualized; the first mask map of the image to be blurred may also be determined using the image segmentation result of the image to be blurred. The depth information of the image to be blurred indicates the color resolution of the image, and the first mask image of the image to be blurred is obtained by using the depth information, for example, the depth image information obtained by calculating the binocular camera image, so as to highlight the hierarchy effect generated by the depth of field. The image to be blurred may have organisms such as, but not limited to, a person, for example, a person image may be detected by using an algorithm, the person image and the background may be segmented to obtain a person image segmentation result of the image to be blurred, and based on the person image segmentation result, a pixel value of the first mask image of the area where the person image is located corresponds to a pixel point of the image to be blurred to belong to the foreground.
After the first mask map of the image to be virtualized is obtained, the image to be virtualized can be processed based on the first mask map to obtain an original background map. Specifically, the first mask map is converted into a second mask map having pixel values ranging from 0 to 1. The pixel value of the second mask diagram, which indicates that the pixel point corresponding to the image to be virtualized belongs to the foreground, is 1, the pixel value of the second mask diagram, which indicates that the pixel point corresponding to the image to be virtualized belongs to the background, is 0, and the pixel value of the second mask diagram, which indicates that the pixel point corresponding to the image to be virtualized belongs to the transition between the foreground and the background, is a value which is larger than 0 and smaller than 1, wherein the closer the pixel point corresponding to the image to be virtualized is to the pixel value which belongs to the foreground, the closer the pixel point corresponding to the image to be virtualized is to the 1. In one specific application, the second mask map may also be referred to as an alpha map.
For example, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the foreground is 255, the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the background is 0, and the pixel value in the first mask map indicating that the pixel corresponding to the image to be blurred belongs to the transition between the foreground and the background is a value greater than 0 and less than 255. Based on the above, the pixel values in the first mask image are divided by 255 to normalize the pixel values, a pixel value of 1 in the second mask image indicates that the pixel point corresponding to the image to be blurred belongs to the foreground, and a pixel value of 0 in the second mask image indicates that the pixel point corresponding to the image to be blurred belongs to the background. For another example, the pixel value of the first mask map, which indicates that the pixel point corresponding to the image to be blurred belongs to the foreground, is 0, the pixel value of the first mask map, which indicates that the pixel point corresponding to the image to be blurred belongs to the background, is 255, the pixel value of the first mask map, which indicates that the pixel point corresponding to the image to be blurred belongs to the transition between the foreground and the background, is a value greater than 0 and less than 255, based on which, each pixel value in the first mask map is subtracted by the maximum value 255 of the first mask map to obtain an anti-mask map, and the pixel values of the anti-mask map are divided by 255 to normalize the pixel values, the pixel value of the second mask map, which indicates that the pixel point corresponding to the image to be blurred belongs to the foreground, is 1, and the pixel value of the second mask map, which indicates that the pixel point corresponding to the image to be blurred belongs to the background, is 0.
After the first mask map is converted into a second mask map with the pixel value range of 0 to 1, multiplying the image to be virtualized with the second mask map to obtain an original foreground map, and differentiating the image to be virtualized with the original foreground map to obtain an original background map.
Step S102: and filling the pixel value of the invalid region by using the valid pixel value of the original background map, which is positioned outside the invalid region, so as to obtain a filled background map.
In the application, the region corresponding to the foreground part in the original background image is an invalid region, the pixel points in the invalid region in the original background image are invalid pixel points, and the corresponding value is an invalid pixel value; the pixels outside the invalid region in the original background image are valid pixels, and the corresponding values are valid pixel values.
In one embodiment, the inactive areas in the original background map may be determined first. For example, before the present step S102, further includes: specifically, for example, in the above example, since the pixel value of the second mask map indicating that the pixel corresponding to the image to be blurred belongs to the foreground is 1, the region formed by the pixel corresponding to the pixel value of the second mask map in the original background map may be used as the invalid region.
