Three-dimensional face rejuvenation processing method and system and electronic equipment

Abstract

The invention is suitable for the field of computer image processing, and provides a three-dimensional face rejuvenation processing method and system and electronic equipment, and the method comprises the steps: obtaining rejuvenation region information and rejuvenation processing intensity; determining at least one second vertex corresponding to the aging feature from a plurality of first vertexes in a target area, and determining at least one deformation interpolation point in the target area based on the second vertex; on the basis of the rejuvenation processing intensity and the facial biomechanical constraint, respectively determining the updating positions of the second vertexes and the deformation interpolation points required for rejuvenation processing of the aging features; and respectively adjusting each second vertex and each deformation interpolation point to the corresponding updating position to obtain the updated three-dimensional face model. According to the scheme, the three-dimensional face model after rejuvenation processing is objectively established based on the biological parameters, and the three-dimensional face model can provide more rejuvenation face details.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of computer image processing, and particularly relates to a three-dimensional face rejuvenation processing method and system and an electronic device. BACKGROUND

[0002] Facial rejuvenation is a core demand in the field of medical cosmetology. Intervention means such as photoelectric devices, injection filling, and surgery are usually used to combat facial aging and achieve facial rejuvenation. Before facial rejuvenation, the facial rejuvenation effect needs to be predicted. The current facial rejuvenation effect is manually drawn by doctors according to experience and displayed in two-dimensional images, which is not objective and easy to lose facial details. SUMMARY

[0003] The embodiments of the present application provide a three-dimensional face rejuvenation processing method, system and electronic device to solve the problem that the facial rejuvenation effect in the prior art is manually drawn by doctors according to experience and displayed in two-dimensional images, which is not objective and easy to lose facial details.

[0004] The first aspect of the embodiments of the present application provides a three-dimensional face rejuvenation processing method, comprising: obtaining rejuvenation area information and rejuvenation processing intensity; the rejuvenation area information corresponds to a target area to be rejuvenated in a three-dimensional face model, and the target area includes a plurality of first vertices; determining at least one second vertex corresponding to an aging feature from the plurality of first vertices in the target area, and determining at least one deformation interpolation point in the target area based on the second vertex; determining the update positions of each second vertex and each deformation interpolation point required for rejuvenation processing of the aging feature based on the rejuvenation processing intensity and facial biomechanics constraints; adjusting each second vertex and each deformation interpolation point to the corresponding update position respectively to obtain an updated three-dimensional face model.

[0005] The second aspect of the embodiments of the present application provides a three-dimensional face rejuvenation processing system, comprising: an obtaining module configured to obtain rejuvenation area information and rejuvenation processing intensity; the rejuvenation area information corresponds to a target area to be rejuvenated in a three-dimensional face model, and the target area includes a plurality of first vertices; a first determining module configured to determine at least one second vertex corresponding to an aging feature from the plurality of first vertices in the target area, and determine at least one deformation interpolation point in the target area based on the second vertex; a second determining module configured to determine, based on the aging treatment intensity and the facial biomechanics constraint, updated positions of each of the second vertices and each of the morphing interpolation points respectively for the aging features to be treated with the aging treatment; an adjusting module configured to adjust each of the second vertices and each of the morphing interpolation points to the corresponding updated position respectively to obtain an updated three-dimensional face model.

[0006] A third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to the first aspect when executing the computer program.

[0007] A fourth aspect of the embodiments of the present application provides a computer program product, including a computer program, and the computer program implements the steps of the method according to the first aspect when executed by a processor.

[0008] A fifth aspect of the embodiments of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program implements the steps of the method according to the first aspect when executed by a processor.

[0009] As can be seen from the above, based on the aging area information, the aging treatment intensity and the facial biomechanics constraint, the embodiments of the present application accurately calculate the displacement amount, i.e., the updated position, of each of the second vertices and each of the morphing interpolation points in the target area to be treated with the aging treatment, and obtain an updated three-dimensional face model by adjusting the positions of the second vertices and the morphing interpolation points, thereby realizing the aging treatment of the aging features in the target area of the three-dimensional face model. The position adjustment process converts the aging prediction from relying on the doctor's experience to drawing a two-dimensional image to an objective three-dimensional modeling process based on biological parameters, promotes the transformation of facial aging prediction from experience-driven to data-driven, and intuitively displays more aging facial details through the updated three-dimensional face model. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0011] Figure 1 is a flow of a three-dimensional face aging treatment method provided by the embodiments of the present application Figure 1 ; Figure 2is a flow of a three-dimensional face rejuvenation processing method provided by an embodiment of the present application Figure 2 ; Figure 3 is a three-dimensional face gray model schematic diagram before and after rejuvenation processing provided by an embodiment of the present application Figure 4 is a three-dimensional face gray model schematic diagram before and after rejuvenation processing provided by an embodiment of the present application Figure 5 is a structure diagram of a three-dimensional face rejuvenation processing system provided by an embodiment of the present application Figure 6 is a structure diagram of an electronic device provided by an embodiment of the present application DETAILED DESCRIPTION

[0012] In the following description, for the purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0013] It should be understood that the term “comprises / comprising” when used in this specification and the appended claims indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0014] It should also be understood that the terms used in the specification and the appended claims are intended to describe particular embodiments and do not intend to limit the present application. As used in the specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0015] It should further be understood that the term “and / or” used in the specification and the appended claims means one or more of the associated listed items as well as all possible combinations of the items and includes the combinations.

[0016] As used in the specification and the appended claims, the term "if' can be interpreted as meaning "when," or "upon," or "in response to determining," or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [the recited condition or event] is detected" can be interpreted as meaning "upon determining" or "in response to determining" or "upon detecting [the recited condition or event]" or "in response to detecting [the recited condition or event]" depending on the context.

