Virtual human eyebrow redirection method and device, electronic equipment and storage medium

Abstract

The invention provides a virtual human eyebrow redirection method and device, electronic equipment and a storage medium, and relates to the technical field of virtual digital humans, and the method comprises the steps: firstly obtaining a template human face corresponding to a target human face; and then redirecting the template eyebrow of the template face by using the facial form relationship between the target face and the template face to obtain a target eyebrow of the target face. According to the method, redirection processing of a template eyebrow is unbound with a face grid, migration of the template eyebrow by the face grid is not needed any more, the facial form relation between a target face and a template face is introduced in the redirection processing process, and the possible facial form difference between the target face and the template face is considered. Therefore, the display effect of the template eyebrow on the template human face is the same as the display effect of the target eyebrow on the target human face and is not influenced by the face shape difference, the template eyebrow can be perfectly matched with the target human faces with different face shapes, the user requirements can be met, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual digital humans, and in particular to a method, device, electronic equipment and storage medium for redirecting eyebrows of a virtual human. Background Art

[0002] With the continuous development of 3D virtual human technology, 3D video generation platforms allow users to create personalized 3D virtual humans as characters in 3D videos on the platform. Users can choose different hairstyles, face shapes, facial features, decorations, and clothing for 3D virtual humans to create personalized 3D virtual humans.

[0003] In terms of technical implementation, different types of hairstyles, face shapes, facial features, eyebrow shapes, decorations, and clothing are pre-stored on the platform and deployed on the 3D virtual human template for display for users to choose. When creating a personalized 3D virtual human, the hairstyle, face shape, facial features, eyebrow shape, decorations, clothing, etc. that are compatible with the 3D virtual human template need to be migrated to the personalized 3D virtual human created by the user.

[0004] The usual method of migrating eyebrows is to use the 3D virtual human face mesh as a reference system to migrate the eyebrows on the face of the 3D virtual human template to the same position on the face of the personalized 3D virtual human created by the user. However, since the face shape of the 3D virtual human template may be different from the face shape of the personalized 3D virtual human, this will cause the display effect of the eyebrows selected by the user on the face of the 3D virtual human template to be different from the display effect on the face of the personalized 3D virtual human, thereby reducing the user experience. Summary of the invention

[0005] The present invention provides a virtual human eyebrow redirection method, device, electronic device and storage medium, which are used to solve the defects existing in the related technology.

[0006] The present invention provides a virtual human eyebrow redirection method, comprising: Obtain a template face corresponding to the target face; Based on the face shape relationship between the target face and the template face, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face.

[0007] According to a virtual human eyebrow redirection method provided by the present invention, the face shape relationship includes a proportional relationship between the target face and the template face, and / or an eyebrow and eye distribution relationship.

[0008] According to a virtual human eyebrow redirection method provided by the present invention, based on the proportion relationship and / or the eyebrow and eye distribution relationship, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, including: Based on the proportional relationship and / or the eyebrow and eye distribution relationship, redirect the position information of the first projection point of the control point of the template eyebrow in the frontal view to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view; Based on the position information of the second projection point, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0009] According to a virtual human eyebrow redirection method provided by the present invention, the control points of the template eyebrow and the target eyebrow each include a plurality of control points; Based on the proportional relationship and the eyebrow and eye distribution relationship, the position information of the first projection point of the control point of the template eyebrow in the frontal view is redirected to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view, including: Based on the proportional relationship, the position information of the plurality of first projection points is scaled, and based on the eyebrow and eyebrows distribution relationship, the position information of the plurality of first projection points is translated to obtain the position information of the plurality of second projection points.

[0010] According to a virtual human eyebrow redirection method provided by the present invention, based on the distribution relationship between eyebrows and eyes, the position information of the plurality of first projection points is translated to obtain the position information of the plurality of second projection points, including: Based on the proportional relationship, determining a first association relationship between the position information of the plurality of first projection points and the position information of the plurality of second projection points; Based on the first association relationship and the eyebrow and eye distribution relationship, the position information of the plurality of first projection points is translated to obtain the position information of the plurality of second projection points.

[0011] According to a virtual human eyebrow redirection method provided by the present invention, based on the proportion relationship and / or the eyebrow and eye distribution relationship, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, and further includes: Sampling the control points of the template eyebrow to obtain the sampling points of the template eyebrow, and establishing a second association relationship between the control points of the template eyebrow and the sampling points; Based on the proportion relationship and / or the eyebrow distribution relationship, redirect the position information of the third projection point of the sampling point in the frontal face view to obtain the position information of the fourth projection point of the sampling point in the frontal face view; Based on the position information of the fourth projection point and the second association relationship, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0012] According to a virtual human eyebrow redirection method provided by the present invention, the number of the sampling points is multiple; the spatial position information of the control point of the target eyebrow on the target face is calculated based on the position information of the fourth projection point and the second association relationship, including: Based on the position information of each of the fourth projection points, calculate the centroid coordinates of the plurality of the fourth projection points, and apply the centroid coordinates to the face grid of the target face to obtain the spatial position information of the plurality of sampling points on the target face; Based on the second association relationship, the spatial position information of multiple sampling points on the template face, the spatial position information of multiple sampling points on the target face, and the spatial position information of the control points of the template eyebrows, the spatial position information of the control points of the target eyebrows on the target face is calculated.

[0013] According to a virtual human eyebrow redirection method provided by the present invention, the proportional relationship is determined based on the eye length ratio of the target face and the template face, and / or the face width ratio.

[0014] According to a virtual human eyebrow redirection method provided by the present invention, the eyebrow and eye distribution relationship includes that the eyebrow and eye distribution ratio of the target face and the template face are the same.

[0015] According to a virtual human eyebrow redirection method provided by the present invention, the template eyebrows of the template face are redirected based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face, and then the method includes: Determining the template curvature of each curve segment in the template eyebrow; Based on the template curvature, the target curvature of each curve segment in the target eyebrow is corrected.

[0016] According to a virtual human eyebrow redirection method provided by the present invention, the template eyebrows of the template face are redirected based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face, and then the method further includes: Performing deformation processing on the eyebrow region of the texture map of the template face to obtain an eyebrow texture map adapted to the target eyebrow; Apply the eyebrow texture map to the target face.

[0017] The present invention also provides a virtual human eyebrow redirection device, comprising: A template face acquisition module is used to acquire a template face corresponding to a target face; The eyebrow redirection module is used to redirect the template eyebrows of the template face based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face.