For each invalid pixel point in the invalid region, the value of the invalid pixel point is obtained by using the values of the adjacent valid pixel points. For example, the value of the invalid pixel point may be utilized as the value of the valid pixel point nearest to the invalid pixel point. Specifically, for each invalid pixel point in the invalid region, an adjacent region with the invalid pixel point as a center and a radius of a preset radius can be determined, an effective pixel point nearest to the invalid pixel point is found out from the adjacent region, and a value of the invalid pixel point is obtained based on the value of the found effective pixel point. In another embodiment, if the valid pixel value is not found in the neighboring area, the range of the neighboring area may be enlarged to further search, i.e. the radius of the neighboring area is increased, and the valid pixel nearest to the invalid pixel is found in the neighboring area after the radius is increased, if the nearest valid pixel is found, the value of the invalid pixel is obtained based on the value of the found valid pixel, and if the valid pixel is not found yet, the above steps are continuously performed to continue enlarging the range of the neighboring area to further search. Wherein the adjacent area can be, but is not limited to, a circular shape. The value of the invalid pixel point based on the found value of the valid pixel point may specifically include: and directly taking the value of the searched effective pixel point as the value of the ineffective pixel point. Of course, if there are a plurality of valid pixels found, that is, there are a plurality of valid pixels closest to the invalid pixel, a value of one valid pixel may be selected as the value of the invalid pixel, or an average value of the plurality of valid pixels may be used as the value of the invalid pixel, which is not particularly limited herein.
In yet another embodiment, invalid pixel points in the invalid region may be filled one by one, and the filled invalid pixel points are updated to new valid pixel values, and then the remaining invalid pixel points are filled for the updated valid pixel points in the original background map. For example, the step of using the value of the valid pixel nearest to the invalid pixel for each invalid pixel in the invalid region may specifically include: selecting an invalid pixel point from the invalid region, utilizing the value of the invalid pixel point which is closest to the valid pixel point, and updating the value of the invalid pixel point into a new valid pixel value; and repeatedly executing the step until all the invalid pixel points are updated to be new valid pixel values. Therefore, the effective pixel values in the original background image are more and more, so that the invalid pixel points can find the nearest effective pixel points faster and faster, and the filling efficiency of the invalid pixel points is improved.
Of course, in other embodiments, the value of the invalid pixel point may be obtained by using a value of an valid pixel point that is not closest to the invalid pixel point, for example, a value of an invalid pixel point that occurs most frequently in a certain neighborhood range of the invalid pixel point is selected as the value of the invalid pixel point, so there is no limitation on how to implement the filling of the value of the invalid pixel point by using the valid pixel value.
Step S103: and carrying out blurring treatment on the filling background image to obtain a blurring background image.
For example, filtering the filled background image by using a preset filtering function to obtain an imaginary background image. Specifically, each pixel point in the filling background image is subjected to filtering processing by using a preset filtering function, and linear smooth filtering can be completed by using the preset filtering function, so that noise reduction processing can be performed on the filling background image. The preset filter function may be a filter function in the prior art, such as a gaussian filter function, and is not limited in any way.
If the whole image to be blurred is directly filtered to obtain a blurred image, the foreground color of the blurred image leaks into the background in a transition part where the foreground and the background are intersected, so that the halation problem is serious.
Step S104: and fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
The image to be subjected to blurring provides clear foreground for the image subjected to blurring, the blurring background image provides blurring background for the image subjected to blurring, and the blurring background image and the image to be subjected to blurring are fused to obtain the image subjected to blurring.
For example, when the blurring background image and the image to be blurring are fused to obtain a blurring image, the formula is usedAnd processing the blurring background image and the image to be blurring to obtain a blurring image. Wherein y is i For the value of the ith pixel point in the blurred image, < >>For the value of the ith pixel point in the image to be blurred,/and (B)>Alpha is the value of the ith pixel point in the blurring background picture i Is the value of the ith pixel point in the second mask map. Multiplying the value of the ith pixel point in the image to be virtualized by the value of the ith pixel point in the second mask diagram to obtain the value of the pixel point of the image foreground after blurring; the difference value between 1 and the ith pixel point in the second mask diagram is multiplied by the value of the ith pixel point in the blurring background diagram to obtain the value of the pixel point of the blurring image background; and finally, adding the value of the pixel point of the image foreground after blurring with the value of the pixel point of the image background after blurring, and obtaining the whole image after blurring.