[0017] In particular implementations, the terminals described in the embodiments of the present application include, but are not limited to, other portable devices such as mobile telephones, laptop computers, or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and / or touch pads). It should also be understood that, in some embodiments, the device is not a portable communication device, but is a desktop computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0018] In the following discussion, a terminal that includes a display and a touch-sensitive surface is described. It should be understood, however, that a terminal can include one or more other physical user-interface devices, such as a physical keyboard, a mouse and / or a joystick.

[0019] The terminal supports a variety of applications, such as one or more of the following: a drawing application, a presentation application, a word processing application, a website creation application, a disk authoring application, a spreadsheet application, a game application, a telephone application, a video conferencing application, an e-mail application, an instant messaging application, a workout support application, a photo management application, a digital camera application, a digital camcorder application, a web browsing application, a digital music player application, and / or a digital video player application.

[0020] The various applications that can be executed on the terminal can use at least one common physical user-interface device, such as the touch-sensitive surface. One or more functions of the touch-sensitive surface, as well as the display of information on the terminal, can be adjusted and / or changed in accordance with the application that is being executed by the terminal. In this way, the user experiences a consistent user interface when switching between various applications that are executed on the terminal.

[0021] It should be understood that the sequence of the steps in the embodiments of the present application does not mean the order of execution, the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0022] In order to illustrate the technical solutions described in the present application, the following will be described by specific embodiments. In order to illustrate the technical solutions described in the present application, the following will be described by specific embodiments.

[0023] See Figure 1 , Figure 1 This is a flowchart of a three-dimensional face rejuvenation method provided in the embodiments of this application. Figure 1 .like Figure 1 As shown, a three-dimensional face rejuvenation method includes the following steps: Step 101: Obtain the rejuvenation region information and rejuvenation processing intensity; the rejuvenation region information corresponds to the target region to be rejuvenationd in the three-dimensional face model, and the target region includes multiple first vertices.

[0024] A 3D face model is a three-dimensional geometric structure of a face constructed using digital technology. It consists of vertices and a mesh and is used to accurately describe the contours of the face.

[0025] In some embodiments, surface geometric data of a human face are acquired using image acquisition devices such as depth cameras, 3D laser scanners, and 3D structured light scanners to obtain a 3D point cloud constituting the face. Triangulation methods such as Delaunay triangulation or Poisson surface reconstruction algorithms are then used to triangulate the 3D point cloud to obtain a 3D face model.

[0026] The rejuvenation region information is used to precisely define the target region in a 3D face model that needs rejuvenation processing and its spatial attributes. The target region can be part or all of the 3D face model, depending on the user's region selection. The target region contains multiple vertices; here, the vertex in the target region is defined as the first vertex.

[0027] The spatial attributes of the target region include the spatial extent of the target region, the location of the center point of the region, the location of each first vertex in the target region, and biometric information.

[0028] Any point in a 3D face model can be represented using 3D coordinates. Accordingly, the spatial extent of the target region within the 3D face model, the position of its center point, and the position of its first vertex can all be represented using 3D coordinates.

[0029] The rejuvenation intensity is a quantitative parameter that controls the degree of deformation in the target area and is used to achieve displacement mapping of the target area.

[0030] In some embodiments, the rejuvenation intensity takes values ​​in the range [0,1].

[0031] By acquiring information on the rejuvenation region and the rejuvenation processing intensity, the location and biometric information of the target region to be rejuvenationd in the 3D face model are clarified, enabling precise localization of the region and accurate determination of the aging state, so as to carry out targeted rejuvenation processing on the target region according to the rejuvenation processing intensity.

[0032] In some embodiments, the obtaining of the rejuvenation region information and the rejuvenation processing intensity comprises: determining the target region selected by the user in the three-dimensional face model based on the region selection operation instruction of the user, and determining the center point position of the region center point of the target region accordingly to obtain the rejuvenation region information; and obtaining the real-time processing intensity as the rejuvenation processing intensity corresponding to the target region.

[0033] In some embodiments, an interactive interface is provided for the user to display the three-dimensional face model. The user refers to an individual who operates the product corresponding to the method of the present application, such as a medical staff.

[0034] The interactive interface is provided with various region selection controls (such as a rectangular selection box, a lasso tool, a brush tool, and a laser cursor tool), and the user can select different region selection controls to freely adjust the region selection range through the region selection controls to select a local region or a global region for rejuvenation processing. The present application also supports region selection undo and reselection functions, and has strong flexibility.

[0035] The user clicks, frames, or draws a closed region on the three-dimensional face model displayed on the interactive interface by means of a mouse, an interactive handle, a touch screen, or the like to select a target region to be rejuvenated, and generates a region selection operation instruction according to the region selection operation of the user.

[0036] In some embodiments, when the user selects a region, the selected region is rendered in real time with a highlighted grid to ensure operation visibility.

[0037] Based on the region selection operation instruction, a target region located in the three-dimensional face model is determined, that is, the spatial range (geometric boundary) of the target region is determined. The target region can cover a circular shape, a square shape, and an irregular geometric body of a free form, and includes both planar polygons and non-planar curved surfaces.

[0038] In some embodiments, based on the three-dimensional coordinates of all region points in the target region, the center point position of the region center point in the target region is calculated through a geometric centroid formula, and the center point position is represented by three-dimensional coordinates . The center point position is updated in real time as the user selects, and serves as a reference origin point for subsequent position calculation.

[0039] In some embodiments, the user controls the intensity of the rejuvenation deformation by means of a mouse, a keyboard, a touch screen, or the like through the methods of sliding an intensity slider, rotating an intensity knob, or inputting a numerical value, that is, flexibly sets the rejuvenation processing intensity.

[0040] After the user determines the target region, the real-time processing intensity is obtained as the rejuvenation processing intensity corresponding to the target region. The rejuvenation processing intensity can be the latest intensity value set by the user, and if the user does not set it, the default intensity value is set.

[0041] By the interactive selection control and the real-time intensity adjustment mechanism, the user's intention is converted into the rejuvenation area information and the rejuvenation processing intensity, which are the deformation control parameters, and the rejuvenation processing is performed according to the user's intention to meet the user's demand.