[0018] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the virtual human eyebrow redirection method as described in any one of the above is implemented.

[0019] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the virtual human eyebrow redirection method as described in any one of the above is implemented.

[0020] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for redirecting the eyebrows of a virtual human as described in any one of the above is implemented.

[0021] The virtual human eyebrow redirection method, device, electronic device and storage medium provided by the present invention first obtain a template face corresponding to a target face; then redirect the template eyebrows of the template face using the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face. The method unbinds the redirection processing of the template eyebrows from the face grid, and no longer migrates the template eyebrows based on the face grid. The face shape relationship between the target face and the template face is introduced in the redirection processing process, and the possible face shape difference between the target face and the template face is taken into account, so that the display effect of the template eyebrows on the template face is the same as the display effect of the target eyebrows on the target face, and will not be affected by the face shape difference. The template eyebrows can achieve perfect adaptation with target faces of different face shapes, which can meet user needs and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a schematic diagram of the face mesh of a 3D virtual human provided by the present invention.

[0024] Figure 2 It is a schematic diagram of the face of a 3D virtual human template and a personalized 3D virtual human provided by the present invention.

[0025] Figure 3It is a flow chart of the virtual human eyebrow redirection method provided by the present invention.

[0026] Figure 4 It is a schematic diagram of the positions of the key points of the eyebrows and eyes on the template face provided by the present invention.

[0027] Figure 5 It is a schematic diagram comparing the display effects of the target eyebrows obtained by the virtual human eyebrow redirection method provided by the present invention and the eyebrow migration performed using the prior art.

[0028] Figure 6 It is a schematic diagram of the positions of control points and sampling points of template eyebrows in the virtual human eyebrow redirection method provided by the present invention.

[0029] Figure 7 It is a schematic diagram of the control point positions for calculating the template curvature in the virtual human eyebrow redirection method provided by the present invention.

[0030] Figure 8 It is a schematic diagram of the effect of triangulating the eyebrow area of ​​the texture map in the virtual human eyebrow redirection method provided by the present invention.

[0031] Fig. 9 A schematic diagram of the redirection effect of the virtual human eyebrow redirection method provided by the present invention applied to short flat eyebrows and long flat eyebrows.

[0032] Fig.10 It is a structural schematic diagram of a virtual human eyebrow redirection device provided by the present invention.

[0033] Fig.11 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] like Figure 1 As shown, in a 3D virtual human creation platform or a 3D video generation platform, the face of a 3D virtual human can be regarded as an irregular surface in a three-dimensional space. In order to facilitate processing of the irregular surface, the irregular surface is segmented into a plurality of cells to form a face grid. Each cell can be a triangle or a quadrilateral. Thus, the face grid of a 3D virtual human can be composed of face grid lines and face grid vertices.

[0036] Here, the face grid is equivalent to adding longitude and latitude lines to the face. Based on the segmentation of the face grid, different positions on the face can be mapped to different cells. In other words, a coordinate system similar to "longitude and latitude" is built on the face through the face grid, so that different positions on the face can be determined based on the face grid.

[0037] After the face mesh is built, the hairstyle, facial features and eyebrow shape of the face can be deployed based on the face mesh. Among them, the eyebrows of the 3D virtual person are usually deployed and extended along the face mesh with the face mesh of the 3D virtual person as the reference system, and the eyebrows on the face of the 3D virtual person template are transferred to the same face mesh area on the face of the personalized 3D virtual person.

[0038] However, since the face shape of the 3D virtual human template and the personalized 3D virtual human may be different, the distribution of the facial grids may also be different. After the user selects a specific eyebrow shape and migrates it to the personalized 3D virtual human's face, the eyebrows will be distorted after migration due to the difference in the distribution of the facial grids, and cannot be distributed and extended on the personalized 3D virtual human's face in the shape expected by the user. As a result, the display effect of the eyebrows selected by the user on the face of the 3D virtual human template is different from that on the personalized 3D virtual human's face, which reduces the user experience.

[0039] like Figure 2 As shown, the face on the left is the face of the 3D virtual human template, and the face on the right is the face of the personalized 3D virtual human. The eyebrow shape of the 3D virtual human template is migrated to the face of the personalized 3D virtual human. Due to the difference in face shape, the spacing of the facial grid lines of the personalized 3D virtual human is narrower than the spacing of the facial grid lines of the 3D virtual human template, so that the migrated eyebrow shape also becomes narrower. This causes the eyebrow shape of the personalized 3D virtual human to be inconsistent with the eyebrow shape selected by the user, reducing the user experience.

[0040] Based on this, a method for redirecting virtual human eyebrows is provided in an embodiment of the present invention.

[0041] Figure 3 FIG. 1 is a flow chart of a method for redirecting eyebrows of a virtual human provided in an embodiment of the present invention. Figure 3 As shown, the method includes: S31, obtaining a template face corresponding to the target face; S32, based on the face shape relationship between the target face and the template face, redirect the template eyebrows of the template face to obtain target eyebrows of the target face.

[0042] Specifically, the virtual human eyebrow redirection method provided in the embodiment of the present invention is executed by a virtual human eyebrow redirection device, which can be configured in a 3D virtual human creation platform or a 3D video generation platform. The 3D virtual human creation platform or the 3D video generation platform can be installed in a local computer or in the cloud. The local computer can be a computer, a tablet, etc., which is not specifically limited here.

[0043] First, step S31 is performed to obtain a template face corresponding to the target face. Here, the target face refers to the face of a personalized 3D virtual human created by the user, and the user needs to generate target eyebrows on the target face. The template face refers to the face of a 3D virtual human template adapted to the template eyebrow shape selected by the user for the target face, and the template eyebrow shape selected by the user is configured on the template face.

[0044] It is understandable that the left and right eyes of the 3D virtual person each have eyebrows corresponding to them, and the eyebrows on the left and right sides are not completely symmetrical, so they need to be redirected separately. For the sake of convenience, the embodiment of the present invention only takes the redirection of one eyebrow as an example to illustrate the technical principle, which does not constitute a limitation on the embodiment of the present invention.