According to the method, an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred is obtained, the effective pixel value of the original background image, which is positioned outside the invalid area, is utilized to fill the pixel value of the invalid area, so that a filled background image is obtained, the pixel value of the invalid area of the filled background image is not related to the foreground any more and is closer to the background part, then the filled background image is subjected to blurring processing, so that a blurring background image is obtained, the blurring background image corresponds to the foreground part and is obtained by blurring the filled pixel value, the color influence of the foreground part on the background part is eliminated, finally, the image to be blurring provides the foreground of the image after blurring, the blurring background image provides the background of the image after blurring, and the blurring background image and the image to be blurring are fused, so that the image after blurring is obtained. The method comprises the steps of obtaining a filling background image from an original background image comprising an invalid area corresponding to a foreground part of an image to be blurred, obtaining a blurring background image from blurring processing of the filling background image, smoothing the formed background color, combining the blurring background image with a foreground of the image to be blurring, obtaining a blurring image with clear foreground and blurring background, and realizing high-quality image blurring processing without a halation problem at a transition part where the blurring foreground and the background of the image are intersected.
Referring to fig. 2, fig. 2 is a flowchart illustrating an image blurring method according to another embodiment of the present application.
Specifically, the method of the embodiment comprises the following steps:
step S201: a first mask map of an image to be blurred is obtained.
In this embodiment, a portrait is described as an example of a foreground portion. The image to be virtualized comprises a human image, the human image and the background can be detected by an algorithm, a human image segmentation result of the image to be virtualized is obtained, then, based on the human image segmentation result, it is determined that the pixel points of the first mask image, corresponding to the region where the human image is located in the image to be virtualized, belong to the foreground, and the pixel points of the first mask image, corresponding to the region outside the human image of the image to be virtualized, belong to the background. Taking a pixel value range of 0 to 255 in a first mask diagram as an example, the pixel value of the pixel point corresponding to the image to be blurred belonging to the foreground in the first mask diagram is 255, the pixel value of the pixel point corresponding to the image to be blurred belonging to the background in the first mask diagram is 0, and the pixel value of the pixel point corresponding to the image to be blurred belonging to the transition between the foreground and the background in the first mask diagram is a value larger than 0 and smaller than 255, wherein the closer the pixel point corresponding to the image to be blurred is to the pixel value belonging to the foreground, the closer 255 is to the pixel value.
Step S202: the first mask map is converted into a second mask map having pixel values ranging from 0 to 1.
For example, the pixel values in the first mask map are divided by 255, and the quotient obtained by dividing each pixel value in the first mask map is used as the corresponding pixel value of the second mask map, so that the normalization of the pixel values of the mask map is realized. The pixel value of the second mask map is 1, which indicates that the pixel corresponding to the image to be blurred belongs to the foreground, and the pixel value of the second mask map is 0, which indicates that the pixel corresponding to the image to be blurred belongs to the background.
Step S203: multiplying the image to be subjected to blurring by the second mask image to obtain an original foreground image, and performing difference between the image to be subjected to blurring and the original foreground image to obtain an original background image.
For example, the value of each pixel in the image to be blurred is multiplied by the corresponding pixel value in the second mask map to obtain the value of each pixel in the original foreground map. And subtracting the value of each pixel point in the image to be virtualized from the value of the corresponding pixel point of the original foreground image to obtain the value of each pixel point in the original background image. The original background image comprises an invalid area corresponding to a foreground part of the image to be virtual, namely an area where the portrait is located.
Step S204: and filling the pixel value of the invalid region by using the valid pixel value of the original background map, which is positioned outside the invalid region, so as to obtain a filled background map.
For each invalid pixel point in the invalid region, the value of the invalid pixel point is utilized to be the value of the valid pixel point nearest to the invalid pixel point. Specifically, for each invalid pixel point in the invalid region, a circular adjacent region with the invalid pixel point as a center and a radius of a preset radius is determined, an effective pixel point closest to the invalid pixel point is found out from the circular adjacent region, and a value of the invalid pixel point is obtained based on the value of the found effective pixel point.