[0042] In some embodiments, to achieve targeted rejuvenation processing, it is also necessary to determine which positions in the three-dimensional face model have aging features, that is, before the rejuvenation area information and the rejuvenation processing intensity are obtained, the method further includes: performing aging detection on the three-dimensional face model to obtain aging feature quantization parameters of each vertex in the three-dimensional face model; the aging feature quantization parameters are recess defect indication values, sag defect indication values or normal values, and the aging feature quantization parameters are used to determine the second vertex; each aging feature quantization parameter is stored as a custom attribute field of the corresponding vertex in the three-dimensional face model; any second vertex in the three-dimensional face model has the recess defect indication value or the sag defect indication value.

[0043] This step realizes the parameterized description of the vertices in the three-dimensional face model through vertex-level aging feature quantization and custom attribute field storage.

[0044] Aging detection refers to analyzing the geometric features of the three-dimensional face model, detecting the aging features of each vertex, that is, whether there are recess defects and sag defects, and then obtaining the biometric information of each vertex, that is, the aging feature quantization parameters. Here, aging feature is a relative concept, which refers to whether there is an aging feature and how severe the aging is relative to the reference model.

[0045] In some embodiments, a three-dimensional face reference model is obtained, the feature point geometric configuration formed by the set facial feature points of the three-dimensional face reference model is the same as the feature point geometric configuration formed by the set facial feature points of the three-dimensional face model, the topological connection relationship between the vertices of the three-dimensional face reference model is the same as the topological connection relationship between the vertices of the three-dimensional face model, and accordingly, a one-to-one vertex mapping relationship between a plurality of vertices of the two models is established based on the same feature point geometric configuration and topological connection relationship. The projection difference between the vertices with vertex mapping relationship is calculated to determine the aging state of each vertex. Among them, the set facial feature points are fixed marker points on the face with stable structure, such as bony landmarks (such as zygomatic tubercle, gonial angle) and muscle attachment points (such as eye corner, mouth corner), which maintain relative spatial stability in expression changes and slight displacement, which helps to realize spatial registration and deformation quantization. In some embodiments, one vertex corresponds to only one state, i.e. there is a sagging defect, there is a drooping defect, or there is no sagging defect and no drooping defect. Accordingly, the aging feature quantification parameter of each vertex is a sagging defect indicator value, a drooping defect indicator value, or a normal value. The sagging defect indicator value is represented by a negative value, the negative sign indicates sagging, and the numerical value after the negative sign represents the sagging characterization, the larger the numerical value, the deeper the sagging, for example, represented as -0.80. The drooping defect indicator value is represented by a positive value, the positive sign indicates drooping, and the numerical value after the positive sign represents the drooping characterization, the larger the numerical value, the more significant the drooping, for example, represented as +1.45. The normal value identifies a region without significant aging features, i.e. there is no sagging defect and no drooping defect, and is usually assigned a value of 0. It should be noted that the normal value is assigned a value of 0 here, and in actual application, the aging characterization value corresponding to the normal value is actually a numerical interval.

[0046] The custom attribute field is a dedicated data storage unit extended for each vertex, used to store its aging feature quantification parameter.

[0047] Each aging feature quantification parameter is stored as a custom attribute field of the corresponding vertex in the three-dimensional face model. When the user operates the control, the corresponding aging feature quantification parameter of the vertex is displayed at the vertex, and the user can select the target area according to the hovering display, and efficiently achieve the rejuvenation treatment.

[0048] According to the aging feature quantification parameter, the second vertex to be rejuvenated in the target area can be determined, and the corresponding content of step 102 can be referred to. The second vertex is the vertex to be rejuvenated, and the second vertex has a sagging defect indicator value or a drooping defect indicator value, i.e. the second vertex has a sagging defect or a drooping defect.

[0049] Step 102: determining at least one second vertex corresponding to the aging feature from the plurality of first vertices in the target area, and determining at least one morphing interpolation point in the target area based on the second vertex.

[0050] This step screens out the second vertex with aging features, avoids full vertex calculation, reduces the processing target to the key area, ensures that the morphing focuses on the real aging part, reduces the calculation amount. At the same time, the morphing interpolation point is determined based on the second vertex, so that the subsequent rejuvenation treatment conforms to the facial biomechanical characteristics, eliminates the morphing fault feeling, naturally transitions, accurately locates the aging area, and optimizes the morphing effect.

[0051] Each vertex in the three-dimensional face model corresponds to an aging feature quantification parameter, and accordingly, each first vertex in the target area also corresponds to an aging feature quantification parameter.

[0052] According to the aging feature quantification parameter, the second vertex to be rejuvenated is identified from the plurality of first vertices in the target area.

[0053] In some embodiments, the first vertex with the sagging defect quantification value is determined as the second vertex to be treated by the rejuvenation process, and the first vertex with the recess defect quantification value is determined as the second vertex to be treated by the rejuvenation process. The first vertex with the normal value is a normal vertex, which does not need to be treated by the rejuvenation process and is not determined as the second vertex.

[0054] In some embodiments, the aging feature quantification parameter of the second vertex is updated in real time under the influence of the rejuvenation process. The update to the normal value is the ideal processing result of the rejuvenation process.

[0055] In some embodiments, the second vertex is divided into at least one feature cluster by spatial clustering, the distance weight between the vertices in each feature cluster is calculated, the interpolation distance is determined according to the distance weight, and the morphing interpolation point located at a non-vertex position is generated. By automatically generating the morphing interpolation point from the selected second vertex, the unnatural local morphing problem is solved by adjusting the position of the morphing interpolation point, ensuring natural morphing, avoiding distortion or boundary fault caused by rejuvenation processing only on the second vertex, and eliminating the "step effect" of the morphing boundary.

[0056] Step 103, based on the rejuvenation processing intensity and the facial biomechanics constraint, respectively determining the update positions of each second vertex and each morphing interpolation point required for rejuvenation processing of the aging feature.

