Video noise reduction method and device, equipment and storage medium

Abstract

The invention provides a video noise reduction method and device, equipment and a storage medium. The method comprises the steps that a first user interface is displayed, the first user interface at least comprises a first touch element, and the first touch element is used for providing an entrance for adjusting the noise reduction intensity; in response to a touch operation received by the first touch element, acquiring input user adjustment information; determining the target noise reduction intensity of the current video frame according to the user adjustment information; and performing noise reduction processing on the current video frame according to the target noise reduction intensity, and determining a target image of the current video frame.

Description

Technical Field

[0001] This application relates to image processing technology, including but not limited to video noise reduction methods, devices, equipment, and storage media. Background Art

[0002] Image noise refers to the interference information existing in image data, and its sources include the thermal noise and dark current noise of the image sensor during the image acquisition process, and the signal noise caused by external interference during the image transmission process, etc. Therefore, it is necessary to perform noise reduction on the image. During the image processing process, image noise reduction processing is a common method to improve image quality. Summary of the Invention

[0003] In a first aspect, an embodiment of this application provides a video noise reduction method, and the method includes: displaying a first user interface, where the first user interface at least includes a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity; in response to a touch operation received by the first touch element, obtaining input user adjustment information; determining a target noise reduction intensity of a current video frame according to the user adjustment information; performing noise reduction processing on the current video frame according to the target noise reduction intensity to determine a target image of the current video frame.

[0004] It can be understood that in the embodiment of this application, the first touch element is displayed on the first user interface, and by displaying the first touch element, an entry for adjusting the noise reduction intensity is provided for the user, so that the user can input user adjustment information that conforms to personal preferences by touching the first touch element, and based on this, a personalized video noise reduction function is realized, improving the user experience.

[0005] In a second aspect, an embodiment of this application provides a video noise reduction device, and the device includes: a display module configured to display a first user interface, where the first user interface at least includes a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity; an obtaining module configured to obtain input user adjustment information in response to a touch operation received by the first touch element; a first determination module configured to determine a target noise reduction intensity of a current video frame according to the user adjustment information; a second determination module configured to perform noise reduction processing on the current video frame according to the target noise reduction intensity to determine a target image of the current video frame.

[0006] In a third aspect, an embodiment of this application provides an electronic device, including a memory and a processor, where the memory stores a computer program that can run on the processor, and when the processor executes the program, the method described in the first aspect is implemented.

[0007] Fourthly, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor or an electronic device, the method described in the first aspect is implemented.

[0008] Fifthly, an embodiment of the present application provides a computer program product, including a computer program or instruction. When the computer program or instruction is executed by a processor or an electronic device, the method described in the first aspect of the present application is implemented.

[0009] Sixthly, an embodiment of the present application provides a computer program, which enables a processor or an electronic device to execute the method described in the first aspect.

[0010] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Description of the Drawings

[0011] The drawings herein are incorporated into the specification and constitute a part of this specification. These drawings show embodiments consistent with the present application and, together with the specification, are used to explain the technical solutions of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] The flowcharts shown in the drawings are only exemplary illustrations, not necessarily including all contents and operations / steps, nor necessarily executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined. Therefore, the actual execution order may change according to the actual situation.

[0013] Figure 1 Schematic diagram of the implementation process of the video noise reduction method provided by the embodiment of the present application Figure 1 ;

[0014] Figure 2 Example of the first touch element provided by the embodiment of the present application Figure 1 ;

[0015] Figure 3 Example of the first touch element provided by the embodiment of the present application Figure 2 ;

[0016] Figure 4 Schematic diagram of the further implementation process of step 103 provided by the embodiment of the present application;

[0017] Figure 5 Schematic diagram of the further implementation process of step 104 provided by the embodiment of the present application;

[0018] Figure 6 Schematic diagram of the further implementation process of step 502 provided by the embodiment of the present application;

[0019] Figure 7 Schematic diagram of the further implementation process of step 503 provided by the embodiment of the present application;

[0020] Figure 8 Schematic diagram of parameter update provided by the embodiment of the present application;

[0021] Figure 9 Schematic diagram of the implementation process of the video noise reduction method provided by the embodiment of the present application Figure 2 ;

[0022] Figure 10 Schematic diagram of the structure of the video noise reduction device provided by the embodiment of the present application;

[0023] Figure 11 Schematic diagram of the structure of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will further describe the specific technical solutions of the present application in detail with reference to the accompanying drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application but are not intended to limit the scope of the present application.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0026] In the following descriptions, references to "some embodiments", "this embodiment", "embodiments of the present application", and examples, etc., describe subsets of all possible embodiments. However, it can be understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict.

[0027] The descriptions such as "first", "second", and "third" that appear in the embodiments of the present application do not have specific meanings (such as no order, nor do they represent special limitations on the number of devices in the embodiments of the present application). They are only used to clearly describe the embodiments of the present application and cannot constitute any limitation to the embodiments of the present application.

[0028] Related video noise reduction methods mostly adopt the traditional spatial domain noise reduction + traditional time domain noise reduction scheme. The traditional spatial domain noise reduction scheme generally uses neighborhood filtering or non-local mean algorithm, and the traditional time domain noise reduction scheme generally adopts the method of finding similar blocks in adjacent frames based on motion vectors and then performing time domain superposition. Since the intensity of noise is different in different shooting scenes, for example, the noise reduction algorithm will set different noise reduction intensities based on different environments, and different noise reduction intensity parameters can be adaptively used based on environmental brightness, ISO information (sensitivity) of the camera, etc.

[0029] If the noise reduction intensity used by the spatial domain noise reduction algorithm is too weak, noise is likely to remain. If the noise reduction intensity used by the spatial domain noise reduction algorithm is too strong, details will be lost while removing the noise. Similarly, if the noise reduction intensity used by the time domain noise reduction algorithm is too weak, noise is likely to remain. If the noise reduction intensity used by the time domain noise reduction algorithm is too strong, ghosting will occur while removing the noise. Different users may have different noise reduction requirements. Some users hope to retain more details and tolerate the existence of some noise. Some users may be more concerned about the purity of the video and not care too much about the loss of details. Some users may even be intolerant of the existence of ghosting in the video. Therefore, it is necessary to open parameters for users to adjust the noise reduction intensity according to their preferences to further improve the user experience. However, there are many debugging parameters in related video noise reduction schemes, and it is difficult to open the debugging parameters to ordinary users.