Step S205: and filtering the filled background image by using a preset filtering function to obtain an blurring background image.
And filtering each pixel point in the filling background image by using a preset filtering function, and completing linear smooth filtering by using the preset filtering function so as to further reduce noise of the filling background image. The preset filter function may be a filter function in the prior art, such as a gaussian filter function, and is not limited in any way.
Step S206: and processing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
For example, the blurring background image and the image to be blurring are processed by using the following formula, so as to obtain a blurring image. Wherein the formula is Wherein y is i For the value of the ith pixel point in the blurred image, < >>For the value of the ith pixel point in the image to be blurred,/and (B)>Alpha is the value of the ith pixel point in the blurring background picture i Is the value of the ith pixel point in the second mask map. Multiplying the value of the ith pixel point in the image to be virtualized by the value of the ith pixel point in the second mask diagram to obtain the value of the pixel point of the image foreground after blurring; the difference value between 1 and the ith pixel point in the second mask diagram is multiplied by the value of the ith pixel point in the blurring background diagram to obtain the value of the pixel point of the blurring image background; and finally, adding the value of the pixel point of the image foreground after blurring with the value of the pixel point of the image background after blurring, and obtaining the whole image after blurring.
The image to be subjected to blurring provides clear foreground for the image subjected to blurring, the blurring background image provides blurring background for the image subjected to blurring, and the blurring background image and the image to be subjected to blurring are fused to obtain the image subjected to blurring. The blurring image has clear foreground and blurring background, and the transition part between the foreground and the background has no halation problem, so that high-quality image blurring processing is realized.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an image blurring apparatus according to an embodiment of the present application. As shown in fig. 3, the image blurring apparatus 30 includes an acquisition module 31, a padding module 32, a blurring module 33, and a fusion module 34. The obtaining module 31 is configured to obtain an original background image of the image to be blurred, where the original background image includes an invalid region corresponding to a foreground portion of the image to be blurred; a filling module 32, configured to fill the invalid region with the pixel values by using the valid pixel values of the original background map that are located outside the invalid region, so as to obtain a filled background map; the blurring module 33 is configured to perform blurring processing on the filled background image to obtain a blurring background image; and the fusion module 34 is configured to fuse the blurring background image with the foreground portion of the image to be blurring to obtain a blurring image.
In one embodiment, the filling module 32 is specifically configured to obtain, for each invalid pixel point in the invalid region, a value of the invalid pixel point using a value of the valid pixel point closest to the invalid pixel point.
The filling module 32 may be further specifically configured to select an invalid pixel point from the invalid region, use a value of the valid pixel point closest to the invalid pixel point to update the invalid pixel point to a new valid pixel value; and re-executing the steps until all the invalid pixel points are updated to be new valid pixel values.
Further, the filling module 32 performing the use of the value of the valid pixel nearest to the invalid pixel may include: and determining an adjacent area taking the invalid pixel point as a center and the radius as a preset radius, searching an effective pixel point closest to the invalid pixel point from the adjacent area, and obtaining the value of the invalid pixel point based on the value of the searched effective pixel point.
Further, the performing of the filling module 32 to utilize the value of the valid pixel nearest to the invalid pixel may further include: if the effective pixel points are not found in the adjacent area, increasing the radius of the adjacent area, searching the effective pixel point closest to the ineffective pixel point in the adjacent area with the increased radius, and based on the value of the searched effective pixel point, obtaining the value of the ineffective pixel point.
Further, the performing of the value of the invalid pixel point by the filling module 32 based on the value of the valid pixel point of the search may include: and taking the value of the searched effective pixel point as the value of the ineffective pixel point.
In an embodiment, the acquisition module 31 includes an acquisition unit and a processing unit. The acquisition unit is used for acquiring a first mask image of the image to be virtualized, wherein each pixel value of the first mask image indicates that a corresponding pixel point of the image to be virtualized belongs to the foreground or the background. The processing unit is used for processing the image to be subjected to blurring based on the first mask map to obtain an original background map.