[0057] The rejuvenation processing intensity controls the degree of morphing, and the facial biomechanics constraint ensures the biological rationality of the morphing, thereby determining the update positions of the aging feature of each second vertex and the morphing interpolation point.

[0058] The facial biomechanics constraint includes a topological morphing constraint, a contour residual constraint, a feature point geometric configuration constraint, and an expression muscle movement constraint.

[0059] The topological morphing constraint is used to assist in generating the initial update position of the morphing interpolation point, and the natural morphing of the second vertex in the target region is realized through the update position of the morphing interpolation point.

[0060] The contour residual constraint is used to promote the natural connection between the target region and the surrounding region, and to ensure that the target region as a whole realizes natural morphing. For example, in the case of a global region as the target region, the change rate of the contour line such as the mandibular line and the zygomatic arch is controlled to avoid step-like faults. Based on the rejuvenation processing intensity and the topological morphing constraint, the first update position of each second vertex and the second update position of each morphing interpolation point can be calculated, and the residual of the region boundary of the target initial adjustment region formed by the first update position and the second update position and the region boundary of the original target region is used to determine the contour residual constraint.

[0061] Feature point geometric configuration constraints refer to the constraints formed by the geometric configuration of multiple inherent facial feature points in a 3D face model, ensuring the stability of inherent stable points and stabilizing the spatial configuration of the facial feature points.

[0062] Facial muscle movement constraints aim to make the facial expressions of the rejuvenated 3D face model consistent with the original expressions as much as possible, limiting non-physiological displacement of expression-related areas, and making it easier to see the rejuvenation effect under the same expression.

[0063] In some embodiments, determining the update positions of each second vertex and each deformation interpolation point required to rejuvenate the aging features based on the rejuvenation processing intensity and facial biomechanical constraints includes: calculating a first update position for mitigating the aging features of the second vertex based on the rejuvenation processing intensity, a first distance between each second vertex and the center point of the region, and the connection weight between each second vertex and its corresponding adjacent vertices; calculating a second update position for mitigating the aging features between the deformation interpolation point and its corresponding second vertex based on the first update position of the second vertex corresponding to each deformation interpolation point and the topological deformation constraints; and correcting the first update position and the second update position based on contour residual constraints, feature point geometric configuration constraints, and facial expression muscle movement constraints to obtain a third update position of each second vertex and a fourth update position of each deformation interpolation point for mitigating the aging features of the target region and for which the rejuvenation processing conforms to biomechanical characteristics.

[0064] This step achieves a gradient decay of deformation intensity from the core to the edge in the target area through a hierarchical calculation and transfer mechanism of second vertex displacement initialization → smooth transition of deformation interpolation points → multi-constraint collaborative correction, ensuring natural deformation in the target area and solving the problem of local swelling caused by traditional single-point deformation. Facial biomechanical constraints ensure that the displacement of tissues after deformation conforms to biological laws, thereby improving the naturalness of deformation and rejuvenation treatment.

[0065] The first updated position of the second vertex is calculated based on the youthening processing intensity, the first distance between each second vertex and the region center, and the connection weights between each second vertex and its corresponding adjacent vertices. The first updated position is represented by three-dimensional coordinates.

[0066] In some embodiments, calculating the first update position for mitigating the aging features of the second vertex based on the rejuvenation processing intensity, the first distance between each second vertex and the center point of the region, and the connection weights between each second vertex and its corresponding adjacent vertices includes: determining the local processing intensity of each second vertex based on the rejuvenation processing intensity and the first distance; and calculating the first update position based on the rejuvenation processing intensity, the local processing intensity, the connection weights, the current position of the second vertex, and the adjacent positions of the adjacent vertices.

[0067] This step combines global strength and distance factors to achieve gradient decay of deformation intensity. At the same time, by connecting weights and position parameters, it ensures that the displacement conforms to the biological laws of the face, thus obtaining the first updated position of the second vertex.

[0068] In some embodiments, the local intensity ratio corresponding to the second vertex is determined based on a first distance from the center point of the region. The local intensity ratio is related to the magnitude of the first distance; the smaller the first distance, the larger the local intensity ratio. The local intensity ratio is at most 1 and at least approximately 0 (not equal to 0). Multiplying the local intensity ratio by the youthening processing intensity yields the local processing intensity of the second vertex. When the target region covers the entire 3D face model, the local processing intensity of each second vertex is 1.

[0069] In some embodiments, the formula for calculating the first updated position of the second vertex is as follows: .

[0070] in, The first update position for the second vertex. This represents the current position of the second vertex. To enhance the intensity of the rejuvenation process, For localized treatment intensity, For the first The second vertex and its first The connection weights between adjacent vertices For the first The adjacent positions of each adjacent vertex. , A positive integer, representing the first... The number of adjacent vertices of the second vertex. , is a positive integer representing the number of second vertices.

[0071] The local processing intensity of the second vertex is calculated by the global rejuvenation processing intensity and a local distance factor (first distance), and meanwhile, the connection weight and the adjacent position are combined to realize the attenuation gradient of the morphing intensity from the center to the edge, avoid the boundary abrupt feeling caused by uniform morphing, maintain the continuity of the organization, and finally obtain the first updated position of the second vertex.

[0072] In some embodiments, to ensure the normal calculation of the first updated position, before the first updated position for mitigating the aging feature of the second vertex is calculated according to the rejuvenation processing intensity, the first distance between each second vertex and the region center point, and the connection weight between each second vertex and each corresponding adjacent vertex, the method further comprises: determining at least one adjacent vertex of each second vertex from the three-dimensional face model by a nearest neighbor algorithm; and calculating the connection weight between each second vertex and each corresponding adjacent vertex based on the second distance, the normal angle, and / or the curvature difference value between each second vertex and each adjacent vertex.