[0045] The template eyebrow shape may include multiple template eyebrows, that is, the template face includes multiple template eyebrows. Each template eyebrow can be represented by a B-spline curve. Since the B-spline curve is a linear combination of B-spline basis functions, the B-spline curve can be converted into a linear combination of several B-spline basis functions. Then, the B-spline curve corresponding to each template eyebrow can include several control points, and the curve shape of the corresponding template eyebrow can be controlled by the control points. All template eyebrows on the template face can constitute a template eyebrow set, that is: , where E is the template eyebrow set, represents the i-th template eyebrow, and m is the number of all template eyebrows.

[0046] All control points of each template eyebrow can constitute a control point set, namely: ,in represents the control point set of the i-th template eyebrow, and n is the number of all control points of the i-th template eyebrow. The control point set of all template eyebrows on the template face can be expressed as: .

[0047] Here, the spatial position information of the control points of each template eyebrow on the template face is known, and the spatial position information may be a three-dimensional coordinate.

[0048] Then, step S32 is executed to redirect the template eyebrows of the template face by using the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face. Here, the face shape relationship between the target face and the template face refers to the association relationship between the face shape of the target face and the face shape of the template face, which can be a difference relationship and can be represented by parameters such as the shape difference, contour deviation or feature point offset between the face shape of the target face and the template face.

[0049] By utilizing the face shape relationship, the template eyebrows of the template face can be redirected. The redirection process refers to the process of mapping the template eyebrows of the template face to the target face by utilizing the face shape relationship, and then obtaining the target eyebrows of the target face. It can be understood that, in the process of the redirection process, the control points of the template eyebrows of the template face can be migrated to the target face by utilizing the face shape relationship, and the target eyebrows of the target face can be obtained. Here, the target face also includes a plurality of target eyebrows, and the target eyebrows correspond to the template eyebrows one by one. Each target eyebrow also includes a plurality of control points, and the curve shape of the corresponding target eyebrows is controlled by the control points. The control points on the target eyebrows also correspond to the control points on the template eyebrows one by one. Thus, obtaining the target eyebrows of the target face can be achieved by determining the spatial position information of the control points of the target eyebrows on the target face.

[0050] The virtual human eyebrow redirection method provided in the embodiment of the present invention first obtains a template face corresponding to a target face; then, the template eyebrows of the template face are redirected using the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face. The method unbinds the redirection processing of the template eyebrows from the face grid, and no longer migrates the template eyebrows based on the face grid. The face shape relationship between the target face and the template face is introduced in the redirection processing process, and the possible face shape difference between the target face and the template face is considered, so that the display effect of the template eyebrows on the template face is the same as the display effect of the target eyebrows on the target face, and will not be affected by the face shape difference. The template eyebrows can be perfectly adapted to target faces with different face shapes, which can meet user needs and improve user experience.

[0051] Based on the above embodiment, the face shape relationship includes the ratio relationship between the target face and the template face, and / or the distribution relationship of the eyebrows and eyes.

[0052] Specifically, the face shape relationship used in the embodiment of the present invention may include at least one of a ratio relationship between the target face and the template face and a distribution relationship between eyebrows and eyes.

[0053] The proportional relationship may refer to the size ratio between the target face and the template face, which may include the overall scaling ratio of the face, the local scaling ratio of the area around the eyebrows, or the weighted sum ratio of the overall scaling ratio of the face and the local scaling ratio, which is not specifically limited here.

[0054] It is understandable that in the frontal view, the direction of the line connecting the two eyes can be regarded as the horizontal direction (i.e., the x-axis), and the direction perpendicular to the horizontal direction can be regarded as the vertical direction (i.e., the y-axis). In three-dimensional space, the direction of the line connecting the two eyes can be regarded as the horizontal direction in the frontal view, and the direction perpendicular to the horizontal direction can be regarded as the vertical direction (i.e., the z-axis).

[0055] The eyebrow and eye distribution relationship refers to the relationship between the eyebrow and eye distribution ratios in the target face and the template face, wherein the eyebrow and eye distribution ratio k1 in the template face can be the distribution ratio of the eyebrow key points and the eye key points on the template face. The eyebrow key points may include the end of the eyebrow, the middle of the eyebrow and the beginning of the eyebrow, and the eye key points may include the beginning of the eye, the middle of the eye and the end of the eye.

[0056] For example, in the frontal view, k1 may include a horizontal eyebrow and eye distribution ratio k11 and a vertical eyebrow and eye distribution ratio k12. k11 may be represented by the horizontal coordinates of the face width boundary points, eyebrow tail, eye tail, eye head, eyebrow head, and midline of the template face. For example, it may be represented as k12 can be represented by the vertical coordinates of the eyes, eyebrows and top of the skull of the template face, for example , , , , , , They are the horizontal coordinates of the face width boundary points, eyebrow tail, eye tail, eye head, eyebrow head and midline of the template face. , , , All can be determined by template face. , , are the vertical coordinates of the eyes, eyebrows and top of the skull of the template face, , All can be determined by template face.

[0057] The face width boundary points, eyebrow tail, eye tail, eye head, eyebrow head and midline of the template face are as follows: Figure 4 As shown by the vertical lines from left to right, the eyes, eyebrows and top of the head are Figure 4 Indicated by the horizontal line from bottom to top. Figure 4 The middle green point is the control point of the template eyebrow.

[0058] In three-dimensional space, k1 includes not only k11 and k12, but also the vertical eyebrow distribution ratio k13. k13 can be represented by the vertical coordinates of the eyebrow tail, eyebrow middle and eyebrow head of the template face, for example , , , They are the vertical coordinates of the eyebrow tail, eyebrow middle and eyebrow beginning of the template face respectively.

[0059] Similarly, the eyebrow and eye distribution ratio k2 in the target face may be the distribution ratio of the eyebrow key points and the eye key points of the target face, and its calculation method is the same as the calculation method of the eyebrow and eye distribution ratio k1 in the template face.

[0060] For example, in the frontal face view, k2 may include a horizontal eyebrow and eye distribution ratio k21 and a vertical eyebrow and eye distribution ratio k22. k21 may be represented by the horizontal coordinates of the face width boundary points, eyebrow tail, eye tail, eye head, eyebrow head, and midline of the target face, for example , k22 can be represented by the vertical coordinates of the target face's eyes, eyebrows, and skull top, for example , , , , , , They are the horizontal coordinates of the face width boundary point, eyebrow tail, eye eye tail, eye head, eyebrow head and midline of the target face. , , , can be determined by the target face. , , are the vertical coordinates of the eyes, eyebrows and top of the skull of the target face, respectively. , All are determined by the target face.