Further, the obtaining unit is further configured to determine a first mask map of the image to be blurred by using depth information in the image to be blurred; or determining a first mask image of the image to be virtualized by using the image segmentation result of the image to be virtualized. The processing unit is further configured to convert the first mask map into a second mask map with pixel values ranging from 0 to 1, where a pixel value in the second mask map, where the pixel value is 1, where the pixel value is corresponding to a pixel point belonging to a foreground, and the pixel value is 0; multiplying the image to be subjected to blurring by the second mask image to obtain an original foreground image, and performing difference between the image to be subjected to blurring and the original foreground image to obtain an original background image.
In an embodiment, the filling module 32 is further configured to fill the invalid region with the pixel values of the valid pixel values of the original background map, which are located outside the invalid region, and take the region formed by the pixel points of the original background map corresponding to the pixel value 1 of the second mask map as the invalid region before the filled background map is obtained.
In an embodiment, the blurring module 33 is further configured to perform a filtering process on the filled background map by using a preset filtering function, so as to obtain a blurring background map.
In one embodiment, the fusion module 34 is further configured to utilize a formula Processing the blurring background image and the image to be blurring to obtain a blurring image, wherein y is as follows i For the value of the ith pixel point in the blurred image, < >>For the value of the i-th pixel point in the image to be blurred,/>alpha is the value of the ith pixel point in the blurring background picture i Is the value of the ith pixel point in the second mask map.
Referring to fig. 4, fig. 4 is a schematic frame diagram of an image blurring apparatus according to an embodiment of the present application. Specifically, the image blurring apparatus 40 in this embodiment includes a processor 41 and a memory 42 coupled to each other, wherein the processor 41 is configured to execute a computer program stored in the memory 42 to perform the image blurring method described above.
The processor 41 controls the memory 42 and itself to implement the steps of any of the embodiments of the image blurring method described above. The processor 41 may also be referred to as a CPU (Central Processing Unit ). The processor 41 may be an integrated circuit chip with signal processing capabilities. The processor 41 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 41 may be commonly implemented by a plurality of circuit-forming chips.
In an embodiment, the image blurring apparatus 40 may further include an image capturing device 43, and the processor 41 is further configured to control the image capturing device 43 so that the image capturing device 43 captures an image to obtain an image to be blurring. In another embodiment, the image blurring apparatus 40 may not include the image capturing device 43, and the image blurring apparatus 40 includes a communication circuit, and the processor 41 is connected to the external image capturing device through the communication circuit to obtain the image to be blurring captured by the external image capturing device.
Referring to fig. 5, fig. 5 is a schematic diagram illustrating a frame of a storage device 50 according to an embodiment of the application. The storage device 50 of the present application stores program instructions 501 executable by the processor, the program instructions 501 being adapted to implement steps of any of the embodiments of the image blurring method described above.
The storage device 50 may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or the like, which may store the program instructions 501, or may be a server storing the program instructions 501, and the server may send the stored program instructions 501 to another device for execution, or may also self-execute the stored program instructions 501.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (11)
1. A method of image blurring, comprising:
acquiring an original background image of an image to be virtualized, wherein the image to be virtualized comprises a foreground part and a background part, the background part is the part to be virtualized, and the original background image comprises an invalid region corresponding to the foreground part of the image to be virtualized;
filling the invalid region with the pixel values by using the valid pixel values of the original background map, which are positioned outside the invalid region, to obtain a filled background map;
blurring the filled background image to obtain a blurring background image;
and fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
2. The method according to claim 1, wherein the filling the invalid region with the valid pixel values of the original background map outside the invalid region to obtain a filled background map includes:
and for each invalid pixel point in the invalid region, obtaining the value of the invalid pixel point by using the value of the valid pixel point nearest to the invalid pixel point.
3. The method of claim 2, wherein for each invalid pixel in the invalid region, deriving the value of the invalid pixel using the value of the valid pixel nearest to the invalid pixel, comprises:
Selecting an invalid pixel point from the invalid region, obtaining the value of the invalid pixel point by using the value of the valid pixel point nearest to the invalid pixel point, and updating the invalid pixel point into a new valid pixel point;
and re-executing the steps until all the invalid pixel points are updated to be new valid pixel points.