[0030] Based on this, the embodiments of the present application provide the following video noise reduction methods, devices, equipment, etc.

[0031] Figure 1 Schematic diagram of the implementation process of the video noise reduction method provided by the embodiments of the present application Figure 1 ; As Figure 1 shown, the method includes the following steps 101 to 104:

[0032] Step 101, display a first user interface, where the first user interface at least includes a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity;

[0033] Step 102, in response to a touch operation received by the first touch element, obtain the input user adjustment information;

[0034] Step 103, determine the target noise reduction intensity of the current video frame according to the user adjustment information;

[0035] Step 104, perform noise reduction processing on the current video frame according to the target noise reduction intensity to determine the target image of the current video frame.

[0036] It can be understood that in the embodiments of the present application, a first touch element is displayed on the first user interface, and by displaying this first touch element, an entry for adjusting the noise reduction intensity is provided for the user, so that the user can input user adjustment information that conforms to personal preferences by touching the first touch element, and based on this, a personalized video noise reduction function is realized, improving the user experience.

[0037] The following will separately describe further optional implementation manners of the above steps, related terms, etc.

[0038] Step 101: Display a first user interface, where the first user interface at least includes a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity.

[0039] In the embodiments of the present application, the appearance shape of the first touch element is not limited. In short, the user can adjust the noise reduction intensity by touching the first touch element.

[0040] Exemplarily, Figure 2 is an example of the first touch element provided in the embodiments of the present application Figure 1 ; as Figure 2 shown, a first touch element 202 is displayed on the first user interface 201. The first touch element 202 is a progress bar. The user can input a sliding operation within the progress bar or the preset area where the progress bar is located to adjust the noise reduction intensity, or the user can also click any position on the progress bar to adjust the noise reduction intensity. In short, the user can input intensity parameters (i.e., an example of user adjustment information) by operating the progress bar. As Figure 2 shown, the value "0" on the left side of the progress bar represents the minimum value that can be adjusted through the progress bar, and the value "100" on the right side of the progress bar represents the maximum value that can be adjusted through the progress bar; among them, the length of the gray area of the progress bar 202 represents the progress of the progress bar, corresponding to the current intensity parameter value. For example, Figure 2 as shown in the progress bar 202, the current intensity parameter value corresponding to the progress is "50".

[0041] Exemplarily, Figure 3 is an example of the first touch element provided in the embodiments of the present application Figure 2 ; as Figure 3 shown, a first touch element 302 is displayed on the first user interface 301. The first touch element 302 is a voice input icon. The user can input voice information while long-pressing the icon, and the voice information contains user adjustment information.

[0042] In the embodiments of the present application, the information displayed on the first user interface is not limited. The first user interface at least displays a first touch element. In some embodiments, the method further includes: displaying the target image on the first user interface. That is, a target image determined by performing noise reduction processing on the current video frame based on the input user adjustment information is also displayed on the first user interface. Exemplarily, the first user interface is a video preview interface, and the video preview interface further includes a video preview window for displaying the target image or the video file to which the target image belongs.

[0043] Step 102, in response to a touch operation received by the first touch element, obtain the input user adjustment information.

[0044] In the embodiments of the present application, the input user adjustment information is not limited. In short, a corresponding target noise reduction intensity can be obtained according to the user adjustment information.

[0045] Exemplarily, in some embodiments, the user adjustment information may include user adjustment parameters, and / or the user adjustment information may also include information explicitly indicating to increase or decrease the noise reduction intensity.

[0046] In other embodiments, the user adjustment information may also include the desired temporal noise reduction intensity and / or spatial noise reduction intensity of the user.

[0047] In still other embodiments, the user adjustment information may further include the step size for increasing or decreasing the desired temporal noise reduction intensity of the user, and / or the step size for increasing or decreasing the desired spatial noise reduction intensity of the user.

[0048] Step 103, determine the target noise reduction intensity of the current video frame according to the user adjustment information.

[0049] In the embodiments of the present application, the user adjustment information may be effective for one or more frames of images in the current video, that is, the target noise reduction intensity is used to perform noise reduction processing on one or more frames of images in the current video frame. It should be understood that the current video frame can be understood as the image frame to be currently subjected to noise reduction processing, and this image frame is one of the one or more frames of images.

[0050] The further implementation manner of step 103 is not limited. Different information types included in the user adjustment information may result in different methods for determining the target noise reduction intensity based on the user adjustment information. Moreover, when determining the target noise reduction intensity of the current video frame, the size-related parameters of the moving region of the current video frame may or may not participate in the determination of the target noise reduction intensity.

[0051] In some embodiments, such as Figure 4As shown, step 103 may further include the following steps 401 and 403:

[0052] Step 401, determining the size-related parameters of the motion area of the current video frame;

[0053] Step 402, obtaining the default noise reduction intensity of the current shooting scene;

[0054] Step 403, adjusting the default noise reduction intensity according to the user adjustment information and the size-related parameters, and determining the target noise reduction intensity of the current video frame.

[0055] It can be understood that when performing spatial domain noise reduction, if the used noise reduction intensity is too weak / small, noise is likely to remain, while if the used noise reduction intensity is too strong, details will be lost while removing the noise. When performing temporal domain noise reduction, if the used noise reduction intensity is too weak, noise is also likely to remain, while if the used noise reduction intensity is too strong, ghosting will occur while removing the noise. It can be seen that if the size of the noise reduction intensity is not appropriate, the quality of the target image will be lost. For this consideration, in the embodiments of the present application, when determining the target noise reduction intensity of the current video frame according to the user adjustment information, the size-related parameters of the motion area of the current video frame are also considered. In this way, it is beneficial to determine a more appropriate target noise reduction intensity, thereby reducing the negative impact of the noise reduction process on the image quality.

[0056] Among them, for the above step 401, the size-related parameters of the motion area of the current video frame are determined.

[0057] In the embodiments of the present application, the size-related parameters of the motion area of the current video frame are not limited. The size-related parameters may be the size of the motion area, or the size ratio of the motion area in the current video frame, etc.

[0058] In the embodiments of the present application, the detection method of the motion area of the current video frame is not limited. The motion area of the current video frame can be detected by an optical flow method or a pre-trained motion detection network (i.e., an AI model for motion detection).

[0059] Among them, for the above step 402, the default noise reduction intensity of the current shooting scene is obtained.

[0060] In a possible implementation, scene parameters of one or more shooting scenes and their respective corresponding default noise reduction intensities are stored in a memory. In the embodiments of the present application, the scene parameters are not limited, and the scene parameters include one or more of the following parameters: light intensity, sensitivity (ISO), exposure time, and the proportion of the shadow area in the current video frame. Alternatively, in some other embodiments, the scene parameter may also be a comprehensive value determined based on one or more of the following parameters: light intensity, sensitivity (ISO), exposure time, and the proportion of the shadow area in the current video frame.

[0061] In the embodiments of the present application, the default noise reduction intensity of the current shooting scene may or may not be updated. For the solution of updating the default noise reduction intensity, in some embodiments, the method further includes: updating the default noise reduction intensity according to the target noise reduction intensity.

[0062] Further, in some embodiments, the default noise reduction intensity may be updated to the target noise reduction intensity. In some other embodiments, the updating the default noise reduction intensity according to the target noise reduction intensity includes: performing a fusion process (such as an average operation or a weighted average operation) on the target noise reduction intensity and the default noise reduction intensity to obtain a fusion result, and updating the default noise reduction intensity according to the fusion result. For example, the value of the default noise reduction intensity is updated to the fusion result. In this way, as the number of video shootings increases, the actual preferences of the user are gradually learned, so that the updated default noise reduction intensity gradually approaches the personal preferences of the user.

[0063] For the solution where the fusion result is the weighted average of the target noise reduction intensity and the default noise reduction intensity, in some embodiments, the fusion weight of the target noise reduction intensity is less than the fusion weight of the default noise reduction intensity. Of course, it can also be designed such that the fusion weight of the target noise reduction intensity is greater than the fusion weight of the default noise reduction intensity. However, compared with the latter, the main consideration in the foregoing embodiments where the fusion weight of the target noise reduction intensity is less than the fusion weight of the default noise reduction intensity is that the user adjustment information input by the user may be inaccurate, and the initial value of the default noise reduction intensity basically meets the noise reduction requirements of the corresponding shooting scene, and the target image determined based on the default noise reduction intensity meets the preferences of most users. Therefore, in order to avoid over-relying on the user adjustment information input by the user to perform noise reduction on the current video frame, the weight of the target noise reduction intensity is configured to be greater than the default noise reduction intensity, thereby avoiding the problem of poor image quality caused by over-relying on the user adjustment information input by the user to perform noise reduction on the current video frame.

[0064] Further, in some embodiments, the fusion process (such as averaging operation or weighted averaging operation) of the target noise reduction intensity and the default noise reduction intensity to obtain a fusion result includes: performing weighted averaging on the first time-domain noise reduction intensity in the default noise reduction intensity and the second time-domain noise reduction intensity in the target noise reduction intensity to obtain a first weighted average result; wherein the weight of the second time-domain noise reduction intensity is less than the weight of the first time-domain noise reduction intensity; and / or performing weighted averaging on the first spatial-domain noise reduction intensity in the default noise reduction intensity and the second spatial-domain noise reduction intensity in the target noise reduction intensity to obtain a second weighted average result; wherein the weight of the second spatial-domain noise reduction intensity is less than the weight of the first spatial-domain noise reduction intensity.

[0065] Correspondingly, the update of the default noise reduction intensity according to the fusion result includes: updating the value of the first time-domain noise reduction intensity in the default noise reduction intensity to the first weighted average result; and / or updating the value of the first spatial-domain noise reduction intensity in the default noise reduction intensity to the second weighted average result.

[0066] Wherein, for step 403 above, according to the user adjustment information and the size-related parameters, the default noise reduction intensity is adjusted to determine the target noise reduction intensity of the current video frame.

[0067] In the embodiments of the present application, it is not limited whether the default noise reduction intensity includes the noise reduction intensity of one noise reduction dimension or the noise reduction intensities corresponding to multiple noise reduction dimensions respectively.

[0068] Exemplarily, in some embodiments, the default noise reduction intensity includes a first time-domain noise reduction intensity, and the target noise reduction intensity includes a second time-domain noise reduction intensity obtained by adjusting the first time-domain noise reduction intensity. Further, in some embodiments, the default noise reduction intensity includes a first time-domain noise reduction intensity and a first spatial-domain noise reduction intensity, and the target noise reduction intensity includes the second time-domain noise reduction intensity and the first spatial-domain noise reduction intensity.

[0069] Exemplarily, in some other embodiments, the default noise reduction intensity includes a first spatial-domain noise reduction intensity, and the target noise reduction intensity includes a second spatial-domain noise reduction intensity obtained by adjusting the first spatial-domain noise reduction intensity. Further, in some embodiments, the default noise reduction intensity includes a first time-domain noise reduction intensity and a first spatial-domain noise reduction intensity, and the target noise reduction intensity includes the first time-domain noise reduction intensity and the second spatial-domain noise reduction intensity.

[0070] Exemplarily, in some other embodiments, the default noise reduction intensity includes a first time-domain noise reduction intensity and a first spatial-domain noise reduction intensity, and the target noise reduction intensity includes a second time-domain noise reduction intensity obtained by adjusting the first time-domain noise reduction intensity and a second spatial-domain noise reduction intensity obtained by adjusting the first spatial-domain noise reduction intensity.

[0071] As mentioned in the previous step 403, that is, according to the user adjustment information and the size-related parameters, the default noise reduction intensity is adjusted to determine the target noise reduction intensity of the current video frame.

[0072] Wherein, the size-related parameters refer to the size-related parameters of the motion area of the current video frame; in the embodiments of the present application, the relationship between the size-related parameters and the adjustment amplitude of the default noise reduction intensity is not limited.

[0073] In some embodiments, when the adjustment intention corresponding to the user adjustment information is to increase the noise reduction intensity (that is, increase the noise reduction intensity), the increase amplitude of the first spatial-domain noise reduction intensity is positively correlated with the size-related parameters, and the increase amplitude of the first time-domain noise reduction intensity is negatively correlated with the size-related parameters.

[0074] That is to say, when the user expects to increase or enhance the noise reduction intensity, for the current video frame with a larger motion area size, the first spatial-domain noise reduction intensity is significantly increased, and the first time-domain noise reduction intensity is slightly increased. For the current video frame with a smaller motion area size, the first spatial-domain noise reduction intensity is slightly increased, and the first time-domain noise reduction intensity is significantly increased. The main consideration for such a design is that: for the current video frame with a larger motion area size, that is, the difference between the current video frame and the reference video frame is relatively large. At this time, if the time-domain noise reduction intensity of this video frame is too large, it is easy to cause ghosting in the processing result. For the current video frame with a smaller motion area size, that is, the difference between the current video frame and the reference video frame is relatively small. At this time, if the spatial-domain noise reduction intensity of this video frame is too large, it is easy to lose more image details. Therefore, for the current video frame with a smaller motion area size, the first spatial-domain noise reduction intensity is slightly increased, and the first time-domain noise reduction intensity is significantly increased, which is beneficial to better removing the noise signal of the current video frame, helping to better remove the noise signal while retaining more image details and improving the image quality.

[0075] In some embodiments, when the adjustment intention corresponding to the user adjustment information is to decrease the noise reduction intensity, the decrease amplitude of the first spatial-domain noise reduction intensity is negatively correlated with the size-related parameters, and the decrease amplitude of the first time-domain noise reduction intensity is positively correlated with the size-related parameters.

[0076] That is to say, in the case where the user expects to reduce or weaken the noise reduction intensity, for the current video frame with a relatively large size of the motion area, the first spatial domain noise reduction intensity is slightly weakened, and the first temporal domain noise reduction intensity is significantly weakened. For the current video frame with a relatively small size of the motion area, the first spatial domain noise reduction intensity is significantly weakened, and the first temporal domain noise reduction intensity is slightly weakened. The main consideration for such a design is as follows: For the current video frame with a relatively large size of the motion area, that is, the current video frame has a relatively large difference from the reference video frame. At this time, if the temporal domain noise reduction intensity for this video frame is too large, it is easy to cause ghosting in the processing result. For the current video frame with a relatively small size of the motion area, that is, the current video frame has a relatively small difference from the reference video frame. At this time, if the spatial domain noise reduction intensity for this video frame is too large, it is easy to lose more image details. Therefore, for the current video frame with a relatively small size of the motion area, slightly strengthening the first spatial domain noise reduction intensity and significantly strengthening the first temporal domain noise reduction intensity are beneficial to better removing the noise signal of the current video frame, helping to better remove the noise signal while retaining more image details and improving the image quality.

[0077] Exemplarily, in a possible implementation manner, the second spatial domain noise reduction intensity W can be determined according to the following formula (1) S , and the second temporal domain noise reduction intensity W can be determined according to the following formula (2) T :

[0078]

[0079] Among them, α 1 and β 1 are preset parameters in different shooting scenarios; P 1 and P 2 are the default noise reduction intensities corresponding to the current shooting scenario, that is, P 1 is the first spatial domain noise reduction intensity, and P 2 is the first temporal domain noise reduction intensity; M r is a parameter related to the size of the motion area of the current video frame (such as the proportion of the motion area in the overall image, etc.); the mapping function f is a mapping function that is positively correlated with the parameter M r ; in formulas (1) and (2), str is the intensity parameter input by the user obtained (i.e., an example of the user adjustment information), and the value "50" is the standard value of str before the user inputs the intensity parameter. If str > 50, it means that the user's adjustment intention is to strengthen the noise reduction intensity. If str ≤ 50, it means that the user's adjustment intention is to weaken the noise reduction intensity. For example Figure 2 As shown, before the user inputs the intensity parameter, the current intensity parameter corresponding to the progress bar is the progress corresponding to 50 (i.e., the gray area).

[0080] It should be noted that in the embodiments of the present application, the standard value of str before the user inputs the intensity parameter is not limited to 50, and this standard value can be any value greater than 0 defined in advance.

[0081] As mentioned above, the user adjustment information input by the user may include user adjustment parameters (such as the intensity parameter str input by the user as described above). Based on this, in some embodiments, the method further includes: determining the adjustment intention corresponding to the user adjustment information according to the magnitude relationship between the user adjustment parameter and the initial adjustment parameter displayed by the first touch element.

[0082] For example, if the user adjustment parameter is greater than the initial adjustment parameter (for example, str is greater than the standard value of str before the user inputs the intensity parameter), it is determined that the adjustment intention corresponding to the user adjustment information is to increase the noise reduction intensity. If the user adjustment parameter is less than the initial adjustment parameter (for example, str is less than the standard value of str before the user inputs the intensity parameter), it is determined that the adjustment intention corresponding to the user adjustment information is to decrease the noise reduction intensity.

[0083] In the embodiments of the present application, for the initial adjustment parameter displayed by the first touch element, it can also be understood as the default value, standard value, or initial value of the user adjustment parameter when no user adjustment parameter is received.

[0084] Step 104, perform noise reduction processing on the current video frame according to the target noise reduction intensity to determine the target image of the current video frame.

[0085] In some embodiments, as Figure 5 shown, step 104 may further include the following steps 501 to 503:

[0086] Step 501, perform spatial domain noise reduction processing on the current video frame to determine the first spatial domain noise reduction map.

[0087] In the embodiments of the present application, a spatial domain noise reduction algorithm or a pre-trained spatial domain noise reduction network can be used to perform spatial domain noise reduction processing on the current video frame. The first spatial domain noise reduction map can be an image obtained by performing spatial domain noise reduction processing on the current video frame, or can be obtained by further processing the result of performing spatial domain noise reduction processing on the current video frame.

[0088] Step 502, determine the temporal domain noise reduction map of the current video frame according to the temporal domain noise reduction map of the reference video frame of the current video frame.

[0089] In the embodiments of the present application, there is no limitation on the reference video frame, and the reference video frame can be the previous adjacent frame image of the current video frame, or other adjacent frame images.

[0090] There is no limitation on the time-domain noise reduction processing method adopted in step 502, and a time-domain noise reduction algorithm or a pre-trained time-domain noise reduction network can be used.

[0091] In some embodiments, as Figure 6 shown, step 502 may include the following steps 601 and 602:

[0092] Step 601, determining the motion information of the current video frame relative to the reference video frame.

[0093] In some embodiments, the motion information is determined according to the use of an optical flow method or a pre-trained motion detection network. For example, in a possible implementation manner, step 601 may further include: aligning the first spatial domain noise reduction map of the current video frame with the first spatial domain noise reduction map of the reference video frame (or the target image of the reference video frame, etc.) to obtain image alignment information; determining the motion gray scale map (i.e., an example of motion information) of the first spatial domain noise reduction map of the current video frame and the first spatial domain noise reduction map of the reference video frame (or the target image of the reference video frame, etc.) according to the image alignment information.

[0094] It should be understood that the pixel value of each pixel point in the motion gray scale map represents the motion information of the corresponding pixel point. For example, a pixel value of 0 represents that there is no movement between the two frames before and after the current pixel point, a pixel value of 255 represents that there is a large movement between the two frames before and after the current pixel point, and a value between 0 and 255 represents the confidence level of whether there is movement.

[0095] Step 602, determining the time-domain noise reduction map of the current video frame according to the first spatial domain noise reduction map, the time-domain noise reduction map of the reference video frame, and the motion information.

[0096] In some embodiments, step 602 can be implemented by using a time-domain noise reduction method or a pre-trained time-domain noise reduction network (i.e., a time-domain noise reduction AI model).

[0097] In a possible implementation manner, step 602 may further include: performing morphological processing on the motion information (such as the motion gray scale map); inputting the image obtained after morphological processing, the first spatial domain noise reduction map, and the time-domain noise reduction map of the reference video frame into a pre-trained time-domain noise reduction network, and the time-domain noise reduction network obtains the time-domain noise reduction map of the current video frame after operation.

[0098] Step 503, determining the target image of the current video frame according to the target noise reduction intensity, the first spatial domain noise reduction map, and the time-domain noise reduction map of the current video frame.

[0099] As mentioned above, the target noise reduction intensity includes a second spatial domain noise reduction intensity and / or a second temporal domain noise reduction intensity.

[0100] Based on this, further, in some embodiments, as Figure 7 shown, step 503 may include the following steps 701 and 702:

[0101] Step 701, according to the second spatial domain noise reduction intensity, perform a fusion process on the current video frame and the first spatial domain noise reduction map to determine a second spatial domain noise reduction map.

[0102] For example, according to the second spatial domain noise reduction intensity, perform a weighted average operation on the current video frame and the first spatial domain noise reduction map to determine a second spatial domain noise reduction map. The second spatial domain noise reduction map may be obtained by a weighted average operation, or may be obtained by further processing the image obtained by the weighted average operation.

[0103] It can be understood that step 701 describes how to determine the second spatial domain noise reduction map when the target noise reduction intensity includes the second spatial domain noise reduction intensity obtained by adjusting the first spatial domain noise reduction intensity.

[0104] In other embodiments, when the target noise reduction intensity does not include the second spatial domain noise reduction intensity, then according to the first spatial domain noise reduction intensity in the default noise reduction intensity, perform a fusion process on the current video frame and the first spatial domain noise reduction map to determine a second spatial domain noise reduction map. For example, according to the first spatial domain noise reduction intensity, perform a weighted average operation on the current video frame and the first spatial domain noise reduction map to determine a second spatial domain noise reduction map. The second spatial domain noise reduction map may be obtained by a weighted average operation, or may be obtained by further processing the image obtained by the weighted average operation.

[0105] Step 702, according to the second spatial domain noise reduction map and the temporal domain noise reduction map of the current video frame, determine the target image of the current video frame.

[0106] In some embodiments, step 702 may further include: according to the second temporal domain noise reduction intensity, perform a fusion process on the second spatial domain noise reduction map and the temporal domain noise reduction map of the current video frame to determine the target image of the current video frame.

[0107] For example, according to the second temporal domain noise reduction intensity, perform a weighted average operation on the second spatial domain noise reduction map and the temporal domain noise reduction map of the current video frame to determine the target image of the current video frame. The target image may be obtained by a weighted average operation, or may be obtained by further processing the image obtained by the weighted average operation.

[0108] It can be understood that in the case where the target noise reduction intensity includes the second time-domain noise reduction intensity obtained by adjusting the first time-domain noise reduction intensity, how to determine the target image is described in the above embodiments.

[0109] In some other embodiments, in the case where the target noise reduction intensity does not include the second time-domain noise reduction intensity, the second spatial-domain noise reduction map and the time-domain noise reduction map of the current video frame are fused according to the first time-domain noise reduction intensity in the default noise reduction intensity to determine the target image of the current video frame. For example, according to the first time-domain noise reduction intensity, a weighted average operation is performed on the second spatial-domain noise reduction map and the time-domain noise reduction map of the current video frame to determine the target image of the current video frame. The target image may be obtained by a weighted average operation, or may be obtained by further processing the image obtained by the weighted average operation.

[0110] The possible implementation solutions of the video noise reduction method described in one or more of the above embodiments are described by way of example as follows.

[0111] In the embodiments of the present application, an entry for a user to adjust noise and details according to personal preferences is provided, and the time-domain noise reduction intensity and the spatial-domain noise reduction intensity corresponding to the user adjustment parameters of the current scene are recorded and stored as the default noise reduction intensity of the current scene; after obtaining the user adjustment parameters, the underlying algorithm adaptively adjusts the spatial-domain noise reduction intensity and the time-domain noise reduction intensity according to the proportion of the moving area in the current picture. Among them, the parameters representing the current scene include: illuminance, ISO (sensitivity), exposure time, shadow area ratio, etc.

[0112] 1) Interface schematic diagram

[0113] A manipulation option for adjusting the noise reduction intensity is added to the video preview interface (i.e., an example of the first user interface). For example Figure 2 The first touch element 202 shown. The default intensity parameter is set to 50. If the user adjusts the intensity parameter to be between 0 and 50, it means weakening the current noise reduction intensity to highlight many details. If the user adjusts the intensity parameter to be between 50 and 100, it means enhancing the current noise reduction intensity to remove more noise.

[0114] 2) Parameter update

[0115] Different default noise reduction intensities are set according to multi-dimensional information such as light intensity, ISO (sensitivity), exposure time, and shadow area ratio, where this multi-dimensional information corresponds to a shooting scene. If the user does not adjust the intensity parameter, the default noise reduction intensity is read and used for noise reduction processing. Such as Figure 8As shown in the figure, if the user adjusts the intensity parameter, the Image Signal Processor (ISP) will read the intensity parameter input by the user in real time, and the intensity parameter set by the user can be applied to update the preview and recording effects in the next frame. Moreover, the target noise reduction intensity corresponding to the intensity parameter set by the user and the default noise reduction intensity are weighted and averaged to generate a new noise reduction intensity, and the new noise reduction intensity obtained by the weighted average is stored as the default noise reduction intensity when the camera is started next time in the same condition scene.

[0116] 3) Algorithm Design

[0117] In this solution, three networks are pre-trained, one spatial domain noise reduction network, one temporal domain noise reduction network, and one motion detection network. The spatial domain noise reduction network outputs a spatial domain noise reduction map, the temporal domain noise reduction network outputs a temporal domain noise reduction map, and the motion detection network outputs a motion grayscale map. In the motion grayscale map, the pixel value of 0 represents that there is no movement between the two frames before and after the current pixel point, the pixel value of 255 represents that there is a large movement between the two frames before and after the current pixel point, and the value between 0 - 255 represents the confidence level of whether there is movement.

[0118] When implementing noise reduction as Figure 9 shown in the figure, first, the current frame image (i.e., the input image or the current video frame) is sent into the spatial domain noise reduction network to remove the spatial domain noise, and the fusion ratio of the spatial domain noise reduction map (i.e., the image output by the spatial domain noise reduction network after the input image is input into the spatial domain noise reduction network, that is, the first spatial domain noise reduction map) and the input image is controlled by the parameter Ws to obtain the adjusted spatial domain noise reduction map (i.e., the second spatial domain noise reduction map). The spatial domain noise reduction map output by the spatial domain noise reduction network, the motion grayscale map after morphological processing, and the temporal domain noise reduction map of the previous frame are sent into the temporal domain noise reduction network to obtain the temporal domain noise reduction map of the current frame. Finally, according to the parameter W T The temporal domain noise reduction map of the current frame and the adjusted spatial domain noise reduction map are fused to obtain the final noise reduction output.

[0119] Among them, the image alignment network is used to align the content of the spatial domain noise reduction image output by the spatial domain noise reduction network and the previous frame image, obtain the alignment information and input it into the motion detection network.

[0120] Among them, the intensity parameter str adjusted by the user will directly affect the spatial domain noise reduction intensity Ws and the temporal domain noise reduction intensity W T , that is, the spatial domain noise reduction intensity Ws and the temporal domain noise reduction intensity W are determined according to the following formulas (1) and (2) T .

[0121]

[0122] Among them, α 1 , β 1 are preset parameters in different scenarios, P1 , P 2 are the default parameters of the airspace noise reduction intensity and the time domain noise reduction intensity in different scenarios. str is the intensity parameter obtained from the user input, and M r is the proportion of the moving area obtained by motion detection in the overall image. The mapping function f is a mapping function that is positively correlated with the parameter M r .

[0123] According to this formula, it can be known that when adjusting the intensity of the intensity-modulated noise reduction str (i.e., str > 50), if the proportion of the moving area is large, the intensity of the airspace noise reduction is mainly adjusted (greatly adjusted), and the intensity of the time domain noise reduction is slightly adjusted. If the proportion of the moving area is small, the intensity of the time domain noise reduction is mainly adjusted, and the intensity of the airspace noise reduction is slightly adjusted; similarly, when adjusting the weakening noise reduction intensity (i.e., str ≤ 50), if the proportion of the moving area is large, the intensity of the time domain noise reduction is mainly weakened, and the intensity of the airspace noise reduction is slightly weakened. If the proportion of the moving area is small, the intensity of the airspace noise reduction is mainly weakened, and the intensity of the time domain noise reduction is slightly weakened.

[0124] It can be understood that this solution proposes a solution that can adjust the noise intensity according to personal preferences and record personal preference parameters for the next startup of the camera. Using this solution, the noise reduction intensity can be adjusted according to the user's personal preferences, and the user-set parameters can be stored, which is equivalent to having the function of personal customized noise reduction effect, helping to further improve the user experience.

[0125] It should be noted that this solution can be extended to the user to control the noise reduction intensity by voice input, recognize keywords such as "weaken noise reduction" and "strengthen noise reduction" through voice recognition, and adjust the intensity of the input noise in a certain step size to achieve the purpose of controlling the noise reduction intensity.

[0126] It should be noted that the video noise reduction method provided in the embodiments of the present application can be used for noise reduction processing of the already captured video files (such as video files in the album, etc.), and can also be used for noise reduction processing during video shooting. When the video noise reduction method is used for noise reduction processing during video shooting, this method can be applied to the noise reduction unit in the ISP.

[0127] It should be noted that although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that these steps must be executed in this specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step for execution, and / or one step can be decomposed into multiple steps for execution, etc.; or, the steps in different embodiments can be combined into a new technical solution.

[0128] Based on the foregoing embodiments, an embodiment of the present application provides a video noise reduction device. The device includes each module included therein, as well as each unit included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be an AI acceleration engine (such as an NPU, etc.), an ISP, a GPU, a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0129] Figure 10 is a schematic structural diagram of the video noise reduction device provided by an embodiment of the present application; as Figure 10 shown, the video noise reduction device 100 includes a display module 1001, an acquisition module 1002, a first determination module 1003, and a second determination module 1004, where:

[0130] The display module 1001 is configured to display a first user interface, and the first user interface includes at least a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity;

[0131] The acquisition module 1002 is configured to acquire input user adjustment information in response to a touch operation received by the first touch element;

[0132] The first determination module 1003 is configured to determine the target noise reduction intensity of the current video frame according to the user adjustment information;

[0133] The second determination module 1004 is configured to perform noise reduction processing on the current video frame according to the target noise reduction intensity and determine the target image of the current video frame.

[0134] In some embodiments, the determining the target noise reduction intensity of the current video frame according to the user adjustment information includes: determining size-related parameters of the motion area of the current video frame; acquiring the default noise reduction intensity of the current shooting scene; and adjusting the default noise reduction intensity according to the user adjustment information and the size-related parameters to determine the target noise reduction intensity of the current video frame.

[0135] Exemplarily, in some embodiments, the default noise reduction intensity includes a first time-domain noise reduction intensity and / or a first spatial-domain noise reduction intensity, and the target noise reduction intensity includes a second time-domain noise reduction intensity obtained by adjusting the first time-domain noise reduction intensity and / or a second spatial-domain noise reduction intensity obtained by adjusting the first spatial-domain noise reduction intensity.

[0136] In some embodiments, when the adjustment intention corresponding to the user adjustment information is to enhance the noise reduction intensity, the enhancement amplitude of the first spatial domain noise reduction intensity is positively correlated with the size-related parameter, and the enhancement amplitude of the first time domain noise reduction intensity is negatively correlated with the size-related parameter.

[0137] In some embodiments, when the adjustment intention corresponding to the user adjustment information is to weaken the noise reduction intensity, the weakening amplitude of the first spatial domain noise reduction intensity is negatively correlated with the size-related parameter, and the weakening amplitude of the first time domain noise reduction intensity is positively correlated with the size-related parameter.

[0138] In some embodiments, the method of performing noise reduction processing on the current video frame according to the target noise reduction intensity to determine the target image of the current video frame includes: performing spatial domain noise reduction processing on the current video frame to determine a first spatial domain noise reduction map; determining the time domain noise reduction map of the current video frame according to the time domain noise reduction map of the reference video frame of the current video frame; and determining the target image of the current video frame according to the target noise reduction intensity, the first spatial domain noise reduction map, and the time domain noise reduction map of the current video frame.

[0139] Further, in some embodiments, the method of determining the target image of the current video frame according to the target noise reduction intensity, the first spatial domain noise reduction map, and the time domain noise reduction map of the current video frame includes: performing fusion processing on the current video frame and the first spatial domain noise reduction map according to the second spatial domain noise reduction intensity to determine a second spatial domain noise reduction map; and determining the target image of the current video frame according to the second spatial domain noise reduction map and the time domain noise reduction map of the current video frame.

[0140] Even further, in some embodiments, the method of determining the target image of the current video frame according to the second spatial domain noise reduction map and the time domain noise reduction map of the current video frame includes: performing fusion processing on the second spatial domain noise reduction map and the time domain noise reduction map of the current video frame according to the second time domain noise reduction intensity to determine the target image of the current video frame.

[0141] Further, in some embodiments, the method of determining the time domain noise reduction map of the current video frame according to the time domain noise reduction map of the reference video frame of the current video frame includes: determining the motion information of the current video frame relative to the reference video frame; and determining the time domain noise reduction map of the current video frame according to the first spatial domain noise reduction map, the time domain noise reduction map of the reference video frame, and the motion information.

[0142] In some embodiments, the target image is also displayed on the first user interface.

[0143] In some embodiments, the user adjustment information includes user adjustment parameters; the first determination module 1003 is further configured to determine the adjustment intention corresponding to the user adjustment information according to the magnitude relationship between the user adjustment parameters and the initial adjustment parameters displayed by the first touch element.

[0144] In some embodiments, the video noise reduction device 100 further includes a third determination module and an update module, wherein the third determination module is configured to perform a fusion process on the target noise reduction intensity and the default noise reduction intensity to obtain a fusion process result; the update module is configured to update the default noise reduction intensity according to the fusion process result; wherein, the fusion weight of the target noise reduction intensity is less than the fusion weight of the default noise reduction intensity.

[0145] The description of the above device embodiments is similar to the description of the above method embodiments and has similar beneficial effects to those of the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0146] It should be noted that the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there may be other division methods in actual implementation. In addition, each functional unit in the various embodiments of the present application may be integrated in one processing unit, may exist separately physically, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, or in the form of a software functional unit. It may also be implemented in the form of a combination of software and hardware.

[0147] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the related technology, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), magnetic disks, or optical discs that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0148] The embodiments of the present application provide an electronic device, Figure 11 is a schematic structural diagram of the electronic device provided by the embodiments of the present application; as Figure 11As shown, the electronic device 110 includes a memory 1101 and a processor 1102. The memory 1101 stores a computer program that can run on the processor 1102. When the processor 1102 executes the program, it implements the steps in the method provided in the above embodiments.

[0149] It should be noted that the memory 1101 is configured to store instructions and applications executable by the processor 1102, and can also cache data to be processed or already processed in the processor 1102 and each module of the electronic device 110 (for example, image data, audio data, voice communication data, and video communication data), and can be implemented by flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0150] In the embodiments of the present application, the type of the electronic device is not limited, and the electronic device can be various devices with image processing capabilities. For example, the electronic device can be a mobile phone, a laptop computer, a tablet computer, a drone, or a vehicle-mounted device, etc.

[0151] The embodiments of the present application also provide a computer-readable storage medium for storing a computer program.

[0152] Optionally, the computer-readable storage medium can be applied to the electronic device in the embodiments of the present application, and the computer program causes the processor or the electronic device to execute the various methods in the embodiments of the present application. For the sake of brevity, it will not be elaborated here.

[0153] The embodiments of the present application also provide a computer program product including computer program instructions.

[0154] Optionally, the computer program product can be applied to the electronic device in the embodiments of the present application, and the computer program instructions cause the processor or the electronic device to execute the various methods in the embodiments of the present application. For the sake of brevity, it will not be elaborated here.

[0155] The embodiments of the present application also provide a computer program.

[0156] Optionally, the computer program can be applied to the electronic device in the embodiments of the present application. When the computer program runs on the processor or the electronic device, it causes the processor or the electronic device to execute the various methods in the embodiments of the present application. For the sake of brevity, it will not be elaborated here.

[0157] It should be noted here that the descriptions of the above electronic devices, storage media, computer program products, and computer program embodiments are similar to those of the above method embodiments and have similar beneficial effects to the method embodiments. For the technical details not disclosed in the electronic devices, storage media, computer program products, and computer program embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0158] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures, or characteristics related to the embodiment are included in at least one embodiment of this application. Therefore, the appearances of "in one embodiment" or "in an embodiment" or "in some embodiments" throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of this application, the sequence numbers of the above processes do not mean the order of execution is prior or subsequent. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application. The sequence numbers of the embodiments of this application above are only for description and do not represent the advantages or disadvantages of the embodiments. The descriptions of the above embodiments tend to emphasize the differences between the embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated here.

[0159] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, object A and / or object B can represent: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0160] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further limitation, the element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0161] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0162] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules; they can be located in one place or distributed to multiple network units; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0163] In addition, each functional module in the embodiments of the present application can be all integrated in a processing unit, or each module can be separately used as a unit, or two or more modules can be integrated in a unit; the above-mentioned integrated modules can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0164] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), magnetic disks, or optical disks, etc., which can store program codes.

[0165] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable an electronic device to execute all or part of the methods described in the various embodiments of the present application. And the foregoing storage medium includes: removable storage devices, ROM, magnetic disks, or optical disks, etc., which can store program codes.

[0166] The methods disclosed in several method embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0167] The features disclosed in several product embodiments provided by this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0168] The features disclosed in several method or device embodiments provided by this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0169] As mentioned above, it is only the implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A video noise reduction method, characterized in that: The method comprises: Displaying a first user interface, wherein the first user interface includes at least a first touch element, and the first touch element is used to provide an entry for adjusting noise reduction intensity; In response to the touch operation received by the first touch element, acquiring input user adjustment information; Determining a target noise reduction intensity of a current video frame according to the user adjustment information; The current video frame is subjected to noise reduction processing according to the target noise reduction intensity to determine a target image of the current video frame.

2. The method according to claim 1, characterized in that The step of determining a target noise reduction intensity of the current video frame according to the user adjustment information includes: Determining parameters related to the size of the motion region of the current video frame; Get the default noise reduction strength of the current shooting scene; The default noise reduction intensity is adjusted according to the user adjustment information and the size-related parameters to determine a target noise reduction intensity for the current video frame.

3. The method according to claim 2, characterized in that The default noise reduction intensity includes a first time domain noise reduction intensity and / or a first spatial domain noise reduction intensity, and the target noise reduction intensity includes a second time domain noise reduction intensity obtained by adjusting the first time domain noise reduction intensity and / or a second spatial domain noise reduction intensity obtained by adjusting the first spatial domain noise reduction intensity.

4. The method according to claim 3, characterized in that When the adjustment intention corresponding to the user adjustment information is to increase the noise reduction intensity, the intensity adjustment amplitude of the first spatial noise reduction intensity is positively correlated with the size-related parameter, and the intensity adjustment amplitude of the first time domain noise reduction intensity is negatively correlated with the size-related parameter.

5. The method according to claim 3, characterized in that: When the adjustment intention corresponding to the user adjustment information is to weaken the noise reduction intensity, the weakening amplitude of the first spatial noise reduction intensity is negatively correlated with the size-related parameter, and the weakening amplitude of the first time-domain noise reduction intensity is positively correlated with the size-related parameter.

6. The method according to any one of claims 1 to 5, characterized in that The performing noise reduction processing on the current video frame according to the target noise reduction intensity to determine the target image of the current video frame includes: Performing spatial noise reduction processing on the current video frame to determine a first spatial noise reduction map; Determining a temporal denoising map of the current video frame according to a temporal denoising map of a reference video frame of the current video frame; A target image of the current video frame is determined according to the target noise reduction intensity, the first spatial noise reduction map, and the temporal noise reduction map of the current video frame.

7. The method according to claim 6, characterized in that The step of determining a target image of the current video frame according to the target noise reduction strength, the first spatial noise reduction map, and the temporal noise reduction map of the current video frame includes: According to the second spatial noise reduction strength, the current video frame and the first spatial noise reduction map are fused to determine a second spatial noise reduction map; A target image of the current video frame is determined according to the second spatial denoising map and the temporal denoising map of the current video frame.

8. The method according to claim 7, characterized in that The step of determining the target image of the current video frame according to the second spatial denoising map and the temporal denoising map of the current video frame includes: According to the second temporal noise reduction strength, the second spatial noise reduction map and the temporal noise reduction map of the current video frame are fused to determine a target image of the current video frame.

9. The method according to claim 6, characterized in that The step of determining the temporal denoising map of the current video frame according to the temporal denoising map of the reference video frame of the current video frame comprises: Determining motion information of the current video frame relative to the reference video frame; The temporal denoising map of the current video frame is determined according to the first spatial denoising map, the temporal denoising map of the reference video frame and the motion information.

10. The method according to any one of claims 1 to 9, characterized in that The method also includes: displaying the target image on the first user interface.

11. The method according to claim 4 or 5, characterized in that: The user adjustment information includes user adjustment parameters; the method further includes: An adjustment intention corresponding to the user adjustment information is determined according to a magnitude relationship between the user adjustment parameter and an initial adjustment parameter displayed by the first touch element.

12. The method according to any one of claims 2 to 5, characterized in that: The method further comprises: Performing a fusion process on the target noise reduction intensity and the default noise reduction intensity to obtain a fusion process result; The default noise reduction strength is updated according to the fusion processing result; wherein the fusion weight of the target noise reduction strength is less than the fusion weight of the default noise reduction strength.

13. A video noise reduction device, characterized in that: The device comprises: A display module configured to display a first user interface, wherein the first user interface includes at least a first touch element, and the first touch element is used to provide an entry for adjusting the noise reduction intensity; an acquisition module, configured to acquire input user adjustment information in response to the touch operation received by the first touch element; A first determination module is configured to determine a target noise reduction intensity of a current video frame according to the user adjustment information; The second determination module is configured to perform noise reduction processing on the current video frame according to the target noise reduction intensity to determine a target image of the current video frame.

14. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 12 is implemented.

15. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the method according to any one of claims 1 to 12 is implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method according to any one of claims 1 to 12 is implemented.

Images