[0061] In three-dimensional space, k2 includes not only k21 and k22, but also the vertical eyebrow distribution ratio k23. k23 can be represented by the vertical coordinates of the eyebrow tail, eyebrow middle and eyebrow head of the target face, for example , , , are the vertical coordinates of the eyebrow tail, eyebrow middle and eyebrow beginning of the target face, , All are determined by the target face.

[0062] The eyebrow distribution relationship, i.e., the relationship between k1 and k2, may include a horizontal eyebrow distribution relationship and a vertical eyebrow distribution relationship, and may also include a vertical eyebrow distribution relationship. For example, the horizontal eyebrow distribution relationship is , the vertical distribution relationship of eyebrows and eyes is , the vertical distribution relationship of eyebrows and eyes is , , , All of them are proportional coefficients greater than 0.

[0063] If the face shape relationship only includes the ratio relationship between the target face and the template face, the ratio relationship can be used to redirect the template eyebrows of the template face to obtain the target eyebrows of the target face. If the face shape relationship only includes the distribution relationship between the eyebrows and eyes of the target face and the template face, the eyebrows and eyes distribution relationship can be used to redirect the template eyebrows of the template face to obtain the target eyebrows of the target face. If the face shape relationship includes the ratio relationship between the target face and the template face and the eyebrows and eyes distribution relationship, the ratio relationship and the eyebrows and eyes distribution relationship can be used to redirect the template eyebrows of the template face to obtain the target eyebrows of the target face.

[0064] In the embodiment of the present invention, the specific content of the face shape relationship is enriched, and at least one of the proportion relationship and the eyebrow distribution relationship can be fully utilized to improve the orientation accuracy of the target eyebrow of the target face. In particular, when the proportion relationship and the eyebrow distribution relationship are used at the same time, the specific content of the face shape relationship can be further enriched, and the orientation accuracy of the target eyebrow of the target face can be further improved.

[0065] On the basis of the above embodiment, based on the proportion relationship and / or the distribution relationship of eyebrows and eyes, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, including: Based on the proportion relationship and / or the distribution relationship of the eyebrows and eyes, the position information of the first projection point of the control point of the template eyebrow in the frontal view is redirected to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view; Based on the position information of the second projection point, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0066] Specifically, when redirecting the template eyebrows of the template face, the control points of the template eyebrows can be projected in the frontal view to obtain a first projection point, and the position information of the first projection point is the two-dimensional coordinates of the first projection point in the frontal view.

[0067] Then, using the proportional relationship and / or the eyebrow distribution relationship, the position information of the control point of the template eyebrow at the first projection point in the frontal view is redirected to obtain the position information of the control point of the target eyebrow at the second projection point in the frontal view. Here, the position information of the second projection point is the two-dimensional coordinate of the second projection point in the frontal view, and the first projection point corresponds to the second projection point one by one. Using at least one of the proportional relationship and the eyebrow distribution relationship in the frontal view, the position information of the first projection point is redirected to obtain the position information of the second projection point.

[0068] Finally, the spatial position information of the control point of the target eyebrow on the target face is calculated using the position information of the second projection point. Since the position information of the second projection point is a two-dimensional coordinate, and the spatial position information of the control point of the target eyebrow on the target face is a three-dimensional coordinate, the process of calculating the spatial position information of the control point of the target eyebrow on the target face is essentially a process of converting the two-dimensional coordinate to the three-dimensional coordinate. Since the control point of the target eyebrow can include multiple points, the second projection point can also include multiple points, and then the position information of each second projection point can be used to determine the cell where each second projection point is located in the two-dimensional grid under the frontal view of the target face, and the centroid coordinates of the second projection point in the cell are calculated according to the vertex position of the cell.

[0069] It is understandable that each second projection point corresponds to a barycentric coordinate, which can also be called an area coordinate, which is a coordinate calculated with reference to the vertex position of the cell where the second projection point is located. In a two-dimensional grid, the vertex position of each cell is a two-dimensional coordinate.

[0070] After that, the centroid coordinates of each second projection point are applied to the face mesh of the target face, and the spatial position information of each control point of the target eyebrow on the target face can be obtained. Among them, the face mesh of the target face is a three-dimensional mesh, and the vertex position of each cell in the three-dimensional mesh is a three-dimensional coordinate. The cell where each second projection point is located in the two-dimensional mesh is consistent with the cell where the corresponding control point is located in the three-dimensional mesh.

[0071] Therefore, based on the centroid coordinates of each second projection point and the vertex position of the cell where the corresponding control point is located in the three-dimensional grid, the spatial position information of each control point of the target eyebrow on the target face can be calculated, that is, the centroid coordinates of each second projection point are multiplied by the vertex position of the cell where the corresponding control point is located in the three-dimensional grid to obtain the spatial position information of the corresponding control point on the target face.

[0072] like Figure 5As shown in the figure, the green points are the distribution of the control points of the eyebrows after migrating from the template face to the target face using the existing technology, and the red points are the control points of the target eyebrows in the embodiment of the present invention. Figure 5 It can be seen that the display effect of the target eyebrows formed by red dots on the target face is consistent with the display effect of the template eyebrows on the template face, while the display effect of the eyebrows formed by green dots on the target face is different from the display effect of the template eyebrows on the template face. Compared with the eyebrows formed by green dots, the target eyebrows formed by red dots maintain the display effect of the eyebrow shape and are more suitable for the face shape of the target face.

[0073] In an embodiment of the present invention, the redirection process of the template eyebrows is split into the redirection process of the position information of the projection point under the frontal view and the conversion process of the two-dimensional coordinates to the three-dimensional coordinates, which can simplify the difficulty of the redirection process of the template eyebrows and improve the processing efficiency.

[0074] Based on the above embodiment, the control points of the template eyebrow and the target eyebrow each include multiple; Based on the proportion relationship and the distribution relationship between eyebrows and eyes, the position information of the first projection point of the control point of the template eyebrow in the frontal view is redirected to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view, including: Based on the proportional relationship, the position information of the multiple first projection points is scaled, and based on the distribution relationship of the eyebrows and eyes, the position information of the multiple first projection points is translated to obtain the position information of the multiple second projection points.