4. A method according to claim 2 or 3, wherein said deriving the value of the invalid pixel using the value of the valid pixel nearest to the invalid pixel comprises:
and determining an adjacent area taking the invalid pixel point as a center and the radius as a preset radius, searching an effective pixel point closest to the invalid pixel point from the adjacent area, and obtaining the value of the invalid pixel point based on the value of the searched effective pixel point.
5. The method of claim 4, wherein the deriving the value of the invalid pixel using the value of the valid pixel nearest to the invalid pixel comprises:
if the effective pixel point is not found in the adjacent area, increasing the radius of the adjacent area, searching an effective pixel point nearest to the ineffective pixel point in the adjacent area after increasing the radius, and based on the value of the searched effective pixel point, obtaining a value of the ineffective pixel point;
The value of the invalid pixel point based on the value of the searched valid pixel point comprises the following steps:
and taking the value of the searched effective pixel point as the value of the ineffective pixel point.
6. The method according to claim 1, wherein the obtaining an original background image of the image to be blurred comprises:
acquiring a first mask image of the image to be virtualized, wherein each pixel value of the first mask image represents that a pixel point corresponding to the image to be virtualized belongs to a foreground or a background;
and processing the image to be subjected to blurring based on the first mask map to obtain an original background map.
7. The method of claim 6, wherein the acquiring the first mask map of the image to be blurred comprises:
determining a first mask map of the image to be virtualized by utilizing depth information in the image to be virtualized; or alternatively, the process may be performed,
determining a first mask image of the image to be virtualized by using a human image segmentation result of the image to be virtualized;
the processing the image to be virtualized based on the first mask map to obtain an original background map includes:
converting the first mask map into a second mask map with pixel values ranging from 0 to 1, wherein the pixel value of the pixel point corresponding to the image to be virtualized, which belongs to the foreground, in the second mask map is 1, and the pixel value of the pixel point corresponding to the image to be virtualized, which belongs to the background, is 0;
Multiplying the image to be subjected to blurring with the second mask image to obtain an original foreground image, and differencing the image to be subjected to blurring with the original foreground image to obtain the original background image.
8. The method of claim 7, wherein prior to said filling the invalid region with valid pixel values of the original background map that are outside the invalid region, the method further comprises:
and taking an area formed by the pixel points corresponding to the pixel value of the second mask image in the original background image as the invalid area.
9. An image blurring apparatus, comprising:
the image blurring module is used for obtaining an original background image of an image to be blurring, wherein the image to be blurring comprises a foreground part and a background part, the background part is the part to be blurring, and the original background image comprises an invalid area corresponding to the foreground part of the image to be blurring;
the filling module is used for filling the pixel value of the invalid region by utilizing the effective pixel value of the original background map, which is positioned outside the invalid region, so as to obtain a filled background map;
The blurring module is used for blurring the filling background image to obtain a blurring background image;
and the fusion module is used for fusing the blurring background image and the foreground part of the image to be blurring to obtain a blurring image.
10. An image blurring apparatus comprising a processor and a memory coupled to each other, wherein,
the processor is configured to execute the computer program stored by the memory to perform the method of any one of claims 1 to 8.