[0073] The adjacent vertices with strong spatial correlation with the second vertex are screened by the nearest neighbor algorithm, and the connection weight is determined based on geometric properties such as spatial distance, normal angle, and / or curvature difference. The connection weight represents the spatial correlation strength, provides a local constraint force transmission coefficient conforming to the biomechanical law, and ensures the cooperativity of vertex displacement in subsequent morphing processing.

[0074] At least one adjacent vertex of each second vertex is determined from a plurality of vertices of the three-dimensional face model by a nearest neighbor algorithm such as the K-nearest neighbor algorithm. The adjacent vertex is located within the target region and / or outside the target region.

[0075] In some embodiments, the connection weight is determined by a single value. The second distance between each second vertex and each corresponding adjacent vertex is calculated, and these second distances are normalized to obtain the connection weight between the second vertex and each corresponding adjacent vertex. Alternatively, the angle between the line connecting each second vertex and each corresponding adjacent vertex and the normal at the second vertex is calculated to obtain the normal angle, and these normal angles are normalized to obtain the connection weight between the second vertex and each corresponding adjacent vertex. Alternatively, the curvature difference value between each second vertex and each corresponding adjacent vertex is calculated, and these curvature difference values are normalized to obtain the connection weight between the second vertex and each corresponding adjacent vertex.

[0076] In some embodiments, the connection weight between each second vertex and its respective adjacent vertex is determined by normalizing the second distance and the normal angle between them, or by normalizing the second distance and the curvature difference between them, or by normalizing the normal angle and the curvature difference between them, or by normalizing the second distance, the normal angle and the curvature difference between them.

[0077] The connection weights between the second vertices and their adjacent vertices are integrated into an adjacency list or an adjacency matrix for storage, which facilitates quick access when calculating the updated positions.

[0078] In some embodiments, the first updated position of a second vertex is used as a position reference for a morphing interpolation point when calculating the second updated position of the morphing interpolation point. The second updated position of the morphing interpolation point is calculated by a Laplacian smoothing algorithm or a linear interpolation basis function, which satisfies the topological deformation constraint and ensures that the morphing interpolation point maintains the continuity of the local structure of the mesh after displacement, realizes smooth deformation transfer, and avoids local tearing or faulting.

[0079] In some embodiments, the first updated position and the second updated position are corrected by combining the contour residual constraint, the feature point geometric configuration constraint and the expression muscle movement constraint, which eliminates non-physiological deformation and obtains the third updated position of each second vertex and the fourth updated position of each morphing interpolation point. The third updated position and the fourth updated position can not only reduce the aging features of the target region, but also realize the rejuvenation treatment in accordance with the biomechanical properties.

[0080] In the above, the first updated position, the second updated position, the third updated position and the fourth updated position are all represented by three-dimensional coordinates.

[0081] Step 104: adjusting each second vertex and each morphing interpolation point to the corresponding updated position respectively to obtain an updated three-dimensional face model.

[0082] Adjusting each second vertex and each morphing interpolation point to the corresponding updated position realizes smooth deformation processing of the target region, which makes the sagging lifting and the concave filling, i.e. realizes the rejuvenation treatment of the target region. Accordingly, an updated three-dimensional face model, i.e. a rejuvenated three-dimensional face model, is obtained, which is a local rejuvenation or a global rejuvenation.

[0083] In some embodiments, adjusting each second vertex to a respective corresponding third updated position and adjusting each morphing interpolation point to a respective corresponding fourth updated position obtains an updated three-dimensional face model.

[0084] In some embodiments, performing weighted Laplacian smoothing or bilateral smoothing on the second vertices and the morphing interpolation points during position adjustment reduces noise and improves the smoothness of morphing transition.

[0085] Through iterative updating of positions, the layered calculation and the mathematical output of constraint optimization are converted into a visualized rejuvenation three-dimensional face model that exhibits more facial information, so that doctors and patients can intuitively understand the rejuvenation effect through the model, thereby determining a suitable rejuvenation plan, which has excellent visibility and practicality.

[0086] In the embodiments of the present application, based on the rejuvenation area information, the rejuvenation processing intensity and the facial biomechanical constraints, the displacement amount of each second vertex and each morphing interpolation point in the target area to be rejuvenated, i.e., the updated position, is accurately calculated, the position of the second vertex and the morphing interpolation point is adjusted, an updated three-dimensional face model is obtained, and the rejuvenation processing of the aging features in the target area in the three-dimensional face model is realized. The position adjustment process converts the rejuvenation prediction from relying on the doctor's experience to draw a two-dimensional image to an objective three-dimensional modeling process based on biological parameters, promotes the transformation of facial rejuvenation prediction from experience-driven to data-driven, and intuitively displays more rejuvenation facial details through the updated three-dimensional face model.

[0087] Referring to Figure 2 , Figure 2 is a flow of a three-dimensional face rejuvenation processing method provided by the embodiments of the present application Figure 2 . As shown in Figure 2 , a three-dimensional face rejuvenation processing method includes the following steps: Step 201, obtaining rejuvenation area information and rejuvenation processing intensity; the rejuvenation area information corresponds to a target area to be rejuvenated in a three-dimensional face model, and the target area includes a plurality of first vertices.

[0088] The implementation process of this step is the same as that of step 101 in the foregoing embodiments, which will not be described here again.

[0089] Step 202, determining at least one second vertex corresponding to an aging feature from the plurality of first vertices in the target area, and determining at least one morphing interpolation point in the target area based on the second vertex.

[0090] The implementation process of this step is the same as that of step 102 in the foregoing embodiments, which will not be described here again.

[0091] In step 203, based on the rejuvenation processing intensity and the facial biomechanics constraint, the update positions of each second vertex and each morphing interpolation point for rejuvenating the aging features are determined respectively.

[0092] The implementation process of this step is the same as that of step 103 in the foregoing embodiments, which will not be described here again.

[0093] In step 204, each second vertex and each morphing interpolation point are adjusted to the corresponding update position to obtain an updated three-dimensional face model.

[0094] The implementation process of this step is the same as that of step 104 in the foregoing embodiments, which will not be described here again.

[0095] In step 205, the updated three-dimensional face model is subjected to aging detection to obtain aging detection information.

[0096] The topological connection of the updated three-dimensional face model is similar to that of the three-dimensional face model. When calculating the update position, the feature point geometric configuration constraint is used to ensure that the feature point geometric configuration of the updated three-dimensional face model is the same as that of the three-dimensional face model. That is, the topological connection relationship and the feature point geometric configuration of the updated three-dimensional face model and the three-dimensional face reference model are basically the same, thereby forming a vertex mapping relationship of one-to-one correspondence between the vertices of the updated three-dimensional face model and the three-dimensional face reference model.

[0097] In some embodiments, the aging detection of the updated three-dimensional face model is realized by using the three-dimensional face reference model, that is, the aging detection is realized under the same detection standard, which improves the information comparability of the updated three-dimensional face model and the three-dimensional face model, and the detection is superior to the traditional subjective evaluation.

[0098] Through the aging detection, the aging detection information of each third vertex in the updated three-dimensional face model is obtained, and the aging detection information includes the aging feature quantitative parameter.

[0099] In step 206, based on the aging detection information, the updated three-dimensional face model is subjected to color mapping to generate an aging distribution three-dimensional color spectrum model.

[0100] The color rendering is performed on the updated three-dimensional face model to improve the visual effect.

[0101] In some embodiments, the rendering color of the third vertex with the concave defect is a warm color tone, the rendering color of the third vertex with the sagging defect is a cold color tone, and the rendering color of the third vertex without the concave defect and the sagging defect is a neutral color.

[0102] In some embodiments, for a third vertex with a concave defect or a sag defect, the concave grade or sag grade of the third vertex is determined based on its concave defect quantization value or sag defect quantization value. Warm colors of different saturations indicate third vertices with different concave grades, and cool colors of different saturations indicate third vertices with different sag grades.

[0103] At the same time, the color rendering range is determined based on the quantization value of the third vertex where there is a concave or drooping defect.

[0104] The updated 3D face model is color-rendered based on the determined rendering colors and color rendering range to obtain a 3D color spectrum model of aging distribution.

[0105] Step 207: Output the updated 3D face model and its corresponding aging detection information and 3D chromatographic model of aging distribution.

[0106] The updated 3D face model, along with its corresponding aging detection information and 3D chromatographic model of aging distribution, is output through an interactive interface for doctors and patients to view.

[0107] The effects of the rejuvenation process are showcased through various types of information and from multiple perspectives.

[0108] In some embodiments, a first grayscale model of the 3D face model and a second grayscale model of the updated 3D face model can be output together. For example... Figure 3 As shown, Figure 3 This is a schematic diagram of a three-dimensional face grayscale model before and after rejuvenation processing provided in an embodiment of this application. Figure 3 The 3D face models involved are non-realistic face models generated based on technologies such as artificial intelligence or deep learning.

[0109] In practical applications, users adjust the viewing angle using view controls. Figure 3 The grayscale models are shown from different perspectives. (a1), (b1), and (c1) correspond to the first grayscale model from the left, front, and right perspectives, respectively, and (a1), (b1), and (c1) are the left, front, and right views of the first grayscale model, respectively. (a2), (b2), and (c2) correspond to the second grayscale model from the left, front, and right perspectives, respectively, and (a2), (b2), and (c2) are the left, front, and right views of the second grayscale model, respectively.

[0110] In some embodiments, a first aging distribution 3D chromatographic model of the 3D face model and a second aging distribution 3D chromatographic model of the updated 3D face model can be output together. Figure 4 This is a schematic diagram of a three-dimensional chromatographic model of aging distribution before and after rejuvenation treatment provided in an embodiment of this application. Figure 4The three-dimensional face model involved is a non-real face model generated based on artificial intelligence or deep learning technology.

[0111] In actual application, the user adjusts the viewing angle through the view control, and views the aging condition from different viewing angles. Figure 4 The aging distribution three-dimensional chromatogram model under different viewing angles is shown. (d1), (e1), (f1) correspond to the first aging distribution three-dimensional chromatogram model under the left viewing angle, the front viewing angle, and the right viewing angle, respectively, and (d1), (e1), (f1) are the left view, the front view, and the right view of the first aging distribution three-dimensional chromatogram model, respectively. (d2), (e2), (f2) correspond to the second aging distribution three-dimensional chromatogram model under the left viewing angle, the front viewing angle, and the right viewing angle, respectively, and (d2), (e2), (f2) are the left view, the front view, and the right view of the second aging distribution three-dimensional chromatogram model, respectively.

[0112] In Figure 4 , different saturation warm colors (red and yellow), neutral colors (green), and different saturation cold colors (dark blue and light blue) are used to mark the facial regions in different aging states. The green region is the facial region without sagging defects and drooping defects, the red region is the facial region with secondary sagging, the yellow region is the facial region with primary sagging, the light blue region is the facial region with primary drooping, and the dark blue region is the facial region with secondary drooping. Among them, the sagging degree of secondary sagging is greater than that of primary sagging, and the drooping degree of secondary drooping is greater than that of primary drooping.

[0113] Based on Figure 3 and Figure 4 , the rejuvenation effect can be clearly and intuitively understood, that is, after rejuvenation treatment, the aging features are reduced, for example, Figure 4 In the second aging distribution three-dimensional chromatogram model, the warm color region indicating the sagging defect and the cold color region indicating the drooping defect are significantly reduced compared with the first aging distribution three-dimensional chromatogram model.

[0114] In some embodiments, the area proportion of each type of color marking region in the aging distribution three-dimensional chromatogram model is determined, and based on the area proportion of each type of color marking region and the scoring weight coefficient corresponding to each type of color, the aging comprehensive score of the model is calculated. Based on this method, the first aging comprehensive score of the three-dimensional face model and the second aging comprehensive score of the updated three-dimensional face model are obtained and output through the interactive interface, which objectively evaluates the model aging score and is more accurate and has reference value.

[0115] In some embodiments, the user can perform rejuvenation treatment again based on the updated three-dimensional face model, and in the case of ensuring the safety of the patient's face, the patient's rejuvenation treatment demand is achieved as much as possible.

[0116] In the embodiments of the present application, after adjusting the positions of the second vertices and the deformation interpolation points, an updated three-dimensional face model, i.e., a rejuvenation three-dimensional face model, is obtained, aging detection is performed on the rejuvenation three-dimensional face model, and aging detection information and an aging distribution three-dimensional chromatographic model are generated, which are output together with the updated three-dimensional face model, so as to realize accurate quantitative evaluation and visual presentation of the rejuvenation processing effect.

[0117] Referring to Figure 5 , Figure 5 is a structural diagram of a three-dimensional face rejuvenation processing system provided by the embodiments of the present application, and only parts related to the embodiments of the present application are shown for ease of description.

[0118] The three-dimensional face rejuvenation processing system 500 includes an acquisition module 501, a first determination module 502, a second determination module 503, and an adjustment module 504.

[0119] The acquisition module 501 is configured to acquire rejuvenation region information and rejuvenation processing intensity; the rejuvenation region information corresponds to a target region to be rejuvenated in a three-dimensional face model, and the target region includes a plurality of first vertices.

[0120] The first determination module 502 is configured to determine at least one second vertex corresponding to an aging feature from the plurality of first vertices in the target region, and determine at least one deformation interpolation point in the target region based on the second vertex.

[0121] The second determination module 503 is configured to determine, based on the rejuvenation processing intensity and a facial biomechanics constraint, an updated position of each second vertex and each deformation interpolation point required for rejuvenation processing of the aging feature.

[0122] The adjustment module 504 is configured to adjust each second vertex and each deformation interpolation point to the corresponding updated position, to obtain an updated three-dimensional face model.

[0123] In some embodiments, the system further includes a model preprocessing module configured to: perform aging detection on the three-dimensional face model to obtain an aging feature quantitative parameter of each vertex in the three-dimensional face model; the aging feature quantitative parameter is a sag defect indicator value, a droop defect indicator value, or a normal value, and the aging feature quantitative parameter is used to determine the second vertex; store each aging feature quantitative parameter as a custom attribute field of the corresponding vertex in the three-dimensional face model; any second vertex in the three-dimensional face model has the sag defect indicator value or the droop defect indicator value.

[0124] In some embodiments, the obtaining module is specifically configured to: determine the target region selected by the user in the three-dimensional face model based on the user's selection operation instruction, and accordingly determine the center point position of the region center point of the target region, to obtain the rejuvenation region information; obtain the real-time processing intensity as the rejuvenation processing intensity corresponding to the target region.

[0125] In some embodiments, the second determining module is specifically configured to: calculate a first updated position for mitigating the aging feature of each second vertex according to the rejuvenation processing intensity, the first distance between each second vertex and the region center point, and the connection weight between each second vertex and each adjacent vertex corresponding thereto; calculate a second updated position for mitigating the aging feature between each morphing interpolation point and the second vertex corresponding thereto based on the first updated position of the second vertex corresponding to each morphing interpolation point and the topological deformation constraint; correct the first updated position and the second updated position based on the contour residual constraint, the feature point geometric configuration constraint, and the expression muscle movement constraint, to obtain a third updated position of each second vertex for mitigating the aging feature of the target region and a fourth updated position of each morphing interpolation point for rejuvenation processing in accordance with the biomechanical characteristics.

[0126] In some embodiments, the second determining module is further configured to: determine at least one adjacent vertex of each second vertex from the three-dimensional face model by a nearest neighbor algorithm; calculate the connection weight between each second vertex and each adjacent vertex corresponding thereto based on the second distance, the normal angle, and / or the curvature difference value between each second vertex and each adjacent vertex.

[0127] In some embodiments, the second determining module is further configured to: determine a local processing intensity of each second vertex according to the rejuvenation processing intensity and the first distance; calculate the first updated position based on the rejuvenation processing intensity, the local processing intensity, the connection weight, the current position of the second vertex, and the adjacent position of the adjacent vertex.

[0128] In some embodiments, the system further comprises an output processing module configured to: perform aging detection on the updated three-dimensional face model to obtain aging detection information; Based on the aging detection information, color mapping is performed on the updated three-dimensional face model to generate an aging distribution three-dimensional color spectrum model. The updated three-dimensional face model, the corresponding aging detection information and the aging distribution three-dimensional color spectrum model are outputted.

[0129] The three-dimensional face rejuvenation processing system provided by the embodiments of the present application can implement each process of the embodiments of the three-dimensional face rejuvenation processing method described above and achieve the same technical effects. To avoid repetition, the details are not described herein.

[0130] Figure 6 is a structural diagram of an electronic device provided by an embodiment of the present application. As shown in the diagram, the electronic device 6 of the embodiment includes at least one processor 60 (only one is shown in the figure), a memory 61, and a computer program 62 stored in the memory 61 and executable on the at least one processor 60, wherein the processor 60 implements the steps in any of the method embodiments described above when executing the computer program 62. Figure 6

[0131] The electronic device 6 can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The electronic device 6 can include, but is not limited to, the processor 60 and the memory 61. Those skilled in the art can understand that the electronic device 6 is only an example of the electronic device 6 and does not constitute a limitation on the electronic device 6, and can include more or fewer components than those shown in the diagram, or combine certain components, or different components, for example, the electronic device can also include an input / output device, a network access device, a bus, etc. Figure 6 The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0132] The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0133] ​The memory 61 can be an internal storage unit of the electronic device 6, for example, a hard disk or a memory of the electronic device 6. The memory 61 can also be an external storage device of the electronic device 6, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 6. Further, the memory 61 can also include both the internal storage unit and the external storage device of the electronic device 6. The memory 61 is used to store the computer program and other programs and data required by the electronic device. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0134] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is exemplified, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for easy distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0135] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0136] Those of ordinary skill in the art can appreciate that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the application.

[0137] In the embodiments of the present application, it should be understood that the disclosed system / electronic device and method can be implemented in other manners. For example, the embodiments of the system / electronic device described above are merely schematic. For example, the division of the modules or units is only a logical function division. There can be another division manner for the actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different units, can be indirect couplings or communication connections through some interfaces, and electrical, mechanical or other forms.

[0138] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0139] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0140] The integrated module / unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of the above-mentioned various method embodiments can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer readable medium can include appropriate contents according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0141] The application can realize all or part of the processes in the above-mentioned embodiment methods, and can also be realized by a computer program product. When the computer program product runs on an electronic device, the electronic device is caused to perform the steps in the above-mentioned various method embodiments.

[0142] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents. The modifications or replacements do not change the essence of the corresponding technical solutions, and should be included in the protection scope of the present application.

Claims

1. A three-dimensional facial rejuvenation method, characterized in that, include: Obtain information on youth-oriented areas and the intensity of youth-oriented treatments; The rejuvenation region information corresponds to the target region to be rejuvenationd in the 3D face model, and the target region includes multiple first vertices; Determine at least one second vertex corresponding to the aging feature from a plurality of first vertices in the target region, and determine at least one deformation interpolation point in the target region based on the second vertex; Based on the rejuvenation processing intensity and facial biomechanical constraints, the update positions of each second vertex and each deformation interpolation point required to rejuvenate the aging features are determined respectively. Each of the second vertices and each of the deformation interpolation points are adjusted to the corresponding update positions to obtain the updated 3D face model.

2. The method according to claim 1, characterized in that, Before obtaining the information on the youthful region and the intensity of the youthful processing, the process also includes: Aging detection is performed on the three-dimensional face model to obtain aging feature quantification parameters for each vertex in the three-dimensional face model; the aging feature quantification parameters are indentation defect indication values, sagging defect indication values, or normal values, and the aging feature quantification parameters are used to determine the second vertex; Each of the aging feature quantization parameters is stored as a custom attribute field of the corresponding vertex in the three-dimensional face model; any second vertex in the three-dimensional face model has the indentation defect indication value or the sagging defect indication value.

3. The method according to claim 1, characterized in that, The acquisition of youthful region information and youthful processing intensity includes: Based on the user's selection operation command, the target area selected by the user in the three-dimensional face model is determined, and the center point position of the center point of the target area is determined accordingly to obtain the youthful area information; The real-time processing intensity is obtained as the rejuvenation processing intensity corresponding to the target region.

4. The method according to claim 3, characterized in that, The step of determining the update positions of each second vertex and each deformation interpolation point required for rejuvenating the aging features based on the rejuvenation processing intensity and facial biomechanical constraints includes: Based on the rejuvenation intensity, the first distance between each second vertex and the center point of the region, and the connection weight between each second vertex and its corresponding neighboring vertices, calculate the first update position for mitigating the aging features of the second vertex; Based on the first update position of the second vertex corresponding to each deformation interpolation point and the topological deformation constraint, a second update position for mitigating the aging characteristics between the deformation interpolation point and its corresponding second vertex is calculated. Based on contour residual constraints, feature point geometric configuration constraints, and facial muscle movement constraints, the first update position and the second update position are corrected to obtain the third update position of each of the second vertices and the fourth update position of each of the deformation interpolation points, which are used to reduce the aging characteristics of the target region and the rejuvenation process conforms to biomechanical characteristics.

5. The method according to claim 4, characterized in that, Before calculating the first update position for mitigating the aging features of the second vertex based on the rejuvenation processing intensity, the first distance between each second vertex and the center point of the region, and the connection weights between each second vertex and its corresponding neighboring vertices, the method further includes: Using a nearest neighbor algorithm, at least one of the adjacent vertices of each second vertex is determined from the three-dimensional face model; Based on the second distance, normal angle, and / or curvature difference between each second vertex and each of the adjacent vertices, the connection weight between each second vertex and its corresponding adjacent vertices is calculated.

6. The method according to any one of claims 4 or 5, characterized in that, The step of calculating the first update position for mitigating the aging features of the second vertex based on the rejuvenation processing intensity, the first distance between each second vertex and the center point of the region, and the connection weights between each second vertex and its corresponding neighboring vertices includes: The local processing intensity of each second vertex is determined based on the rejuvenation processing intensity and the first distance; The first update position is calculated based on the youthening processing intensity, the local processing intensity, the connection weight, the current position of the second vertex, and the adjacent positions of the adjacent vertices.

7. The method according to claim 1, characterized in that, After adjusting each of the second vertices and each of the deformation interpolation points to the corresponding updated positions to obtain the updated 3D face model, the method further includes: Aging detection is performed on the updated 3D face model to obtain aging detection information; Based on the aging detection information, color mapping is performed on the updated 3D face model to generate a 3D chromatographic model of aging distribution. The updated 3D face model, its corresponding aging detection information, and the 3D chromatographic model of aging distribution are output.

8. A three-dimensional facial rejuvenation system, characterized in that, include: The acquisition module is used to acquire information on youth-rejuvenated areas and the intensity of youth-rejuvenation treatment. The rejuvenation region information corresponds to the target region to be rejuvenationd in the 3D face model, and the target region includes multiple first vertices; The first determining module is used to determine at least one second vertex corresponding to the aging feature from a plurality of first vertices in the target region, and to determine at least one deformation interpolation point in the target region based on the second vertex; The second determining module is used to determine the update positions of each of the second vertices and each of the deformation interpolation points required to rejuvenate the aging features based on the rejuvenation processing intensity and facial biomechanical constraints. The adjustment module is used to adjust each of the second vertices and each of the deformation interpolation points to the corresponding update positions to obtain the updated three-dimensional face model.

9. An electronic device, characterized in that, The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device performs the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, Includes a computer program, which, when run, causes the method as described in any one of claims 1 to 7 to be performed.

Images