[0075] Specifically, the template eyebrow and the target eyebrow control point may include multiple points. When the position information of the first projection point is redirected by using the proportional relationship and the eyebrow distribution relationship at the same time, the position information of the multiple first projection points can be scaled and translated by using the proportional relationship and the eyebrow distribution relationship respectively. Here, the order of scaling and translation can be performed as needed or simultaneously, which is not specifically limited here.

[0076] When scaling the position information of the plurality of first projection points using the proportional relationship, the intermediate position information of the plurality of first projection points may be determined first. The intermediate position information of the plurality of first projection points may be expressed as , and there are: in, is the horizontal coordinate of the middle position information of the first projection point t1, is the ordinate of the middle position information of the first projection point t1, They are respectively the position information of the 1st, 2nd, ..., t1th first projection points, and the position information is a two-dimensional coordinate vector. is the minimum value of the horizontal coordinates of the t1 first projection points, that is, the horizontal coordinate of the first edge point among the t1 first projection points, is the maximum value of the horizontal coordinates of the t1 first projection points, that is, the horizontal coordinate of the second edge point among the t1 first projection points, is the minimum value of the ordinate of the t1 first projection points, that is, the ordinate of the first edge point among the t1 first projection points, It is the maximum value of the ordinates of the t1 first projection points, that is, the ordinate of the second edge point among the t1 first projection points.

[0077] Understandably, Then, the position information of the plurality of first projection points is scaled using the intermediate position information and the proportional relationship. For example, there may be: in, and represents the position information of the i-th first projection point, which are the horizontal and vertical coordinates of the i-th first projection point, and represents the position information obtained after the position information of the i-th first projection point is scaled, and are respectively the abscissa and ordinate obtained after the position information of the i-th first projection point is scaled; For proportional relationship.

[0078] When performing translation processing on the position information of multiple first projection points by using the distribution relationship of eyebrows and eyes, the edge position information of multiple first projection points can be determined first. The edge position information can include the position information of the first edge point and the second edge point in each first projection point. The position information of the first edge point in each first projection point can be expressed as , the position information of the second edge point in each first projection point can be expressed as .

[0079] Then, the position information of the plurality of first projection points is translated using the edge position information and the eyebrow and eye distribution relationship information. Preferably, a proportional relationship can also be introduced during the translation process, so that the position information obtained after the translation process can be more accurate.

[0080] Finally, the position information obtained after the scaling and translation processing is the position information of the second projection point, and the redirection processing of the position information of the plurality of first projection points is completed.

[0081] In the embodiment of the present invention, the redirection process can be simplified, the processing difficulty can be reduced, and the processing efficiency can be improved through independent scaling processing and translation processing.

[0082] On the basis of the above embodiment, based on the distribution relationship of eyebrows and eyes, the position information of multiple first projection points is translated to obtain the position information of multiple second projection points, including: Based on the proportional relationship, determining a first association relationship between the position information of the plurality of first projection points and the position information of the plurality of second projection points; Based on the first association relationship and the distribution relationship of the eyebrows and eyes, the position information of the multiple first projection points is translated to obtain the position information of the multiple second projection points.

[0083] Specifically, when performing translation processing on the position information of the plurality of first projection points, the first association relationship between the position information of the plurality of first projection points and the position information of the plurality of second projection points may be determined by using a proportional relationship.

[0084] The first association relationship may include a horizontal association relationship and a vertical association relationship. The horizontal association relationship may include a first mapping relationship between the horizontal coordinate of a first edge point among multiple first projection points and the horizontal coordinate of the first edge point among multiple second projection points, and a second mapping relationship between the horizontal coordinate of a second edge point among multiple first projection points and the horizontal coordinate of a second edge point among multiple second projection points.

[0085] The first mapping relationship can be expressed as: The second mapping relationship can be expressed as: in, is the horizontal coordinate of the first edge point among the t1 second projection points, is the horizontal coordinate of the second edge point among the t1 second projection points, is the lateral translation distance.

[0086] Understandably, The longitudinal association relationship may be a third association relationship between the intermediate position information of the plurality of first projection points and the intermediate position information of the plurality of second projection points. The third association relationship may be expressed as: in, is the ordinate of the middle position information of the t1 second projection point, is the longitudinal translation distance. It can be understood that .

[0087] Afterwards, the first correlation relationship and the eyebrow distribution relationship are used to translate the position information of each first projection point to obtain the position information of each second projection point. In the vertical direction, the vertical distribution relationship of eyebrows and eyes can be used to solve the vertical correlation relationship. To solve.

[0088] Finally, the solution is and After that, you can follow By translating each first projection point horizontally, the horizontal coordinates of each second projection point can be obtained. By performing a longitudinal translation on each first projection point, the longitudinal coordinate of each second projection point can be obtained, thereby obtaining the position information of each second projection point.

[0089] In the embodiment of the present invention, the position information of the plurality of first projection points is translated together through the proportional relationship and the distribution relationship of the eyebrows and eyes, so that the translation distance can be quickly determined, and then the translation is performed according to the translation distance.

[0090] On the basis of the above embodiment, based on the proportion relationship and / or the distribution relationship of eyebrows and eyes, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, and further comprising: Sampling the control points of the template eyebrows to obtain sampling points of the template eyebrows, and establishing a second association relationship between the control points of the template eyebrows and the sampling points; Based on the proportion relationship and / or the distribution relationship of the eyebrows and eyes, redirect the position information of the third projection point of the sampling point in the frontal face view to obtain the position information of the fourth projection point of the sampling point in the frontal face view; Based on the position information of the fourth projection point and the second association relationship, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0091] Specifically, in the process of redirecting the template eyebrows of the template face, the control points of the template eyebrows need to be processed. Since the number of control points of the template eyebrows is huge, the amount of data processing in the redirection process will be too large, increasing the system burden. Based on this, in order to reduce the amount of data processing in the redirection process, the control points of the template eyebrows can be sampled to obtain the sampling points of the template eyebrows. One implementation method of sampling can be to select the root node and the end node as sampling points from all control points corresponding to each template eyebrow. Another implementation method can be to sample all control points corresponding to each template eyebrow using the farthest point sampling (FPS) method. In addition, other common sampling methods can also be used, which are not limited in the embodiments of the present invention.

[0092] It can be understood that farthest point sampling is a commonly used sampling algorithm, and the core idea is to make the distance between all sampling points as far as possible, that is, the sampling points are as discrete and uniform as possible.

[0093] Through the above sampling process, all sampling point combinations of all template eyebrows can be obtained. .like Figure 6 As shown, the green points are all control points and the red points are sampling points.

[0094] After that, a second association relationship between the control points and the sampling points of the template eyebrows can be established. In this case, all control points and all sampling points can be projected respectively under the camera perspective corresponding to the frontal view, so as to obtain the first projection point set of all control points on the two-dimensional plane under the frontal view. And the third projection point set of all sampling points on the two-dimensional plane under the frontal view .

[0095] The distance from the first projection point of each control point to the third projection point of the surrounding sampling points is calculated in the two-dimensional plane, and the binding weight is determined based on the distance to construct a sparse binding weight matrix , the sparse binding weight matrix The binding weight matrix is ​​composed of binding weights. The value of the binding weight is negatively correlated with the distance, that is, the smaller the distance, the larger the value of the binding weight. In other words, the closer the distance is, the closer the relationship between the sampling point and the control point is. In the embodiment of the present invention, the sparse binding weight matrix Indicates the second association relationship.

[0096] Specifically, the set of two-dimensional coordinate vectors of t1 first projection points can be expressed as: ; The two-dimensional coordinate vector set of t2 third projection points can be expressed as: .

[0097] Therefore, the sparse binding weight matrix W obtained by determining the binding weight based on the distance between each first projection point and each third projection point can be expressed as: in, Indicates The third projection point of the sampling point and the The binding weights between the first projection points of the control points.

[0098] Through projection processing, each control point can be bound to the surrounding sampling points based on the distance between each control point and the projection point of the surrounding sampling points, so as to facilitate the subsequent determination of the control point using the sampling points.

[0099] Afterwards, the position information of the third projection point of the sampling point in the frontal view can be redirected by using the proportional relationship and / or the distribution relationship of the eyebrows and eyes, so as to obtain the position information of the fourth projection point of the sampling point in the frontal view. It can be understood that the process of redirecting the position information of the third projection point is exactly the same as the process of redirecting the position information of the first projection point in the above embodiment. The only difference is that the redirection process here can greatly reduce the amount of processed data because the object of processing is the third projection point of the sampling point. The position information of all the fourth projection points obtained by the redirection process can be expressed as , is the two-dimensional coordinate of the fourth projection point in the frontal view of the target face.

[0100] Finally, the spatial position information of the control point of the target eyebrow on the target face is calculated using the position information of the fourth projection point obtained by the redirection process and the second association relationship. Here, since the position information of the fourth projection point is a two-dimensional coordinate, and the spatial position information of the control point of the target eyebrow on the target face is a three-dimensional coordinate, it is necessary to determine the spatial position information of the sampling point on the target face according to the position information of the fourth projection point, and then combine the second association relationship to calculate the spatial position information of the control point of the target eyebrow on the target face. The direction of the target eyebrow of the target face can be controlled by the control point of the target eyebrow, that is, the target eyebrow of the target face is obtained.

[0101] In the embodiment of the present invention, the target eyebrow of the target face is converted into the spatial position information of the control point of calculating the target eyebrow on the target face, so that the target eyebrow can be calculated quickly and the efficiency of the eyebrow redirection processing is improved.

[0102] On the basis of the above embodiment, the number of sampling points is multiple; based on the position information of the fourth projection point and the second association relationship, calculating the spatial position information of the control point of the target eyebrow on the target face includes: Based on the position information of each fourth projection point, calculate the centroid coordinates of the plurality of fourth projection points, and apply the centroid coordinates to the face grid of the target face to obtain the spatial position information of the plurality of sampling points on the target face; Based on the second association relationship, the spatial position information of multiple sampling points on the template face, the spatial position information of multiple sampling points on the target face, and the spatial position information of the control point of the template eyebrow, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0103] Specifically, in the embodiment of the present invention, the number of sampling points can be multiple. Further, when calculating the spatial position information of the control point of the target eyebrow on the target face, the position information of each fourth projection point is first used to calculate the centroid coordinates of the multiple fourth projection points. Then, the centroid coordinates are applied to the face grid of the target face to obtain the spatial position information of the multiple sampling points on the target face.

[0104] Thereafter, the spatial position information of the control point of the target eyebrow on the target face is calculated by using the second association relationship, the spatial position information of the multiple sampling points on the template face, the spatial position information of the multiple sampling points on the target face, and the spatial position information of the control point of the template eyebrow. That is, in, is the control point set of all target eyebrows on the target face, is the control point set of all template eyebrows on the template face, is the three-dimensional coordinate of each sampling point on the target face, is the three-dimensional coordinate of each sampling point on the template face, and W is the sparse binding weight matrix, which represents the second association relationship.

[0105] Thus, the redirection process of the sampling points is transferred to the control points, and the same redirection process is performed on the control points of all template eyebrows.

[0106] Based on the above description, it can be known that eyebrows are a kind of B-spline curve. Each template eyebrow is determined by several control points. The curve shape of the template eyebrow can be determined based on these control points. After redirecting the control points of all template eyebrows, all template eyebrows are redirected.

[0107] Based on the above embodiment, the proportional relationship is determined based on the ratio of eye lengths between the target face and the template face, and / or the ratio of face widths.

[0108] Specifically, the proportional relationship can be determined by at least one of the eye length ratio and the face width ratio between the target face and the template face, that is, the proportional relationship can be determined only by the eye length ratio, for example, the eye length ratio can be used as the proportional relationship, or it can be determined only by the face width ratio, for example, the face width ratio is used as the proportional relationship, or it can be determined by both the eye length ratio and the face width ratio, for example, the weighted sum of the eye length ratio and the face width ratio is used as the proportional relationship.

[0109] It is understandable that the eye length ratio It can be obtained by calculating the ratio of the width of the eye head and eye tail of a single eye on the target face to the width of the eye head and eye tail of the eye at the corresponding position on the template face, and then taking the average of the ratio of the two eyes. It can be obtained by calculating the ratio of the face width of the target face to the face width of the template face.

[0110] In particular, the eye length ratio Proportion to face width Take the average and get the proportional relationship At this time, the eye length ratio Proportion to face width The weights are all 0.5.

[0111] On the basis of the above embodiment, the eyebrow and eye distribution relationship includes that the eyebrow and eye distribution ratios of the target face and the template face are the same.

[0112] Specifically, the distribution ratio of the eyebrows and eyes of the target face is set to be the same as that of the template face, so that the target eyebrows obtained by the redirection processing can be consistent with the eyebrow shape of the template eyebrows, and the display effect of the target eyebrows and the template eyebrows can be consistent.

[0113] On the basis of the above embodiment, based on the face shape relationship between the target face and the template face, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, and then the following steps are included: Determine the template curvature of each curve segment in the template eyebrow; Based on the template curvature, the target curvature of each curve segment in the target eyebrow is corrected.

[0114] Specifically, due to the redirection processing, the relative positions between different control points of the target eyebrow have changed compared to the relative positions between different control points of the template eyebrow, which will cause the target eyebrow determined based on the control points to be distorted, so the target eyebrow also needs to be smoothed.

[0115] In the embodiment of the present invention, for other control points except the root node and the end node, the curvature of each control point can be constrained in stages to be consistent with the control points in the template face, so that the curvature of the entire target eyebrow remains unchanged.

[0116] like Figure 7 As shown, the stage constraint can be to determine the template curvature of each curve segment in the template eyebrow, and each curve segment can be every three adjacent control points, namely control point 1, control point 2 and control point 3. The template curvature of each curve segment can be represented by a vector from control point 2 to the midpoint of control point 1 and control point 3.

[0117] Afterwards, the target curvature of each curve segment in the target eyebrow is corrected using the template curvature of each curve segment in the target eyebrow, that is, the template curvature of each curve segment in the target eyebrow is made equal to the template curvature of the corresponding curve segment in the template eyebrow by adjusting the spatial position information of the control point in each curve segment in the target eyebrow.

[0118] On the basis of the above embodiment, based on the face shape relationship between the target face and the template face, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face, and then the following steps are further included: Deforming the eyebrow region of the texture map of the template face to obtain an eyebrow texture map that matches the target eyebrow; Apply the eyebrow texture map to the target face.

[0119] Specifically, in order to make the target eyebrows more realistic in visual effect, the target eyebrow area of ​​the target face will be texture mapped, that is, the target eyebrow area will be colored using an eyebrow texture map adapted to the target eyebrows, making it visually close to a real person.

[0120] Since all template eyebrows are redirected in the embodiment of the present invention, the eyebrow region of the texture map of the template face also needs to be redirected accordingly. The process firstly deforms the eyebrow region of the texture map of the template face to obtain an eyebrow texture map that matches the target eyebrows. Figure 8 As shown, the two-dimensional texture coordinates corresponding to all sampling points in the texture map of the template face are determined, and the eyebrow area of ​​the texture map is triangulated. According to the changes in the two-dimensional texture coordinates corresponding to the sampling points before and after redirection, the eyebrow area of ​​the texture map of the template face is deformed to obtain an eyebrow texture map that matches the target eyebrows.

[0121] Thereafter, the eyebrow texture map is applied to the target face, and the redirection processing of the eyebrow region of the texture map of the template face is completed, so as to obtain the target eyebrow with texture on the target face.

[0122] It can be understood that the virtual human eyebrow redirection method in the embodiment of the present invention can be applied to the redirection of various template eyebrow shapes. Fig. 9 This is a schematic diagram of the redirection effect of the virtual human eyebrow redirection method in an embodiment of the present invention applied to short flat eyebrows and long flat eyebrows. The left side shows the template eyebrows of short flat eyebrows and long flat eyebrows on the template face, and the right side shows the target eyebrows of short flat eyebrows and long flat eyebrows on five different target faces.

[0123] from Fig. 9 It can be seen that the virtual human eyebrow redirection method provided in the embodiment of the present invention can be applied to the migration of short flat eyebrows and long flat eyebrows, and can make the eyebrow shape maintain the same display effect as the template face on the target face with different face shapes.

[0124] like Fig.10 As shown, based on the above embodiment, a virtual human eyebrow redirection device is provided in an embodiment of the present invention, comprising: The template face acquisition module 101 is used to acquire a template face corresponding to the target face; The eyebrow redirection module 102 is used to redirect the template eyebrows of the template face based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face.

[0125] Based on the above embodiment, the face shape relationship includes the ratio relationship between the target face and the template face, and / or the distribution relationship of the eyebrows and eyes.

[0126] Based on the above embodiment, the eyebrow redirection module is specifically used for: Based on the proportion relationship and / or the distribution relationship of the eyebrows and eyes, the position information of the first projection point of the control point of the template eyebrow in the frontal view is redirected to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view; Based on the position information of the second projection point, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0127] Based on the above embodiment, the template eyebrow and the target eyebrow each include multiple control points; the eyebrow redirection module is further specifically used for: Based on the proportional relationship, the position information of the multiple first projection points is scaled, and based on the distribution relationship of the eyebrows and eyes, the position information of the multiple first projection points is translated to obtain the position information of the multiple second projection points.

[0128] Based on the above embodiment, the eyebrow redirection module is further specifically used for: Based on the proportional relationship, determining a first association relationship between the position information of the plurality of first projection points and the position information of the plurality of second projection points; Based on the first association relationship and the distribution relationship of the eyebrows and eyes, the position information of the multiple first projection points is translated to obtain the position information of the multiple second projection points.

[0129] Based on the above embodiment, the eyebrow redirection module is further specifically used for: Sampling the control points of the template eyebrows to obtain sampling points of the template eyebrows, and establishing a second association relationship between the control points of the template eyebrows and the sampling points; Based on the proportion relationship and / or the distribution relationship of the eyebrows and eyes, redirect the position information of the third projection point of the sampling point in the frontal face view to obtain the position information of the fourth projection point of the sampling point in the frontal face view; Based on the position information of the fourth projection point and the second association relationship, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0130] Based on the above embodiment, the number of sampling points is multiple; The Eyebrow Redirection Module is also specifically used to: Based on the position information of each fourth projection point, calculate the centroid coordinates of the plurality of fourth projection points, and apply the centroid coordinates to the face grid of the target face to obtain the spatial position information of the plurality of sampling points on the target face; Based on the second association relationship, the spatial position information of multiple sampling points on the template face, the spatial position information of multiple sampling points on the target face, and the spatial position information of the control point of the template eyebrow, the spatial position information of the control point of the target eyebrow on the target face is calculated.

[0131] Based on the above embodiment, the proportional relationship is determined based on the ratio of eye lengths between the target face and the template face, and / or the ratio of face widths.

[0132] On the basis of the above embodiment, the eyebrow and eye distribution relationship includes that the eyebrow and eye distribution ratios of the target face and the template face are the same.

[0133] Based on the above embodiment, a smoothing module is further included, which is used for: Determine the template curvature of each curve segment in the template eyebrow; Based on the template curvature, the target curvature of each curve segment in the target eyebrow is corrected.

[0134] Based on the above embodiment, a texture mapping module is further included, which is used for: Deforming the eyebrow region of the texture map of the template face to obtain an eyebrow texture map that matches the target eyebrow; Apply the eyebrow texture map to the target face.

[0135] Specifically, the functions of each module in the virtual human eyebrow redirection device provided in the embodiment of the present invention correspond one-to-one to the operation process of each step in the above method embodiment, and the effects achieved are also consistent. Please refer to the above embodiment for details, and no further details will be given in the embodiment of the present invention.

[0136] Fig.11 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.11 As shown, the electronic device may include: a processor 110, a communication interface 120, a memory 130 and a communication bus 140, wherein the processor 110, the communication interface 120 and the memory 130 communicate with each other through the communication bus 140. The processor 110 may call the logic instructions in the memory 130 to execute the virtual human eyebrow redirection method provided in the above embodiments.

[0137] In addition, the logic instructions in the above-mentioned memory 130 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the relevant technology or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0138] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the virtual human eyebrow redirection method provided in the above embodiments.

[0139] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to execute the virtual human eyebrow redirection method provided in the above embodiments.

[0140] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for redirecting virtual human eyebrows, characterized in that: include: Obtain a template face corresponding to the target face; Based on the face shape relationship between the target face and the template face, the template eyebrows of the template face are redirected to obtain the target eyebrows of the target face.

2. The virtual human eyebrow redirection method according to claim 1, characterized in that: The face shape relationship includes the ratio relationship between the target face and the template face, and / or the distribution relationship of eyebrows and eyes.

3. The virtual human eyebrow redirection method according to claim 2, characterized in that: Based on the proportion relationship and / or the eyebrow and eye distribution relationship, redirecting the template eyebrows of the template face to obtain target eyebrows of the target face includes: Based on the proportional relationship and / or the eyebrow and eye distribution relationship, redirect the position information of the first projection point of the control point of the template eyebrow in the frontal view to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view; Based on the position information of the second projection point, the spatial position information of the control point of the target eyebrow on the target face is calculated.

4. The virtual human eyebrow redirection method according to claim 3, characterized in that: The template eyebrow and the target eyebrow each include a plurality of control points; Based on the proportional relationship and the eyebrow and eye distribution relationship, the position information of the first projection point of the control point of the template eyebrow in the frontal view is redirected to obtain the position information of the second projection point of the control point of the target eyebrow in the frontal view, including: Based on the proportional relationship, the position information of the plurality of first projection points is scaled, and based on the eyebrow and eyebrows distribution relationship, the position information of the plurality of first projection points is translated to obtain the position information of the plurality of second projection points.

5. The virtual human eyebrow redirection method according to claim 4, characterized in that: The step of performing translation processing on the position information of the plurality of first projection points based on the distribution relationship of the eyebrows and eyes to obtain the position information of the plurality of second projection points includes: Based on the proportional relationship, determining a first association relationship between the position information of the plurality of first projection points and the position information of the plurality of second projection points; Based on the first association relationship and the eyebrow and eye distribution relationship, the position information of the plurality of first projection points is translated to obtain the position information of the plurality of second projection points.

6. The virtual human eyebrow redirection method according to claim 2, characterized in that: Based on the proportion relationship and / or the eyebrow and eye distribution relationship, redirecting the template eyebrows of the template face to obtain the target eyebrows of the target face, further comprising: Sampling the control points of the template eyebrow to obtain the sampling points of the template eyebrow, and establishing a second association relationship between the control points of the template eyebrow and the sampling points; Based on the proportion relationship and / or the eyebrow distribution relationship, redirect the position information of the third projection point of the sampling point in the frontal face view to obtain the position information of the fourth projection point of the sampling point in the frontal face view; Based on the position information of the fourth projection point and the second association relationship, the spatial position information of the control point of the target eyebrow on the target face is calculated.

7. The virtual human eyebrow redirection method according to claim 6, characterized in that: The number of the sampling points is multiple; the calculating the spatial position information of the control point of the target eyebrow on the target face based on the position information of the fourth projection point and the second association relationship includes: Based on the position information of each of the fourth projection points, calculate the centroid coordinates of the plurality of the fourth projection points, and apply the centroid coordinates to the face grid of the target face to obtain the spatial position information of the plurality of sampling points on the target face; Based on the second association relationship, the spatial position information of multiple sampling points on the template face, the spatial position information of multiple sampling points on the target face, and the spatial position information of the control points of the template eyebrows, the spatial position information of the control points of the target eyebrows on the target face is calculated.

8. The virtual human eyebrow redirection method according to claim 2, characterized in that: The proportional relationship is determined based on the ratio of eye lengths of the target face to the template face, and / or the ratio of face widths.

9. The virtual human eyebrow redirection method according to claim 2, characterized in that: The eyebrow and eye distribution relationship includes that the eyebrow and eye distribution ratio of the target face and the template face is the same.

10. The virtual human eyebrow redirection method according to any one of claims 1 to 9, characterized in that: The step of redirecting the template eyebrows of the template face based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face comprises: Determining the template curvature of each curve segment in the template eyebrow; Based on the template curvature, the target curvature of each curve segment in the target eyebrow is corrected.

11. The virtual human eyebrow redirection method according to any one of claims 1 to 9, characterized in that: The step of redirecting the template eyebrows of the template face based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face further includes: Performing deformation processing on the eyebrow region of the texture map of the template face to obtain an eyebrow texture map adapted to the target eyebrow; Apply the eyebrow texture map to the target face.

12. A virtual human eyebrow redirection device, characterized in that: include: A template face acquisition module is used to acquire a template face corresponding to a target face; The eyebrow redirection module is used to redirect the template eyebrows of the template face based on the face shape relationship between the target face and the template face to obtain the target eyebrows of the target face.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the virtual human eyebrow redirection method as described in any one of claims 1-11 is implemented.

14. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the virtual human eyebrow redirection method according to any one of claims 1 to 11 is implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the virtual human eyebrow redirection method according to any one of claims 1 to 11 is implemented.

Images