11. A storage device, characterized in that a computer program enabling the implementation of the method according to any of claims 1-8 is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911398120.0A CN111161136B (en) | 2019-12-30 | 2019-12-30 | Image blurring method, image blurring device, equipment and storage device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911398120.0A CN111161136B (en) | 2019-12-30 | 2019-12-30 | Image blurring method, image blurring device, equipment and storage device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111161136A CN111161136A (en) | 2020-05-15 |
| CN111161136B true CN111161136B (en) | 2023-11-03 |
Family
ID=70559245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911398120.0A Active CN111161136B (en) | 2019-12-30 | 2019-12-30 | Image blurring method, image blurring device, equipment and storage device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111161136B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113938578A (en) * | 2020-07-13 | 2022-01-14 | 武汉Tcl集团工业研究院有限公司 | Image blurring method, storage medium and terminal device |
| CN112862852A (en) * | 2021-02-24 | 2021-05-28 | 深圳市慧鲤科技有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
| CN113421211B (en) * | 2021-06-18 | 2024-03-12 | Oppo广东移动通信有限公司 | Method for blurring light spots, terminal equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107509031A (en) * | 2017-08-31 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
| CN109146767A (en) * | 2017-09-04 | 2019-01-04 | 成都通甲优博科技有限责任公司 | Image weakening method and device based on depth map |
| WO2019042216A1 (en) * | 2017-08-29 | 2019-03-07 | Oppo广东移动通信有限公司 | Image blurring processing method and device, and photographing terminal |
| CN109829850A (en) * | 2019-03-06 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | Image processing method, device, equipment and computer-readable medium |
| WO2019134504A1 (en) * | 2018-01-05 | 2019-07-11 | Oppo广东移动通信有限公司 | Method and device for blurring image background, storage medium, and electronic apparatus |
| CN110022430A (en) * | 2018-01-10 | 2019-07-16 | 中兴通讯股份有限公司 | Image weakening method, device, mobile terminal and computer readable storage medium |
-
2019
- 2019-12-30 CN CN201911398120.0A patent/CN111161136B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019042216A1 (en) * | 2017-08-29 | 2019-03-07 | Oppo广东移动通信有限公司 | Image blurring processing method and device, and photographing terminal |
| CN107509031A (en) * | 2017-08-31 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method, device, mobile terminal and computer-readable recording medium |
| CN109146767A (en) * | 2017-09-04 | 2019-01-04 | 成都通甲优博科技有限责任公司 | Image weakening method and device based on depth map |
| WO2019134504A1 (en) * | 2018-01-05 | 2019-07-11 | Oppo广东移动通信有限公司 | Method and device for blurring image background, storage medium, and electronic apparatus |
| CN110022430A (en) * | 2018-01-10 | 2019-07-16 | 中兴通讯股份有限公司 | Image weakening method, device, mobile terminal and computer readable storage medium |
| CN109829850A (en) * | 2019-03-06 | 2019-05-31 | 百度在线网络技术（北京）有限公司 | Image processing method, device, equipment and computer-readable medium |
Non-Patent Citations (1)
| Title |
|---|
| 利用Photoshop轻松实现朦胧背景;颜娣;孟庆娜;;照相机(11);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111161136A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898567B (en) | Image noise reduction method, device and system | |
| CN111028189B (en) | Image processing method, device, storage medium and electronic equipment | |
| CN111161136B (en) | Image blurring method, image blurring device, equipment and storage device | |
| CN111402170B (en) | Image enhancement method, device, terminal and computer readable storage medium | |
| CN109064504B (en) | Image processing method, apparatus and computer storage medium | |
| CN105243371A (en) | Human face beauty degree detection method and system and shooting terminal | |
| CN113888437A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN111242843B (en) | Image blurring method, image blurring device, equipment and storage device | |
| CN110942427A (en) | Image noise reduction method and device, equipment and storage medium | |
| WO2017173578A1 (en) | Image enhancement method and device | |
| Choi et al. | A method for fast multi-exposure image fusion | |
| CN113674303A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| WO2014014135A1 (en) | Method and apparatus for refocusing captured images, and computer-readable recording medium | |
| JP2017537396A (en) | Method and apparatus for estimating the depth of unfocused plenoptic data | |
| CN112184609A (en) | Image fusion method and device, storage medium and terminal | |
| CN111161299B (en) | Image segmentation method, storage medium and electronic device | |
| CN113658197B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| JP5509621B2 (en) | Image processing apparatus, camera, and program | |
| CN112634298B (en) | Image processing method and device, storage medium and terminal | |
| CN113129227A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| US10552970B2 (en) | Efficient guide filter for depth refinement | |
| CN111754417A (en) | Noise reduction method and device for video image, video matting method and device and electronic system | |
| CN112529773A (en) | QPD image post-processing method and QPD camera | |
| CN113709365B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN113256482B (en) | Photographing background blurring method, mobile terminal and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |