CN114693515A - Image deformation method and device, electronic device and storage medium - Google Patents

Abstract

The present disclosure relates to an image deformation method and device, an electronic device, and a storage medium. The method includes: acquiring an image to be processed including a target object; acquiring deformation information of a reference object in a preset reference image, where the deformation information represents the deformation of the reference object. The position of the reference key point before and after the movement, the reference key point is used to control the deformation of the reference image; according to the deformation information, the target key point corresponding to the reference key point in the image to be processed is determined, and the reference key point and the target key point are determined. Based on the position change information, the deformation position of the target key point is determined, and according to the deformation position of the target key point, the image to be processed is deformed to obtain the target image, and the target object in the target image has the deformation effect. The embodiments of the present disclosure can realize self-defined deformation of the target object in the target image.

Description

Image deformation method and device, electronic device and storage medium

technical field

The present disclosure relates to the field of computer technology, and in particular, to an image deformation method and device, an electronic device, and a storage medium.

Background technique

At present, camera applications installed in smart devices such as mobile phones and tablets usually have special effects deformation functions to meet the interesting needs of users. In the prior art, the user usually directly selects the deformation template provided in the camera function, which cannot meet the user's requirement of customizing the deformation effect.

SUMMARY OF THE INVENTION

The present disclosure proposes a technical solution for image deformation.

According to an aspect of the present disclosure, an image deformation method is provided, including: acquiring an image to be processed including a target object; acquiring deformation information of a reference object in a preset reference image, where the deformation information represents the reference of the reference object the position of the key point before and after the movement, the reference key point is used to control the deformation of the reference image; according to the deformation information, determine the target key point corresponding to the reference key point in the image to be processed, and determine the position change information between the reference key point and the target key point; determine the deformation position of the target key point based on the position change information, and determine the deformation position of the target key point according to the deformation position of the target key point. The to-be-processed image is deformed to obtain a target image, where the target object in the target image has a deformation effect.

In a possible implementation manner, the determining the deformation position of the target key point based on the position change information includes: acquiring information on a proportional relationship between the reference object and a specified part in the target object; proportional relationship information and the position change information to determine the deformation position of the target key point

In a possible implementation manner, the acquiring the proportional relationship information between the reference object and the designated part in the target object includes: determining the designated part of the reference object according to the reference key point information of the reference object According to the target key point information of the target object, the second scale information between the designated parts of the target object is determined; according to the first scale information and the second scale information, The proportional relationship information of the designated part is determined.

In a possible implementation manner, the determining the deformation position of the target key point according to the proportional relationship information and the position change information includes: according to the position change information and the target key point where the target key point is located The initial position in the image to be processed is determined, and the relative deformation position of the target key point relative to the reference key point is determined; the deformation position of the target key point is determined according to the scale relationship information and the relative deformation position.

In a possible implementation manner, performing deformation processing on the to-be-processed image according to the deformation position of the target key point to obtain the target image includes: according to the deformation position of the target key point and the target image The initial position of the key point in the image to be processed determines the target pixel position of each pixel in the image to be processed; according to the target pixel position of each pixel in the image to be processed, the The image is deformed to obtain the target image.

In a possible implementation manner, the method further includes: acquiring a grid corresponding to the image to be processed, where the grid is obtained by meshing the image to be processed according to a preset division size, The grid includes a plurality of sub-grids with the divided size; wherein, the determination of the The target pixel position of each pixel in the image to be processed includes: determining the first type of pixel according to the initial position, the deformed position and the first initial pixel position of the first type of pixel in the image to be processed The first target pixel position of the pixel point, the first type of pixel point includes the pixel point located at the grid vertex of the sub-grid in the image to be processed; according to the first initial pixel position, the first pixel point a target pixel position and a second initial pixel position of a second type of pixel point in the image to be processed, determine a second target pixel position of the second type of pixel point, the second type of pixel point includes the to-be-processed pixel point The pixel points in the image inside the grid of the sub-grid; wherein, the target pixel position includes the first target pixel position of the first type of pixel point and the second target pixel of the second type of pixel point Location.

In a possible implementation manner, the first type of pixel point of the first type of pixel is determined according to the initial position, the deformed position, and the first initial pixel position of the first type of pixel point in the to-be-processed image. A target pixel position, comprising: determining a position mapping relationship corresponding to the to-be-processed image according to the initial position and the deformed position, where the position-mapping relationship represents that the pixel points in the to-be-processed image are connected with each other before the deformation processing. The mapping relationship after deformation processing; according to the first initial pixel position of the first type of pixel point and the position mapping relationship, the first target pixel position of the first type of pixel point is determined.

In a possible implementation manner, determining the The second target pixel position of the second type of pixel point includes: determining the position movement vector corresponding to the first type pixel point according to the first initial pixel position and the first target pixel position, and the position movement vector represents The moving direction and moving distance of the first type of pixel point moving from the first initial pixel position to the first target pixel position; according to the second initial pixel position of the second type of pixel point, the first Perform interpolation processing on the position movement vector of the first type pixel point on the sub-grid to which the second type pixel point belongs to obtain the target movement vector of the second type pixel point; according to the target movement vector and the second initial pixel position , and determine the second target pixel position of the second type of pixel point.

In a possible implementation manner, the method further includes: in response to a setting operation for the deformed material, determining the deformation information of the reference image indicated by the setting operation as the deformation material, where the deformation material is used for the image to be deformed to deform the target object in .

According to an aspect of the present disclosure, an image deformation apparatus is provided, comprising: an image acquisition module for acquiring an image to be processed including a target object; and an information acquisition module for acquiring deformation information of a reference object in a preset reference image , the deformation information represents the position of the reference key point of the reference object before and after the movement, and the reference key point is used to control the deformation of the reference image; the determination module is used to determine the deformation information according to the deformation information. the target key point corresponding to the reference key point in the to-be-processed image, and determine the position change information between the reference key point and the target key point; the deformation module is used to determine the target key point based on the position change information The deformation position of the target key point is obtained, and according to the deformation position of the target key point, the image to be processed is deformed to obtain a target image, and the target object in the target image has a deformation effect.

In a possible implementation manner, the deformation module includes: a scale acquisition sub-module for acquiring proportional relationship information between the reference object and a specified part in the target object; a position determination sub-module for The proportional relationship information and the position change information are used to determine the deformation position of the target key point.

In a possible implementation manner, the acquiring the proportional relationship information between the reference object and the designated part in the target object includes: determining the designated part of the reference object according to the reference key point information of the reference object According to the target key point information of the target object, the second scale information between the designated parts of the target object is determined; according to the first scale information and the second scale information, The proportional relationship information of the designated part is determined.

In a possible implementation manner, the determining the deformation position of the target key point according to the proportional relationship information and the position change information includes: according to the position change information and the target key point where the target key point is located The initial position in the image to be processed is determined, and the relative deformation position of the target key point relative to the reference key point is determined; the deformation position of the target key point is determined according to the scale relationship information and the relative deformation position.

In a possible implementation manner, the deformation module includes: a pixel position determination sub-module, configured to, according to the deformation position of the target key point and the initial position of the target key point in the image to be processed, Determine the target pixel position of each pixel in the to-be-processed image; the deformation sub-module is configured to perform deformation processing on the to-be-processed image according to the target pixel position of each pixel in the to-be-processed image to obtain the the target image.

In a possible implementation manner, the apparatus further includes: a grid acquiring module, configured to acquire a grid corresponding to the to-be-processed image, where the grid is based on a preset division size for the to-be-processed image Obtained by performing grid division, the grid includes a plurality of sub-grids with the divided size; wherein, the deformation position of the target key point and the target key point are in the image to be processed according to the deformation position determine the target pixel position of each pixel in the image to be processed, including: according to the initial position, the deformation position and the first initial pixel position of the first type of pixel in the image to be processed , determine the first target pixel position of the first type of pixel point, and the first type of pixel point includes the pixel point at the grid vertex of the sub-grid in the image to be processed; according to the first type of pixel point The initial pixel position, the first target pixel position, and the second initial pixel position of the second type of pixel point in the image to be processed, determine the second target pixel position of the second type of pixel point, the second type of pixel point The pixel points include the pixel points in the image to be processed that are inside the grid of the sub-grid; wherein, the target pixel position includes the first target pixel position of the first type of pixel point and the second type of pixel point. The second target pixel position of the pixel point.

In a possible implementation manner, the first type of pixel point of the first type of pixel is determined according to the initial position, the deformed position, and the first initial pixel position of the first type of pixel point in the to-be-processed image. A target pixel position, comprising: determining a position mapping relationship corresponding to the to-be-processed image according to the initial position and the deformed position, where the position-mapping relationship represents that the pixel points in the to-be-processed image are connected with each other before the deformation processing. The mapping relationship after deformation processing; according to the first initial pixel position of the first type of pixel point and the position mapping relationship, the first target pixel position of the first type of pixel point is determined.

In a possible implementation manner, determining the The second target pixel position of the second type of pixel point includes: determining the position movement vector corresponding to the first type pixel point according to the first initial pixel position and the first target pixel position, and the position movement vector represents The moving direction and moving distance of the first type of pixel point moving from the first initial pixel position to the first target pixel position; according to the second initial pixel position of the second type of pixel point, the first Perform interpolation processing on the position movement vector of the first type pixel point on the sub-grid to which the second type pixel point belongs to obtain the target movement vector of the second type pixel point; according to the target movement vector and the second initial pixel position , and determine the second target pixel position of the second type of pixel point.

In a possible implementation manner, the apparatus further includes: a material setting module, configured to, in response to a setting operation for a deformed material, determine the deformation information of the reference image indicated by the setting operation as a deformed material, and the deformed material Footage is used to deform the target object in the image to be deformed.

According to an aspect of the present disclosure, there is provided an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, the computer program instructions implementing the above method when executed by a processor.

In the embodiment of the present disclosure, the deformation effect of the reference object can be synchronously mapped to the target object in the to-be-processed image according to the deformation information of the reference key points on the reference image. Deformation is defined, and the target object in the target image will maintain a similar deformation effect as the reference object without being affected by the pose change of the target object in the image to be processed.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings.

Description of drawings

The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present disclosure, and together with the description, serve to explain the technical solutions of the present disclosure.

FIG. 1 shows a flowchart of an image warping method according to an embodiment of the present disclosure.

FIG. 2 shows a schematic diagram of a reference image according to an embodiment of the present disclosure.

FIG. 3 shows a schematic diagram of an image to be processed according to an embodiment of the present disclosure.

FIG. 4 shows a schematic diagram of a target image according to an embodiment of the present disclosure.

FIG. 5 shows a schematic diagram of a grid according to an embodiment of the present disclosure.

FIG. 6 shows a block diagram of an image warping apparatus according to an embodiment of the present disclosure.

FIG. 7 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure.

Detailed ways

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numbers in the figures denote elements that have the same or similar functions. While various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" in this article is only an association relationship to describe the associated objects, indicating that there can be three kinds of relationships, for example, A and/or B, it can mean that A exists alone, A and B exist at the same time, and A and B exist independently B these three cases. In addition, the term "at least one" herein refers to any combination of any one of the plurality or at least two of the plurality, for example, including at least one of A, B, and C, and may mean including from A, B, and C. Any one or more elements selected from the set of B and C.

In addition, in order to better illustrate the present disclosure, numerous specific details are set forth in the following detailed description. It will be understood by those skilled in the art that the present disclosure may be practiced without certain specific details. In some instances, methods, means, components and circuits well known to those skilled in the art have not been described in detail so as not to obscure the subject matter of the present disclosure.

1 shows a flowchart of an image warping method according to an embodiment of the present disclosure. The image warping method may be executed by an electronic device such as a terminal device or a server. The terminal device may be User Equipment (UE), mobile device, user Terminals, terminals, cellular phones, cordless phones, personal digital assistants (Personal Digital Assistants, PDAs), handheld devices, computing devices, vehicle-mounted devices, wearable devices, etc., the method can be readable by a computer by invoking a computer stored in a memory by a processor The method can be implemented in the form of instructions, or the method can be executed by a server. As shown in Figure 1, the image deformation method includes:

In step S11, an image to be processed including the target object is acquired.

The image to be processed may be an image collected in real time by an image capture device (eg, a camera, a camera, etc.), or an image frame extracted from video data collected by the image capture device, which is not limited in this embodiment of the present disclosure.

It should be understood that the image capture device can be set in the above electronic device as a component, or communicated with the above electronic device by means of wireless connection (such as WIFI connection) or wired connection (such as USB connection), so as to obtain the image capture device. The collected image to be processed; of course, the to-be-processed image may also be data retrieved from the local storage of the electronic device or data transmitted from other electronic devices, which is not limited to this embodiment of the present disclosure.

The target object may include, for example, a human face, a human body, etc. It should be understood that if the target object is a human face, the embodiment of the present disclosure can realize the deformation of the human face, and if the target object is a human body, the embodiment of the present disclosure can realize the deformation of the human body , the embodiment of the present disclosure does not limit the category of the target object.

In step S12, the deformation information of the reference object in the preset reference image is acquired.

It should be understood that when the user expects the target object in the image to be processed to achieve special effect deformation, he can start the relevant application in the electronic device (such as the camera application in the mobile phone) to enter the graphical interaction interface corresponding to the special effect deformation function, and the graphical interaction The above-mentioned reference image may be displayed in the interface, so that the user can move the reference key points on the reference image to obtain deformation information of the reference object in the reference image.

The reference image can be understood as an image provided to the user for customizing the deformation effect. It should be understood that the reference object in the reference image and the target object are of the same category, so that the deformation effect of the reference image can be effectively mapped to the waiting object. Process the target object in the image.

In a possible implementation manner, the reference key points may include reference key points preset on the reference image for controlling the deformation of the reference image, the reference image may be preset with multiple reference key points, and the reference key points may be used for Controls the deformation of the reference image, i.e. the reference key points can be moved. FIG. 2 shows a schematic diagram of a reference image according to an embodiment of the present disclosure. As shown in FIG. 2 , each face key point on the reference face may be a reference key point.

The reference key points may be obtained by detecting object key points on the reference image. For example, when the reference object is a human face, the face key point detection may be performed on the reference image to obtain the reference key points of the face in the reference image; when When the reference object is a human body, the human body key point detection can be performed on the reference image to obtain the reference key points of the human body in the reference image. It should be understood that the embodiments of the present disclosure do not limit the implementation manner of key point detection.

As described above, the reference key points on the reference image can be moved, and the deformation information represents the positions of the reference key points of the reference object before and after the movement. In a possible implementation, for example, the reference key points may be moved by dragging, or some reference key points may be selected first, and movement parameters may be set for the selected reference key points, such as setting the movement After the location, etc., the movement operation for the reference key point is implemented, which is not limited by the embodiment of the present disclosure.

It should be understood that at least one reference key point can be moved at a time, and the reference key point can be moved at least once, and the deformation information can be determined after each movement of the reference key point. The deformation information can represent at least one reference key point before and after moving. s position.

In step S13, according to the deformation information, the target key point corresponding to the reference key point in the image to be processed is determined, and the position change information between the reference key point and the target key point is determined.

Among them, the same key point detection method as the reference key point of the reference object can be used to perform key point detection on the image to be processed to obtain the target key point of the target object in the to-be-processed image, so that the target key point and the reference key point can be corresponding Therefore, it is convenient to use the deformation information of the reference key point to determine the target key point corresponding to the reference key point, and to determine the position change information between the reference key point and the target key point.

The reference key point and the target key point may respectively have index identifiers, and the index identifiers may respectively represent different reference key points on the reference object and different target key points on the target object, so that the target key corresponding to the reference key point can be easily known. point. For example, if the reference key point is the mouth corner key point of the reference object, then the target key point corresponding to the reference key point is also the mouth corner key point of the target object.

As mentioned above, the deformation information can represent the position of the reference key point of the reference object before and after the movement, the position change information can include the movement vector of the target key point relative to the reference key point, and the movement vector can represent the target key point relative to the reference key point. The relative movement direction and relative movement distance of the key points. For example, if the position of a reference key point before moving is (x0, y0) and the position after moving is (x1, y1), then the relative position information can be expressed as a moving vector (x1-x0, y1-y0).

In step S14, the deformation position of the target key point is determined based on the position change information, and according to the deformation position of the target key point, the image to be processed is deformed to obtain a target image, and the target object in the target image has a deformation effect.

Among them, the deformation position can represent the position of the target key point after the target object achieves the deformation effect. As mentioned above, the position change information can include the movement vector of the target key point relative to the reference key point. After the initial position of the target key point in the image to be processed and the position change information are known, it can be obtained that the target key point is in the target object. The deformed position after deformation is reached. For example, following the relative position information (x1-x0, y1-y0) determined based on the deformation information above, if the initial position of the target key point corresponding to the reference key point is (x2, y2), then the target key point's initial position is (x2, y2). The deformed position can be represented as (x2+x1-x0, y2+y1-y0).

Wherein, those skilled in the art can use computer vision technology known in the art, such as OpenCV, to realize the deformation processing of the image to be processed according to the deformation position of the target key point to obtain the target image, which is not limited by the embodiment of the present disclosure. In a possible implementation manner, the target image can be displayed in the above-mentioned graphical interactive interface synchronously, so that when the user moves the reference key point on the reference image, the deformation effect of the target object can be displayed synchronously.

FIG. 3 shows a schematic diagram of an image to be processed according to an embodiment of the present disclosure, and FIG. 4 shows a schematic diagram of a target image according to an embodiment of the present disclosure. deformation information, the deformation effect of the reference face in Fig. 2 can be mapped to the target face in Fig. 3 to obtain the target face shown in Fig. 4, the target face shown in Fig. Refer to the face-like deformation effect.

In the embodiment of the present disclosure, the deformation effect of the reference object can be synchronously mapped to the target object in the to-be-processed image according to the deformation information of the reference key points on the reference image. Deformation is defined, and the target object in the target image will maintain a similar deformation effect as the reference object without being affected by the pose change of the target object in the image to be processed.

Considering that there may be multiple images to be processed, the pose of the target object in each to-be-processed image may vary, that is, the target object in the to-be-processed image may be larger than the reference object in the reference image Or smaller, in order to make the target object in the image to be processed more naturally achieve a similar deformation effect to the reference object, the target object in the image to be processed can be deformed proportionally, that is, the target key points in the deformation can be determined proportionally. After the deformation position, based on the deformation position determined in proportion, the target pixel position of each pixel in the image to be processed is determined, and then the deformation processing of the image to be processed is performed, so that the deformation effect of the target object in the target image after deformation processing is more natural. .

In a possible implementation manner, in step S14, the deformation position of the target key point is determined based on the position change information, including:

Step S141: Obtain the proportional relationship information between the reference object and the designated part in the target object.

The designated part may be a relatively stable part on the target object that is not prone to drastic changes, and the proportional relationship information can be understood as the size ratio between the designated part of the reference object and the designated part of the target object. For example, if the target object is a human face, the designated part can be the eye, and the ratio relationship information can be the ratio between the eye distance of the reference object and the eye distance of the target object; if the target object is a human body, the designated part can be the head and neck, The proportional relationship information may be a ratio between the height of the head and neck of the reference object and the height of the head and neck of the target object.

In a possible implementation manner, acquiring the proportional relationship information between the reference object and the specified part in the target object includes: determining the first proportional information between the specified parts of the reference object according to the reference key point information of the reference object; The target key point information of the object determines the second ratio information between the designated parts of the target object; according to the first ratio information and the second ratio information, the ratio relationship information of the designated parts is determined. In this way, the proportional relationship information of the designated part can be effectively determined.

The first scale information can be understood as the distance information between the designated parts of the reference object, and the second scale information can be understood as the distance information between the designated parts of the target object. For example, if the designated part is the eye, the first The scale information may be the eye distance between the eyes of the reference object, and the second scale information may be the eye distance between the eyes of the target object; if the specified part is the head and neck, the first scale information may be the top of the head of the reference object The height of the head and neck between the bottom of the neck and the bottom of the neck, the second scale information may be the height of the head and the neck between the top of the head and the bottom of the neck of the target object.

The reference key point information may include the position coordinates of the reference key point, and the target key point information may include the position coordinates of the target key point. It should be understood that the first scale information of the designated part of the reference object can be determined according to the position coordinates of the reference key point corresponding to the designated part of the reference object, and the second scale information of the designated part of the target object can be determined according to the position coordinates of the reference key point corresponding to the designated part of the reference object. The position coordinates of the target key points corresponding to the specified parts are determined.

Wherein, determining the proportional relationship information of the specified part according to the first proportional information and the second proportional information may include: determining the ratio between the first proportional information and the second proportional information as the proportional relationship information of the specified part; or, The ratio between the second proportion information and the first proportion information is determined as the proportion relationship information of the designated part, which is not limited in this embodiment of the present disclosure.

Step S142: Determine the deformation position of the target key point according to the proportional relationship information and the position change information.

In a possible implementation manner, determining the deformation position of the target key point according to the scale relationship information and the position change information, including: determining the relative position of the target key point according to the position change information and the initial position of the target key point in the image to be processed. The relative deformation position of the reference key point; according to the proportional relationship information and the relative deformation position, the deformation position of the target key point is determined. In this way, the proportional relationship information can be used to realize the proportional determination of the deformed position of the target key point after the deformation.

As described above, the proportional relationship information may include the movement vector of the target key point relative to the reference key point, wherein the position change information and the initial position of the target key point in the image to be processed are determined to determine the relative movement of the target key point relative to the reference key point. The relative deformation position may include: adding the initial position of the target key point and the movement vector to obtain the relative deformation position. Wherein, determining the deformation position of the target key point according to the proportional relationship information and the relative deformation position may include: multiplying the relative deformation position by the above proportional relationship information to obtain the deformation position of the target key point.

For example, following the relative position information (x1-x0, y1-y0) determined based on the deformation information above, if the initial position of the target key point corresponding to the reference key point is (x2, y2), the reference object is relative to the target object The proportional relationship information of , is expressed as 1/2, then the deformation position of the target key point can be expressed as

In the embodiment of the present disclosure, the deformation effect of the reference object can be proportionally mapped to the target object based on the scale relationship information, so as to achieve a more natural deformation effect.

Considering that the deformation effect of the target object in the target image obtained by deforming the image to be processed is only based on the deformation position of the target key point in the above step S14, the deformation effect of the target object is not natural enough, and the deformation of the target object may affect each image in the image to be processed. The pixel position of the pixel point, in a possible implementation manner, in step S14, according to the deformation position of the target key point, the image to be processed is deformed to obtain the target image, which may include:

Step S143: Determine the target pixel position of each pixel in the image to be processed according to the deformation position of the target key point and the initial position of the target key point in the image to be processed.

Wherein, determining the target pixel position of each pixel in the image to be processed according to the deformation position of the target key point and the initial position of the target key point in the image to be processed may include: according to the deformation position and the initial position of the target key point, Determine the position mapping relationship from the initial position to the deformed position, that is, obtain the position mapping relationship between each pixel in the image to be processed from the initial pixel position before deformation to the target pixel position after deformation; according to the position mapping relationship and the initial pixel position of each pixel point to determine the target pixel position of each pixel point after deformation. It should be understood that each pixel point in the image to be processed includes a pixel point on the target object, so the target object in the deformed target image has a similar deformation effect to the reference object in the reference image.

Wherein, based on the principle of affine transformation, it is possible to determine the position mapping relationship transformed from the initial position to the deformed position according to the initial position and the deformed position, which is not limited in this embodiment of the present disclosure. In a possible implementation manner, formula (1) may be an affine transformation formula obtained based on the principle of affine transformation to characterize the position mapping relationship, and the position mapping relationship determined by formula (1) may be used to obtain the pending processing The target pixel location for each pixel in the image.

i代表第i个与参考关键点对应的第i个目标关键点，p_i代表第i个目标关键点的初始位置，q_i代表第i个目标关键点的变形位置，v代表待处理图像中任一像素点的初始像素位置，w_i代表像素点对应的权重，α代表预设权重控制参数，该α可以是根据图像变形时的自然程度设置的经验值，f_r(v)代表像素点v的目标像素位置，⊥代表对二维向量进行如下变换：(x,y)^⊥＝(-y,x)，T代表转置。in,

_i represents the i-th target key point corresponding to the reference key point, pi represents the initial position of the _i -th target key point, qi represents the deformation position of the i-th target key point, and v represents the image to be processed. The initial pixel position of any pixel point, w _i represents the weight corresponding to the pixel point, α represents the preset weight control parameter, the α can be an empirical value set according to the natural degree of image deformation, _fr (v) represents the pixel point The target pixel position of v, ⊥ represents the following transformation of the two-dimensional vector: (x,y) ^⊥ =(-y,x), T represents the transpose.

It should be understood that the above formula (1) is a method for determining the position mapping relationship provided by the embodiment of the present disclosure, and those skilled in the art can select any affine transformation algorithm known in the art to determine the above position mapping relationship, and correct the position mapping relationship. This embodiment of the present disclosure is not limited.

Step S144: Perform deformation processing on the image to be processed according to the target pixel position of each pixel in the image to be processed to obtain a target image.

As described above, those skilled in the art can use computer vision technologies known in the art, such as OpenCV, to deform the image to be processed according to the target pixel position of each pixel to obtain the target image. For this, the embodiments of the present disclosure No restrictions apply.

In the embodiment of the present disclosure, the image to be processed can be effectively deformed based on the deformation position and the target pixel position of each pixel point in the image to be processed determined based on the initial position.

As described above, in step S143, the target pixel position of each pixel in the image to be processed can be determined by using the position mapping relationship determined between the initial position of the target object and the deformed position to perform deformation processing on the image to be processed. Considering that the resolution of the image to be processed may be relatively large, the amount of computation required to directly calculate the target pixel position of each pixel in the image to be processed based on the position mapping relationship is also relatively large, in order to reduce the calculation of the target pixel position. The amount of computation increases the computational efficiency of the target pixel position. In a possible implementation, the method further includes:

A grid corresponding to the image to be processed is obtained, the grid is obtained by dividing the image to be processed by grid according to a preset division size, and the grid includes a plurality of sub-grids with divided sizes.

The division size may be set according to actual requirements, for example, may be set to a size of 10×10 pixels, which is not limited in this embodiment of the present disclosure. FIG. 5 shows a schematic diagram of a grid according to an embodiment of the present disclosure. The grid shown in FIG. 5 may be obtained by dividing the image to be processed shown in FIG. 3 into a grid according to a size of 10×10 pixels. Each subgrid of 5 has a size of 10×10 pixels.

Based on the grid corresponding to the above-mentioned image to be processed, in a possible implementation manner, in step S143, according to the deformation position of the target key point and the initial position of the target key point in the image to be processed, determine each point in the image to be processed. The target pixel position of a pixel point, which can include:

Step S1431: Determine the first target pixel position of the first type of pixel point according to the initial position, the deformed position and the first initial pixel position of the first type of pixel point in the image to be processed, and the first type of pixel point includes in the image to be processed. The pixel at the mesh vertex of the submesh.

Wherein, the first target pixel position represents the pixel position of the first type of pixel point after the target object achieves the deformation effect. In a possible implementation manner, determining the first target pixel position of the first type of pixel point according to the initial position, the deformed position and the first initial pixel position of the first type of pixel point in the image to be processed includes: according to the initial The position and deformation position determine the position mapping relationship corresponding to the image to be processed; according to the first initial pixel position and the position mapping relationship of the first type pixel point, the first target pixel position of the first type pixel point is determined. In this way, the first target pixel position of the first type of pixel points at the vertices of the mesh in the image to be processed can be effectively obtained based on the position mapping relationship.

The position mapping relationship represents the mapping relationship between the pixels in the image to be processed before the deformation processing and after the deformation processing, or the mapping relationship between the pixels in the image to be processed before the target object achieves the deformation effect and after the deformation effect is achieved. In a possible implementation manner, the determination method of the position mapping relationship in the above-mentioned embodiment of the present disclosure can be referred to, for example, the above formula (1) is used to realize the determination of the position mapping relationship corresponding to the image to be processed and the determination of the first type of pixel point. The first target pixel position of , which is not limited in this embodiment of the present disclosure.

Step S1432: According to the first initial pixel position, the first target pixel position and the second initial pixel position of the second type of pixel point in the image to be processed, determine the second target pixel position of the second type of pixel point, the second type of pixel point. Include pixels in the image to be processed that are inside the grid of the subgrid.

It should be understood that each pixel point in the image to be processed may include a first-type pixel point located at a grid vertex of the sub-grid and a second-type pixel point located inside the grid of the sub-grid in the image to be processed, The target pixel position includes the first target pixel position of the first type of pixel point and the second target pixel position of the second type of pixel point.

Wherein, the second target pixel position represents the pixel position of the second type of pixel point after the target object achieves the deformation effect. In a possible implementation manner, the second target pixel position of the second type of pixel is determined according to the first initial pixel position, the first target pixel position and the second initial pixel position of the second type of pixel in the image to be processed , including: according to the first initial pixel position and the first target pixel position, determining the position movement vector corresponding to the first type of pixel point, the position movement vector representing the movement of the first type of pixel point from the first initial pixel position to the first target pixel position According to the second initial pixel position of the second type of pixel point, the position movement vector of the first type of pixel point on the sub-grid to which the second type of pixel point belongs is interpolated to obtain the second type of pixel point. The target movement vector corresponding to the point; the second target pixel position of the second type of pixel point is determined according to the target movement vector and the second initial pixel position. In this way, the second target pixel of the second type of pixel in the grid to be processed in the image to be processed can be efficiently obtained by using the position movement vector of the first type of pixel point around the second type of pixel point based on the interpolation method Location.

Wherein, it is possible to determine the position movement vector corresponding to the first type of pixel point according to the first initial pixel position and the first target pixel position with reference to the above-mentioned determination method of the relative movement vector, that is, to determine the first type of pixel point of each first type of pixel point. A target pixel position is subtracted from the first initial pixel position to obtain the position movement vector of each first-type pixel point, which is not limited in this embodiment of the present disclosure.

Wherein, for any second-type pixel point, the sub-grid to which the second-type pixel point belongs can be understood as a sub-grid containing the second-type pixel point, and the first-type pixel on the sub-grid to which the second-type pixel point belongs A point can be understood as a pixel point at a mesh vertex of a sub-mesh containing the second type of pixel point. It should be understood that any sub-grid in the grid corresponding to the image to be processed may contain a plurality of second-type pixel points, and according to the second initial pixel position of any second-type pixel point, a Perform interpolation processing, such as linear interpolation, nonlinear interpolation, on the position movement vector of the first type pixel point at the grid vertex of the second type pixel point sub-grid, to obtain the target movement vector corresponding to the second type pixel point.

Wherein, determining the second target pixel position of the second type of pixel point according to the target movement vector and the second initial pixel position, for example, may include: adding the second initial pixel position and the target movement vector to obtain the second type of pixel point The second target pixel location.

As mentioned above, the reference image and the target image can be displayed together in the operation interface, then when the user moves the reference key point, the reference image can be deformed simultaneously according to the process of steps S1431 to S1432, so that the reference image The deformation effects of reference objects in , appear more natural.

In this embodiment of the present disclosure, the first target pixel positions of the first type of pixels at the vertices of the grid after the target object achieves the deformation effect can be calculated based on the position mapping relationship, and the second type of pixels inside the grid can be obtained by interpolation. The second target pixel position of the pixel point, because the amount of computation required for interpolation calculation is less than the amount of computation required to determine the target pixel position based on the position mapping relationship, which can effectively reduce the amount of computation required to calculate the target pixel position and improve the target pixel position. computational efficiency.

Considering that the user may wish to save the custom deformation effect so as to directly use the custom deformation effect later, or share the custom deformation effect with other users, in a possible implementation manner, the method further includes: In response to the setting operation for the deformed material, the deformation information of the reference image indicated by the setting operation is determined as the deformation material, and the deformation material is used to deform the target object in the image to be deformed. In this way, the user-defined deformation effect can be saved, so that the user can directly use the user-defined deformation effect.

The image to be deformed may be any image containing the target object. The deformed material may be saved and/or shared in the form of a data package, and the data package may include an index identifier of a reference key point and deformation information. In this way, when the user selects the deformation material, the target object in the to-be-deformed image can be deformed directly by using the data packet corresponding to the deformation material.

It should be understood that those skilled in the art can use software development technologies known in the art to design and develop the application program of the image deformation method in the above-mentioned embodiment of the present disclosure and the corresponding graphical interactive interface, and the graphical interactive interface can provide settings. The operation control of the deformed material is convenient for the user to set the deformed material, save and/or share the deformed material, etc., which is not limited in this embodiment of the present disclosure.

It can be understood that the above-mentioned method embodiments mentioned in the present disclosure can be combined with each other to form a combined embodiment without violating the principle and logic. Those skilled in the art can understand that, in the above method of the specific embodiment, the specific execution order of each step should be determined by its function and possible internal logic.

In addition, the present disclosure also provides image warping apparatuses, electronic devices, computer-readable storage media, and programs, all of which can be used to implement any image warping method provided by the present disclosure. For the corresponding technical solutions and descriptions, refer to the corresponding records in the Methods section. ,No longer.

FIG. 6 shows a block diagram of an image deformation apparatus according to an embodiment of the present disclosure. As shown in FIG. 6 , the apparatus includes:

an image acquisition module 101, configured to acquire a to-be-processed image including a target object;

The information acquisition module 102 is configured to acquire deformation information of the reference object in the preset reference image, where the deformation information represents the position of the reference key point of the reference object before and after the movement, and the reference key point is used to control the reference image is deformed;

A determination module 103, configured to determine, according to the deformation information, a target key point corresponding to the reference key point in the to-be-processed image, and determine position change information between the reference key point and the target key point ;

The deformation module 104 is configured to determine the deformation position of the target key point based on the position change information, and perform deformation processing on the to-be-processed image according to the deformation position of the target key point to obtain a target image, the target image The target object in the image has a deformation effect.

In a possible implementation manner, the deformation module 104 includes: a scale acquisition sub-module for acquiring proportional relationship information between the reference object and a designated part in the target object; a position determination sub-module for The proportional relationship information and the position change information determine the deformation position of the target key point

In a possible implementation manner, the acquiring the proportional relationship information between the reference object and the designated part in the target object includes: determining the designated part of the reference object according to the reference key point information of the reference object According to the target key point information of the target object, the second scale information between the designated parts of the target object is determined; according to the first scale information and the second scale information, The proportional relationship information of the designated part is determined.

In a possible implementation manner, the determining the deformation position of the target key point according to the proportional relationship information and the position change information includes: according to the position change information and the target key point where the target key point is located The initial position in the image to be processed is determined, and the relative deformation position of the target key point relative to the reference key point is determined; the deformation position of the target key point is determined according to the scale relationship information and the relative deformation position.

In a possible implementation manner, the deformation module 104 includes: a pixel position determination sub-module, configured to determine the deformation position of the target key point according to the deformation position of the target key point and the initial position of the target key point in the image to be processed , determine the target pixel position of each pixel in the image to be processed; the deformation sub-module is used to deform the image to be processed according to the target pixel position of each pixel in the image to be processed, to obtain the target image.

In a possible implementation manner, the apparatus further includes: a grid acquiring module, configured to acquire a grid corresponding to the to-be-processed image, where the grid is based on a preset division size for the to-be-processed image Obtained by performing grid division, the grid includes a plurality of sub-grids with the divided size; wherein, the deformation position of the target key point and the target key point are in the image to be processed according to the deformation position determine the target pixel position of each pixel in the image to be processed, including: according to the initial position, the deformation position and the first initial pixel position of the first type of pixel in the image to be processed , determine the first target pixel position of the first type of pixel point, and the first type of pixel point includes the pixel point at the grid vertex of the sub-grid in the image to be processed; according to the first type of pixel point The initial pixel position, the first target pixel position, and the second initial pixel position of the second type of pixel point in the image to be processed, determine the second target pixel position of the second type of pixel point, the second type of pixel point The pixel points include the pixel points in the image to be processed that are inside the grid of the sub-grid; wherein, the target pixel position includes the first target pixel position of the first type of pixel point and the second type of pixel point. The second target pixel position of the pixel point.

In a possible implementation manner, the first type of pixel point of the first type of pixel is determined according to the initial position, the deformed position, and the first initial pixel position of the first type of pixel point in the to-be-processed image. A target pixel position, comprising: determining a position mapping relationship corresponding to the to-be-processed image according to the initial position and the deformed position, where the position-mapping relationship represents that the pixel points in the to-be-processed image are connected with each other before the deformation processing. The mapping relationship after deformation processing; according to the first initial pixel position of the first type of pixel point and the position mapping relationship, the first target pixel position of the first type of pixel point is determined.

In a possible implementation manner, determining the The second target pixel position of the second type of pixel point includes: determining the position movement vector corresponding to the first type pixel point according to the first initial pixel position and the first target pixel position, and the position movement vector represents The moving direction and moving distance of the first type of pixel point moving from the first initial pixel position to the first target pixel position; according to the second initial pixel position of the second type of pixel point, the first Perform interpolation processing on the position movement vector of the first type pixel point on the sub-grid to which the second type pixel point belongs to obtain the target movement vector of the second type pixel point; according to the target movement vector and the second initial pixel position , and determine the second target pixel position of the second type of pixel point.

In a possible implementation manner, the apparatus further includes: a material setting module, configured to, in response to a setting operation for a deformed material, determine the deformation information of the reference image indicated by the setting operation as a deformed material, and the deformed material Footage is used to deform the target object in the image to be deformed.

In the embodiment of the present disclosure, the deformation effect of the reference object can be synchronously mapped to the target object in the to-be-processed image according to the deformation information of the reference key points on the reference image. Deformation is defined, and the target object in the target image will maintain a similar deformation effect as the reference object without being affected by the pose change of the target object in the image to be processed.

In some embodiments, the functions or modules included in the apparatuses provided in the embodiments of the present disclosure may be used to execute the methods described in the above method embodiments. For specific implementation, reference may be made to the descriptions of the above method embodiments. For brevity, here No longer.

Embodiments of the present disclosure further provide a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the foregoing method is implemented. Computer-readable storage media can be volatile or non-volatile computer-readable storage media.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to invoke the instructions stored in the memory to execute the above method.

Embodiments of the present disclosure also provide a computer program product, including computer-readable codes, or a non-volatile computer-readable storage medium carrying computer-readable codes, when the computer-readable codes are stored in a processor of an electronic device When running in the electronic device, the processor in the electronic device executes the above method.

The present disclosure relates to the field of augmented reality. By acquiring the image information of the target object in the real environment, the relevant features, states and attributes of the target object can be detected or recognized with the help of various visual correlation algorithms, so as to obtain the image information matching the specific application. AR effect that combines virtual and reality. Exemplarily, the target object may involve faces, limbs, gestures, movements, etc. related to the human body, or objects, markers, or sandboxes, display areas, or display items related to venues or venues. Vision-related algorithms may involve visual localization, SLAM, 3D reconstruction, image registration, background segmentation, object keypoint extraction and tracking, object pose or depth detection, etc. The specific application can not only involve interactive scenes such as navigation, navigation, explanation, reconstruction, and virtual effect overlay display related to real scenes or items, but also special effects processing related to people, such as makeup beautification, body beautification, special effects display, virtual Model display and other interactive scenarios. The relevant features, states and attributes of the target object can be detected or recognized through the convolutional neural network. The above convolutional neural network is a network model obtained by model training based on a deep learning framework.

The electronic device may be provided as a terminal, server or other form of device.

FIG. 7 shows a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or terminal device. 7, electronic device 1900 includes processing component 1922, which further includes one or more processors, and a memory resource represented by memory 1932 for storing instructions executable by processing component 1922, such as applications. An application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Additionally, the processing component 1922 is configured to execute instructions to perform the above-described methods.

The electronic device 1900 may also include a power supply assembly 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input output (I/O) interface 1958 . The electronic device 1900 can operate based on an operating system stored in the memory 1932, such as a Microsoft server operating system (Windows Server ^™ ), a graphical user interface-based operating system (Mac OSX ^™ ) introduced by Apple, a multi-user multi-process computer operating system ( Unix ^™ ), Free and Open Source Unix-like Operating System (Linux ^™ ), Open Source Unix-like Operating System (FreeBSD ^™ ) or the like.

In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as memory 1932 comprising computer program instructions executable by processing component 1922 of electronic device 1900 to perform the above-described method.

The present disclosure may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of the present disclosure.

A computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above. Computer-readable storage media, as used herein, are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.

The computer readable program instructions described herein may be downloaded to various computing/processing devices from a computer readable storage medium, or to an external computer or external storage device over a network such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for carrying out operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or instructions in one or more programming languages. Source or object code, written in any combination, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider through the Internet connect). In some embodiments, custom electronic circuits, such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can be personalized by utilizing state information of computer readable program instructions. Computer readable program instructions are executed to implement various aspects of the present disclosure.

Aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.

These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams. These computer readable program instructions can also be stored in a computer readable storage medium, these instructions cause a computer, programmable data processing apparatus and/or other equipment to operate in a specific manner, so that the computer readable medium storing the instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

Computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , thereby causing instructions executing on a computer, other programmable data processing apparatus, or other device to implement the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more functions for implementing the specified logical function(s) executable instructions. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.

The above descriptions of the various embodiments tend to emphasize the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, details are not repeated herein.

Those skilled in the art can understand that in the above method of the specific implementation, the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.

If the technical solution of this application involves personal information, the product applying the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of the present application involves sensitive personal information, the product applying the technical solution of the present application has obtained the individual's individual consent before processing sensitive personal information, and at the same time satisfies the requirement of "express consent". For example, at the personal information collection device such as a camera, a clear and conspicuous sign is set to inform that the personal information has entered the collection range, and the personal information will be collected. On the device for personal information processing, where the personal information processing rules are informed by obvious signs/information, personal authorization is obtained through pop-up information or by asking individuals to upload their personal information; among them, personal information processing rules may include personal information processing rules. Information processor, purpose of processing personal information, method of processing, and types of personal information processed.

Various embodiments of the present disclosure have been described above, and the foregoing descriptions are exemplary, not exhaustive, and not limiting of the disclosed embodiments. Numerous modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the various embodiments, the practical application or improvement over the technology in the marketplace, or to enable others of ordinary skill in the art to understand the various embodiments disclosed herein.

Claims (12)

1. An image warping method, comprising:

acquiring an image to be processed including a target object;

acquiring deformation information of a reference object in a preset reference image, wherein the deformation information represents the positions of reference key points of the reference object before and after movement, and the reference key points are used for controlling the deformation of the reference object;

determining a target key point corresponding to the reference key point in the image to be processed according to the deformation information, and determining position change information between the reference key point and the target key point;

and determining the deformation position of the target key point based on the position change information, and performing deformation processing on the image to be processed according to the deformation position of the target key point to obtain a target image, wherein a target object in the target image has a deformation effect.

2. The method of claim 1, wherein the determining the deformed positions of the target keypoints based on the position change information comprises:

acquiring proportional relation information of the reference object and a designated part in the target object;

and determining the deformation position of the target key point according to the proportional relation information and the position change information.

3. The method according to claim 2, wherein the obtaining of the proportional relationship information between the reference object and the designated part of the target object comprises:

determining first proportion information between specified parts of the reference object according to the reference key point information of the reference object;

determining second proportion information between specified parts of the target object according to the target key point information of the target object;

and determining the proportional relation information of the designated part according to the first proportional information and the second proportional information.

4. The method according to claim 2 or 3, wherein the determining the deformation position of the target key point according to the proportional relationship information and the position change information comprises:

determining the relative deformation position of the target key point relative to the reference key point according to the position change information and the initial position of the target key point in the image to be processed;

and determining the deformation position of the target key point according to the proportional relation information and the relative deformation position.

5. The method according to any one of claims 1 to 4, wherein the performing deformation processing on the image to be processed according to the deformation position of the target key point to obtain a target image comprises:

determining the target pixel position of each pixel point in the image to be processed according to the deformation position of the target key point and the initial position of the target key point in the image to be processed;

and according to the target pixel position of each pixel point in the image to be processed, carrying out deformation processing on the image to be processed to obtain the target image.

6. The method of claim 5, further comprising:

acquiring a grid corresponding to the image to be processed, wherein the grid is obtained by carrying out grid division on the image to be processed according to a preset division size, and the grid comprises a plurality of sub-grids with the division size;

determining the target pixel position of each pixel point in the image to be processed according to the deformation position of the target key point and the initial position of the target key point in the image to be processed, wherein the determining the target pixel position of each pixel point in the image to be processed comprises:

determining a first target pixel position of a first type of pixel points according to the initial position, the deformation position and a first initial pixel position of the first type of pixel points in the image to be processed, wherein the first type of pixel points comprise pixel points at grid vertexes of the sub-grid in the image to be processed;

determining a second target pixel position of a second type of pixel points according to the first initial pixel position, the first target pixel position and a second initial pixel position of the second type of pixel points in the image to be processed, wherein the second type of pixel points comprise pixel points which are positioned in the interior of the grid of the sub-grid in the image to be processed;

the target pixel position comprises a first target pixel position of the first type of pixel point and a second target pixel position of the second type of pixel point.

7. The method according to claim 6, wherein the determining a first target pixel position of a first type pixel point according to the initial position, the deformation position and a first initial pixel position of the first type pixel point in the image to be processed comprises:

determining a position mapping relation corresponding to the image to be processed according to the initial position and the deformation position, wherein the position mapping relation represents a mapping relation between pixel points in the image to be processed before deformation processing and after deformation processing;

and determining a first target pixel position of the first-class pixel point according to the mapping relation between the first initial pixel position of the first-class pixel point and the position.

8. The method of claim 6, wherein determining the second target pixel position of the second type of pixel points according to the first initial pixel position, the first target pixel position, and the second initial pixel position of the second type of pixel points in the image to be processed comprises:

determining a position movement vector corresponding to the first type of pixel point according to the first initial pixel position and the first target pixel position, wherein the position movement vector represents a movement direction and a movement distance of the first type of pixel point from the first initial pixel position to the first target pixel position;

according to the second initial pixel position of the second type of pixel point, carrying out interpolation processing on the position motion vector of the first type of pixel point on the sub-grid to which the second type of pixel point belongs to obtain a target motion vector of the second type of pixel point;

and determining a second target pixel position of the second type of pixel points according to the target motion vector and the second initial pixel position.

9. The method according to any one of claims 1-8, further comprising:

in response to a setting operation for deformation materials, determining deformation information of a reference image indicated by the setting operation as deformation materials, wherein the deformation materials are used for deforming a target object in an image to be deformed.

10. An image morphing apparatus, characterized by comprising:

the image acquisition module is used for acquiring an image to be processed comprising a target object;

the information acquisition module is used for acquiring deformation information of a reference object in a preset reference image, wherein the deformation information represents the positions of reference key points of the reference object before and after movement, and the reference key points are used for controlling the deformation of the reference image;

the determining module is used for determining a target key point corresponding to the reference key point in the image to be processed according to the deformation information and determining position change information between the reference key point and the target key point;

and the deformation module is used for determining the deformation position of the target key point based on the position change information, and performing deformation processing on the image to be processed according to the deformation position of the target key point to obtain a target image, wherein a target object in the target image has a deformation effect.

11. An electronic device, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 9.

12. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 9.

Images